RL • Score 85
TRACE: Capability-Targeted Agentic Training
arXiv:2604.05336v1 Announce Type: new
Abstract: Large Language Models (LLMs) deployed in agentic environments must exercise multiple capabilities across different task instances, where a capability is performing one or more actions in a trajectory that are necessary for successfully solving a subset of tasks in the environment. Many existing approaches either rely on synthetic training data that is not targeted to the model's actual capability deficits in the target environment or train directly on the target environment, where the model needs to implicitly learn the capabilities across tasks. We introduce TRACE (Turning Recurrent Agent failures into Capability-targeted training Environments), an end-to-end system for environment-specific agent self-improvement. TRACE contrasts successful and failed trajectories to automatically identify lacking capabilities, synthesizes a targeted training environment for each that rewards whether the capability was exercised, and trains a LoRA adapter via RL on each synthetic environment, routing to the relevant adapter at inference. Empirically, TRACE generalizes across different environments, improving over the base agent by +14.1 points on $\tau^2$-bench (customer service) and +7 perfect scores on ToolSandbox (tool use), outperforming the strongest baseline by +7.4 points and +4 perfect scores, respectively. Given the same number of rollouts, TRACE scales more efficiently than baselines, outperforming GRPO and GEPA by +9.2 and +7.4 points on $\tau^2$-bench.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writing
arXiv:2604.05018v1 Announce Type: new
Abstract: Synthesizing unstructured research materials into manuscripts is an essential yet under-explored challenge in AI-driven scientific discovery. Existing autonomous writers are rigidly coupled to specific experimental pipelines, and produce superficial literature reviews. We introduce PaperOrchestra, a multi-agent framework for automated AI research paper writing. It flexibly transforms unconstrained pre-writing materials into submission-ready LaTeX manuscripts, including comprehensive literature synthesis and generated visuals, such as plots and conceptual diagrams. To evaluate performance, we present PaperWritingBench, the first standardized benchmark of reverse-engineered raw materials from 200 top-tier AI conference papers, alongside a comprehensive suite of automated evaluators. In side-by-side human evaluations, PaperOrchestra significantly outperforms autonomous baselines, achieving an absolute win rate margin of 50%-68% in literature review quality, and 14%-38% in overall manuscript quality.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Instruction-Tuned LLMs for Parsing and Mining Unstructured Logs on Leadership HPC Systems
arXiv:2604.05168v1 Announce Type: new
Abstract: Leadership-class HPC systems generate massive volumes of heterogeneous, largely unstructured system logs. Because these logs originate from diverse software, hardware, and runtime layers, they exhibit inconsistent formats, making structure extraction and pattern discovery extremely challenging. Therefore, robust log parsing and mining is critical to transform this raw telemetry into actionable insights that reveal operational patterns, diagnose anomalies, and enable reliable, efficient, and scalable system analysis. Recent advances in large language models (LLMs) offer a promising new direction for automated log understanding in leadership-class HPC environments.
To capitalize on this opportunity, we present a domain-adapted, instruction-following, LLM-driven framework that leverages chain-of-thought (CoT) reasoning to parse and structure HPC logs with high fidelity. Our approach combines domain-specific log-template data with instruction-tuned examples to fine-tune an 8B-parameter LLaMA model tailored for HPC log analysis. We develop a hybrid fine-tuning methodology that adapts a general-purpose LLM to domain-specific log data, enabling privacy-preserving, locally deployable, fast, and energy-efficient log-mining approach. We conduct experiments on a diverse set of log datasets from the LogHub repository. The evaluation confirms that our approach achieves parsing accuracy on par with significantly larger models, such as LLaMA 70B and Anthropic's Claude. We further validate the practical utility of our fine-tuned LLM model by parsing over 600 million production logs from the Frontier supercomputer over a four-week window, uncovering critical patterns in temporal dynamics, node-level anomalies, and workload-error log correlations.
Fonte: arXiv cs.AI
RL • Score 85
Learning to Focus: CSI-Free Hierarchical MARL for Reconfigurable Reflectors
arXiv:2604.05165v1 Announce Type: new
Abstract: Reconfigurable Intelligent Surfaces (RIS) has a potential to engineer smart radio environments for next-generation millimeter-wave (mmWave) networks. However, the prohibitive computational overhead of Channel State Information (CSI) estimation and the dimensionality explosion inherent in centralized optimization severely hinder practical large-scale deployments. To overcome these bottlenecks, we introduce a ``CSI-free" paradigm powered by a Hierarchical Multi-Agent Reinforcement Learning (HMARL) architecture to control mechanically reconfigurable reflective surfaces. By substituting pilot-based channel estimation with accessible user localization data, our framework leverages spatial intelligence for macro-scale wave propagation management. The control problem is decomposed into a two-tier neural architecture: a high-level controller executes temporally extended, discrete user-to-reflector allocations, while low-level controllers autonomously optimize continuous focal points utilizing Multi-Agent Proximal Policy Optimization (MAPPO) under a Centralized Training with Decentralized Execution (CTDE) scheme. Comprehensive deterministic ray-tracing evaluations demonstrate that this hierarchical framework achieves massive RSSI improvements of up to 7.79 dB over centralized baselines. Furthermore, the system exhibits robust multi-user scalability and maintains highly resilient beam-focusing performance under practical sub-meter localization tracking errors. By eliminating CSI overhead while maintaining high-fidelity signal redirection, this work establishes a scalable and cost-effective blueprint for intelligent wireless environments.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
Adaptive Serverless Resource Management via Slot-Survival Prediction and Event-Driven Lifecycle Control
arXiv:2604.05465v1 Announce Type: new
Abstract: Serverless computing eliminates infrastructure management overhead but introduces significant challenges regarding cold start latency and resource utilization. Traditional static resource allocation often leads to inefficiencies under variable workloads, resulting in performance degradation or excessive costs. This paper presents an adaptive engineering framework that optimizes serverless performance through event-driven architecture and probabilistic modeling. We propose a dual-strategy mechanism that dynamically adjusts idle durations and employs an intelligent request waiting strategy based on slot survival predictions. By leveraging sliding window aggregation and asynchronous processing, our system proactively manages resource lifecycles. Experimental results show that our approach reduces cold starts by up to 51.2% and improves cost-efficiency by nearly 2x compared to baseline methods in multi-cloud environments.
Fonte: arXiv cs.AI
Privacy/Security/Fairness • Score 85
From Governance Norms to Enforceable Controls: A Layered Translation Method for Runtime Guardrails in Agentic AI
arXiv:2604.05229v1 Announce Type: new
Abstract: Agentic AI systems plan, use tools, maintain state, and produce multi-step trajectories with external effects. Those properties create a governance problem that differs materially from single-turn generative AI: important risks emerge dur- ing execution, not only at model development or deployment time. Governance standards such as ISO/IEC 42001, ISO/IEC 23894, ISO/IEC 42005, ISO/IEC 5338, ISO/IEC 38507, and the NIST AI Risk Management Framework are therefore highly relevant to agentic AI, but they do not by themselves yield implementable runtime guardrails. This paper proposes a layered translation method that connects standards-derived governance objectives to four control layers: governance objectives, design- time constraints, runtime mediation, and assurance feedback. It distinguishes governance objectives, technical controls, runtime guardrails, and assurance evidence; introduces a control tuple and runtime-enforceability rubric for layer assignment; and demonstrates the method in a procurement-agent case study. The central claim is modest: standards should guide control placement across architecture, runtime policy, human escalation, and audit, while runtime guardrails are reserved for controls that are observable, determinate, and time-sensitive enough to justify execution-time intervention.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
MMORF: A Multi-agent Framework for Designing Multi-objective Retrosynthesis Planning Systems
arXiv:2604.05075v1 Announce Type: new
Abstract: Multi-objective retrosynthesis planning is a critical chemistry task requiring dynamic balancing of quality, safety, and cost objectives. Language model-based multi-agent systems (MAS) offer a promising approach for this task: leveraging interactions of specialized agents to incorporate multiple objectives into retrosynthesis planning. We present MMORF, a framework for constructing MAS for multi-objective retrosynthesis planning. MMORF features modular agentic components, which can be flexibly combined and configured into different systems, enabling principled evaluation and comparison of different system designs. Using MMORF, we construct two representative MAS: MASIL and RFAS. On a newly curated benchmark consisting of 218 multi-objective retrosynthesis planning tasks, MASIL achieves strong safety and cost metrics on soft-constraint tasks, frequently Pareto-dominating baseline routes, while RFAS achieves a 48.6% success rate on hard-constraint tasks, outperforming state-of-the-art baselines. Together, these results show the effectiveness of MMORF as a foundational framework for exploring MAS for multi-objective retrosynthesis planning. Code and data are available at https://anonymous.4open.science/r/MMORF/.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
EAGLE: Edge-Aware Graph Learning for Proactive Delivery Delay Prediction in Smart Logistics Networks
arXiv:2604.05254v1 Announce Type: new
Abstract: Modern logistics networks generate rich operational data streams at every warehouse node and transportation lane -- from order timestamps and routing records to shipping manifests -- yet predicting delivery delays remains predominantly reactive. Existing predictive approaches typically treat this problem either as a tabular classification task, ignoring network topology, or as a time-series anomaly detection task, overlooking the spatial dependencies of the supply chain graph. To bridge this gap, we propose a hybrid deep learning framework for proactive supply chain risk management. The proposed method jointly models temporal order-flow dynamics via a lightweight Transformer patch encoder and inter-hub relational dependencies through an Edge-Aware Graph Attention Network (E-GAT), optimized via a multi-task learning objective. Evaluated on the real-world DataCo Smart Supply Chain dataset, our framework achieves consistent improvements over baseline methods, yielding an F1-score of 0.8762 and an AUC-ROC of 0.9773. Across four independent random seeds, the framework exhibits a cross-seed F1 standard deviation of only 0.0089 -- a 3.8 times improvement over the best ablated variant -- achieving the strongest balance of predictive accuracy and training stability among all evaluated models.
Fonte: arXiv cs.AI
NLP/LLMs • Score 88
LatentAudit: Real-Time White-Box Faithfulness Monitoring for Retrieval-Augmented Generation with Verifiable Deployment
arXiv:2604.05358v1 Announce Type: new
Abstract: Retrieval-augmented generation (RAG) mitigates hallucination but does not eliminate it: a deployed system must still decide, at inference time, whether its answer is actually supported by the retrieved evidence. We introduce LatentAudit, a white-box auditor that pools mid-to-late residual-stream activations from an open-weight generator and measures their Mahalanobis distance to the evidence representation. The resulting quadratic rule requires no auxiliary judge model, runs at generation time, and is simple enough to calibrate on a small held-out set. We show that residual-stream geometry carries a usable faithfulness signal, that this signal survives architecture changes and realistic retrieval failures, and that the same rule remains amenable to public verification. On PubMedQA with Llama-3-8B, LatentAudit reaches 0.942 AUROC with 0.77,ms overhead. Across three QA benchmarks and five model families (Llama-2/3, Qwen-2.5/3, Mistral), the monitor remains stable; under a four-way stress test with contradictions, retrieval misses, and partial-support noise, it reaches 0.9566--0.9815 AUROC on PubMedQA and 0.9142--0.9315 on HotpotQA. At 16-bit fixed-point precision, the audit rule preserves 99.8% of the FP16 AUROC, enabling Groth16-based public verification without revealing model weights or activations. Together, these results position residual-stream geometry as a practical basis for real-time RAG faithfulness monitoring and optional verifiable deployment.
Fonte: arXiv cs.AI
RL • Score 85
Bypassing the CSI Bottleneck: MARL-Driven Spatial Control for Reflector Arrays
arXiv:2604.05162v1 Announce Type: new
Abstract: Reconfigurable Intelligent Surfaces (RIS) are pivotal for next-generation smart radio environments, yet their practical deployment is severely bottlenecked by the intractable computational overhead of Channel State Information (CSI) estimation. To bypass this fundamental physical-layer barrier, we propose an AI-native, data-driven paradigm that replaces complex channel modeling with spatial intelligence. This paper presents a fully autonomous Multi-Agent Reinforcement Learning (MARL) framework to control mechanically adjustable metallic reflector arrays. By mapping high-dimensional mechanical constraints to a reduced-order virtual focal point space, we deploy a Centralized Training with Decentralized Execution (CTDE) architecture. Using Multi-Agent Proximal Policy Optimization (MAPPO), our decentralized agents learn cooperative beam-focusing strategies relying on user coordinates, achieving CSI-free operation. High-fidelity ray-tracing simulations in dynamic non-line-of-sight (NLOS) environments demonstrate that this multi-agent approach rapidly adapts to user mobility, yielding up to a 26.86 dB enhancement over static flat reflectors and outperforming single-agent and hardware-constrained DRL baselines in both spatial selectivity and temporal stability. Crucially, the learned policies exhibit good deployment resilience, sustaining stable signal coverage even under 1.0-meter localization noise. These results validate the efficacy of MARL-driven spatial abstractions as a scalable, highly practical pathway toward AI-empowered wireless networks.
Fonte: arXiv cs.AI
RL • Score 85
OmniDiagram: Advancing Unified Diagram Code Generation via Visual Interrogation Reward
arXiv:2604.05514v1 Announce Type: new
Abstract: The paradigm of programmable diagram generation is evolving rapidly, playing a crucial role in structured visualization. However, most existing studies are confined to a narrow range of task formulations and language support, constraining their applicability to diverse diagram types. In this work, we propose OmniDiagram, a unified framework that incorporates diverse diagram code languages and task definitions. To address the challenge of aligning code logic with visual fidelity in Reinforcement Learning (RL), we introduce a novel visual feedback strategy named Visual Interrogation Verifies All (\textsc{Viva}). Unlike brittle syntax-based rules or pixel-level matching, \textsc{Viva} rewards the visual structure of rendered diagrams through a generative approach. Specifically, \textsc{Viva} actively generates targeted visual inquiries to scrutinize diagram visual fidelity and provides fine-grained feedback for optimization. This mechanism facilitates a self-evolving training process, effectively obviating the need for manually annotated ground truth code. Furthermore, we construct M3$^2$Diagram, the first large-scale diagram code generation dataset, containing over 196k high-quality instances. Experimental results confirm that the combination of SFT and our \textsc{Viva}-based RL allows OmniDiagram to establish a new state-of-the-art (SOTA) across diagram code generation benchmarks.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
HYVE: Hybrid Views for LLM Context Engineering over Machine Data
arXiv:2604.05400v1 Announce Type: new
Abstract: Machine data is central to observability and diagnosis in modern computing systems, appearing in logs, metrics, telemetry traces, and configuration snapshots. When provided to large language models (LLMs), this data typically arrives as a mixture of natural language and structured payloads such as JSON or Python/AST literals. Yet LLMs remain brittle on such inputs, particularly when they are long, deeply nested, and dominated by repetitive structure.
We present HYVE (HYbrid ViEw), a framework for LLM context engineering for inputs containing large machine-data payloads, inspired by database management principles. HYVE surrounds model invocation with coordinated preprocessing and postprocessing, centered on a request-scoped datastore augmented with schema information. During preprocessing, HYVE detects repetitive structure in raw inputs, materializes it in the datastore, transforms it into hybrid columnar and row-oriented views, and selectively exposes only the most relevant representation to the LLM. During postprocessing, HYVE either returns the model output directly, queries the datastore to recover omitted information, or performs a bounded additional LLM call for SQL-augmented semantic synthesis.
We evaluate HYVE on diverse real-world workloads spanning knowledge QA, chart generation, anomaly detection, and multi-step network troubleshooting. Across these benchmarks, HYVE reduces token usage by 50-90% while maintaining or improving output quality. On structured generation tasks, it improves chart-generation accuracy by up to 132% and reduces latency by up to 83%. Overall, HYVE offers a practical approximation to an effectively unbounded context window for prompts dominated by large machine-data payloads.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
RUQuant: Towards Refining Uniform Quantization for Large Language Models
arXiv:2604.04013v1 Announce Type: new
Abstract: The increasing size and complexity of large language models (LLMs) have raised significant challenges in deployment efficiency, particularly under resource constraints. Post-training quantization (PTQ) has emerged as a practical solution by compressing models without requiring retraining. While existing methods focus on uniform quantization schemes for both weights and activations, they often suffer from substantial accuracy degradation due to the non-uniform nature of activation distributions. In this work, we revisit the activation quantization problem from a theoretical perspective grounded in the Lloyd-Max optimality conditions. We identify the core issue as the non-uniform distribution of activations within the quantization interval, which causes the optimal quantization point under the Lloyd-Max criterion to shift away from the midpoint of the interval. To address this issue, we propose a two-stage orthogonal transformation method, RUQuant. In the first stage, activations are divided into blocks. Each block is mapped to uniformly sampled target vectors using composite orthogonal matrices, which are constructed from Householder reflections and Givens rotations. In the second stage, a global Householder reflection is fine-tuned to further minimize quantization error using Transformer output discrepancies. Empirical results show that our method achieves near-optimal quantization performance without requiring model fine-tuning: RUQuant achieves 99.8% of full-precision accuracy with W6A6 and 97% with W4A4 quantization for a 13B LLM, within approximately one minute. A fine-tuned variant yields even higher accuracy, demonstrating the effectiveness and scalability of our approach.
Fonte: arXiv cs.CL
RecSys • Score 85
Regime-Calibrated Demand Priors for Ride-Hailing Fleet Dispatch and Repositioning
arXiv:2604.03883v1 Announce Type: new
Abstract: Effective ride-hailing dispatch requires anticipating demand patterns that vary substantially across time-of-day, day-of-week, season, and special events. We propose a regime-calibrated approach that (i) segments historical trip data into demand regimes, (ii) matches the current operating period to the most similar historical analogues via a similarity ensemble combining Kolmogorov-Smirnov distance, Wasserstein-1 distance, feature distance, variance ratio, event pattern similarity, and temporal proximity, and (iii) uses the resulting calibrated demand prior to drive both an LP-based fleet repositioning policy and batch dispatch with Hungarian matching. In ablation, a distributional-only metric subset achieves the strongest mean-wait reduction, while the full ensemble is retained as a robustness-oriented default that preserves calendar and event context.
Evaluated on 5.2 million NYC TLC trips across 8 diverse scenarios (winter/summer, weekday/weekend/holiday, morning/evening/night) with 5 random seeds each, our method reduces mean rider wait times by 31.1% (bootstrap 95% CI: [26.5, 36.6]; Friedman chi-squared = 80.0, p = 4.25e-18; Cohen's d = 7.5-29.9). P95 wait drops 37.6% and the Gini coefficient of wait times improves from 0.441 to 0.409. The two contributions compose multiplicatively: calibration provides 16.9% reduction relative to the replay baseline; LP repositioning adds a further 15.5%. The approach requires no training, is deterministic and explainable, generalizes to Chicago (23.3% wait reduction using the NYC-built regime library without retraining), and is robust across fleet sizes (32-47% improvement for 0.5x-2.0x fleet scaling). Code is available at https://github.com/IndarKarhana/regime-calibrated-dispatch.
Fonte: arXiv cs.LG
RecSys • Score 85
AdaptFuse: Training-Free Sequential Preference Learning via Externalized Bayesian Inference
arXiv:2604.03925v1 Announce Type: new
Abstract: Large language models struggle to accumulate evidence across multiple rounds of user interaction, failing to update their beliefs in a manner consistent with Bayesian inference. Existing solutions require fine-tuning on sensitive user interaction data, limiting their applicability in privacy-conscious settings. We propose AdaptFuse, a training-free framework that externalizes probabilistic computation entirely from the LLM: a symbolic module maintains a Bayesian posterior over a discrete hypothesis set, while a frozen LLM contributes semantic reasoning via multi-sample Dirichlet aggregation. The two signals are combined through entropy-adaptive fusion, which automatically weights each source by its predictive confidence, shifting reliance from the LLM to the symbolic posterior as evidence accumulates. We evaluate across three domains: flight recommendation, hotel recommendation, and web shopping; on Gemma 2 9B, Llama 3 8B, and Qwen 2.5 7B. AdaptFuse consistently outperforms both prompting baselines and fine-tuned Bayesian Teaching models on all tasks, with accuracy improving monotonically over interaction rounds. These results demonstrate that principled inference-time algorithms can substitute for fine-tuning in personalized recommendation, without storing or training on sensitive user data. All the code and materials will be open-sourced.
Fonte: arXiv cs.CL
Privacy/Security/Fairness • Score 85
Your Agent is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs
arXiv:2604.03870v1 Announce Type: new
Abstract: The rapid deployment of open-source frameworks has significantly advanced the development of modern multi-agent systems. However, expanded action spaces, including uncontrolled privilege exposure and hidden inter-system interactions, pose severe security challenges. Specifically, Indirect Prompt Injections (IPI), which conceal malicious instructions within third-party content, can trigger unauthorized actions such as data exfiltration during normal operations. While current security evaluations predominantly rely on isolated single-turn benchmarks, the systemic vulnerabilities of these agents within complex dynamic environments remain critically underexplored. To bridge this gap, we systematically evaluate six defense strategies against four sophisticated IPI attack vectors across nine LLM backbones. Crucially, we conduct our evaluation entirely within dynamic multi-step tool-calling environments to capture the true attack surface of modern autonomous agents. Moving beyond binary success rates, our multidimensional analysis reveals a pronounced fragility. Advanced injections successfully bypass nearly all baseline defenses, and some surface-level mitigations even produce counterproductive side effects. Furthermore, while agents execute malicious instructions almost instantaneously, their internal states exhibit abnormally high decision entropy. Motivated by this latent hesitation, we investigate Representation Engineering (RepE) as a robust detection strategy. By extracting hidden states at the tool-input position, we revealed that the RepE-based circuit breaker successfully identifies and intercepts unauthorized actions before the agent commits to them, achieving high detection accuracy across diverse LLM backbones. This study exposes the limitations of current IPI defenses and provides a highly practical paradigm for building resilient multi-agent architectures.
Fonte: arXiv cs.CL
Theory/Optimization • Score 85
The Geometric Alignment Tax: Tokenization vs. Continuous Geometry in Scientific Foundation Models
arXiv:2604.04155v1 Announce Type: cross
Abstract: Foundation models for biology and physics optimize predictive accuracy, but their internal representations systematically fail to preserve the continuous geometry of the systems they model. We identify the root cause: the Geometric Alignment Tax, an intrinsic cost of forcing continuous manifolds through discrete categorical bottlenecks. Controlled ablations on synthetic dynamical systems demonstrate that replacing cross-entropy with a continuous head on an identical encoder reduces geometric distortion by up to 8.5x, while learned codebooks exhibit a non-monotonic double bind where finer quantization worsens geometry despite improving reconstruction. Under continuous objectives, three architectures differ by 1.3x; under discrete tokenization, they diverge by 3,000x. Evaluating 14 biological foundation models with rate-distortion theory and MINE, we identify three failure regimes: Local-Global Decoupling, Representational Compression, and Geometric Vacuity. A controlled experiment confirms that Evo 2's reverse-complement robustness on real DNA reflects conserved sequence composition, not learned symmetry. No model achieves simultaneously low distortion, high mutual information, and global coherence.
Fonte: arXiv stat.ML
Privacy/Security/Fairness • Score 85
RESIST: Resilient Decentralized Learning Using Consensus Gradient Descent
arXiv:2502.07977v2 Announce Type: replace-cross
Abstract: Empirical risk minimization (ERM) is a cornerstone of modern machine learning (ML), supported by advances in optimization theory that ensure efficient solutions with provable algorithmic and statistical learning rates. Privacy, memory, computation, and communication constraints necessitate data collection, processing, and storage across network-connected devices. In many applications, networks operate in decentralized settings where a central server cannot be assumed, requiring decentralized ML algorithms that are efficient and resilient. Decentralized learning, however, faces significant challenges, including an increased attack surface. This paper focuses on the man-in-the-middle (MITM) attack, wherein adversaries exploit communication vulnerabilities to inject malicious updates during training, potentially causing models to deviate from their intended ERM solutions. To address this challenge, we propose RESIST (Resilient dEcentralized learning using conSensus gradIent deScenT), an optimization algorithm designed to be robust against adversarially compromised communication links, where transmitted information may be arbitrarily altered before being received. Unlike existing adversarially robust decentralized learning methods, which often (i) guarantee convergence only to a neighborhood of the solution, (ii) lack guarantees of linear convergence for strongly convex problems, or (iii) fail to ensure statistical consistency as sample sizes grow, RESIST overcomes all three limitations. It achieves algorithmic and statistical convergence for strongly convex, Polyak-Lojasiewicz, and nonconvex ERM problems by employing a multistep consensus gradient descent framework and robust statistics-based screening methods to mitigate the impact of MITM attacks. Experimental results demonstrate the robustness and scalability of RESIST across attack strategies, screening methods, and loss functions.
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models
arXiv:2503.03206v3 Announce Type: replace-cross
Abstract: We develop an analytical framework for understanding how the generated distribution evolves during diffusion model training. Leveraging a Gaussian-equivalence principle, we solve the full-batch gradient-flow dynamics of linear and convolutional denoisers and integrate the resulting probability-flow ODE, yielding analytic expressions for the generated distribution. The theory exposes a universal inverse-variance spectral law: the time for an eigen- or Fourier mode to match its target variance scales as $\tau\propto\lambda^{-1}$, so high-variance (coarse) structure is mastered orders of magnitude sooner than low-variance (fine) detail. Extending the analysis to deep linear networks and circulant full-width convolutions shows that weight sharing merely multiplies learning rates -- accelerating but not eliminating the bias -- whereas local convolution introduces a qualitatively different bias. Experiments on Gaussian and natural-image datasets confirm the spectral law persists in deep MLP-based UNet. Convolutional U-Nets, however, display rapid near-simultaneous emergence of many modes, implicating local convolution in reshaping learning dynamics. These results underscore how data covariance governs the order and speed with which diffusion models learn, and they call for deeper investigation of the unique inductive biases introduced by local convolution.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
Diagonal-Tiled Mixed-Precision Attention for Efficient Low-Bit MXFP Inference
arXiv:2604.03950v1 Announce Type: new
Abstract: Transformer-based large language models (LLMs) have demonstrated remarkable performance across a wide range of real-world tasks, but their inference cost remains prohibitively high due to the quadratic complexity of attention and the memory bandwidth limitations of high-precision operations. In this work, we present a low-bit mixed-precision attention kernel using the microscaling floating-point (MXFP) data format, utilizing the computing capability on next-generation GPU architectures. Our Diagonal-Tiled Mixed-Precision Attention (DMA) incorporates two kinds of low-bit computation at the tiling-level, and is a delicate fused kernel implemented using Triton, exploiting hardware-level parallelism and memory efficiency to enable fast and efficient inference without compromising model performance. Extensive empirical evaluations on NVIDIA B200 GPUs show that our kernel maintains generation quality with negligible degradation, and meanwhile achieves significant speedup by kernel fusion. We release our code at https://github.com/yifu-ding/MP-Sparse-Attn.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Simple yet Effective: Low-Rank Spatial Attention for Neural Operators
arXiv:2604.03582v1 Announce Type: new
Abstract: Neural operators have emerged as data-driven surrogates for solving partial differential equations (PDEs), and their success hinges on efficiently modeling the long-range, global coupling among spatial points induced by the underlying physics. In many PDE regimes, the induced global interaction kernels are empirically compressible, exhibiting rapid spectral decay that admits low-rank approximations. We leverage this observation to unify representative global mixing modules in neural operators under a shared low-rank template: compressing high-dimensional pointwise features into a compact latent space, processing global interactions within it, and reconstructing the global context back to spatial points. Guided by this view, we introduce Low-Rank Spatial Attention (LRSA) as a clean and direct instantiation of this template. Crucially, unlike prior approaches that often rely on non-standard aggregation or normalization modules, LRSA is built purely from standard Transformer primitives, i.e., attention, normalization, and feed-forward networks, yielding a concise block that is straightforward to implement and directly compatible with hardware-optimized kernels. In our experiments, such a simple construction is sufficient to achieve high accuracy, yielding an average error reduction of over 17\% relative to second-best methods, while remaining stable and efficient in mixed-precision training.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression
arXiv:2604.03258v1 Announce Type: new
Abstract: Large language models (LLMs) have demonstrated impressive capabilities across various tasks, but the billion-scale parameters pose deployment challenges. Although existing methods attempt to reduce the scale of LLMs, they require either special hardware support or expensive post-training to maintain model quality. To facilitate efficient and affordable model slimming, we propose a novel training-free compression method for LLMs, named "SoLA", which leverages \textbf{So}ft activation sparsity and \textbf{L}ow-r\textbf{A}nk decomposition. SoLA can identify and retain a minority of components significantly contributing to inference, while compressing the majority through low-rank decomposition, based on our analysis of the activation pattern in the feed-forward network (FFN) of modern LLMs. To alleviate the decomposition loss, SoLA is equipped with an adaptive component-wise low-rank allocation strategy to assign appropriate truncation positions for different weight matrices. We conduct extensive experiments on LLaMA-2-7B/13B/70B and Mistral-7B models across a variety of benchmarks. SoLA exhibits remarkable improvement in both language modeling and downstream task accuracy without post-training. For example, with a 30\% compression rate on the LLaMA-2-70B model, SoLA surpasses the state-of-the-art method by reducing perplexity from 6.95 to 4.44 and enhancing downstream task accuracy by 10\%.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
DRAFT: Task Decoupled Latent Reasoning for Agent Safety
arXiv:2604.03242v1 Announce Type: new
Abstract: The advent of tool-using LLM agents shifts safety monitoring from output moderation to auditing long, noisy interaction trajectories, where risk-critical evidence is sparse-making standard binary supervision poorly suited for credit assignment. To address this, we propose DRAFT (Task Decoupled Latent Reasoning for Agent Safety), a latent reasoning framework that decouples safety judgment into two trainable stages: an Extractor that distills the full trajectory into a compact continuous latent draft, and a Reasoner that jointly attends to the draft and the original trajectory to predict safety. DRAFT avoids lossy explicit summarize-then-judge pipelines by performing evidence aggregation in latent space, enabling end-to-end differentiable training.Across benchmarks including ASSEBench and R-Judge, DRAFT consistently outperforms strong baselines, improving accuracy from 63.27% (LoRA) to 91.18% averaged over benchmarks, and learns more separable representations. Ablations demonstrate a clear synergy between the Extractor and the Reasoner.Overall, DRAFT suggests that continuous latent reasoning prior to readout is a practical path to robust agent safety under long-context supervision with sparse evidence.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Hardware-Oriented Inference Complexity of Kolmogorov-Arnold Networks
arXiv:2604.03345v1 Announce Type: new
Abstract: Kolmogorov-Arnold Networks (KANs) have recently emerged as a powerful architecture for various machine learning applications. However, their unique structure raises significant concerns regarding their computational overhead. Existing studies primarily evaluate KAN complexity in terms of Floating-Point Operations (FLOPs) required for GPU-based training and inference. However, in many latency-sensitive and power-constrained deployment scenarios, such as neural network-driven non-linearity mitigation in optical communications or channel state estimation in wireless communications, training is performed offline and dedicated hardware accelerators are preferred over GPUs for inference. Recent hardware implementation studies report KAN complexity using platform-specific resource consumption metrics, such as Look-Up Tables, Flip-Flops, and Block RAMs. However, these metrics require a full hardware design and synthesis stage that limits their utility for early-stage architectural decisions and cross-platform comparisons. To address this, we derive generalized, platform-independent formulae for evaluating the hardware inference complexity of KANs in terms of Real Multiplications (RM), Bit Operations (BOP), and Number of Additions and Bit-Shifts (NABS). We extend our analysis across multiple KAN variants, including B-spline, Gaussian Radial Basis Function (GRBF), Chebyshev, and Fourier KANs. The proposed metrics can be computed directly from the network structure and enable a fair and straightforward inference complexity comparison between KAN and other neural network architectures.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
From Model-Based Screening to Data-Driven Surrogates: A Multi-Stage Workflow for Exploring Stochastic Agent-Based Models
arXiv:2604.03350v1 Announce Type: new
Abstract: Systematic exploration of Agent-Based Models (ABMs) is challenged by the curse of dimensionality and their inherent stochasticity. We present a multi-stage pipeline integrating the systematic design of experiments with machine learning surrogates. Using a predator-prey case study, our methodology proceeds in two steps. First, an automated model-based screening identifies dominant variables, assesses outcome variability, and segments the parameter space. Second, we train Machine Learning models to map the remaining nonlinear interaction effects. This approach automates the discovery of unstable regions where system outcomes are highly dependent on nonlinear interactions between many variables. Thus, this work provides modelers with a rigorous, hands-off framework for sensitivity analysis and policy testing, even when dealing with high-dimensional stochastic simulators.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
BWTA: Accurate and Efficient Binarized Transformer by Algorithm-Hardware Co-design
arXiv:2604.03957v1 Announce Type: new
Abstract: Ultra low-bit quantization brings substantial efficiency for Transformer-based models, but the accuracy degradation and limited GPU support hinder its wide usage. In this paper, we analyze zero-point distortion in binarization and propose a Binary Weights & Ternary Activations (BWTA) quantization scheme, which projects tiny values to zero and preserves the accuracy of extremely low-bit models. For training, we propose Smooth Multi-Stage Quantization, combining a Levelwise Degradation Strategy and a Magnitude-Alignment Projection Factor to enable stable and fast convergence. For inference, we develop a BWTA MatMul CUDA kernel with instruction-level parallel bit-packing and comprehensive binary/ternary MatMul implementations for both linear and attention operators, allowing seamless integration across Transformer architectures. Experiments show that BWTA approaches full-precision performance for BERT, with an average 3.5% drop on GLUE and less than 2% drop on five tasks, and achieves comparable perplexity and accuracy for LLMs. In efficiency, it delivers 16 to 24 times kernel-level speedup over FP16 on NVIDIA GPUs, and 216 to 330 tokens/s end-to-end prefill speedup with lower memory footprint on LLMs. As an algorithm-hardware co-design, BWTA demonstrates practical, low-latency ultra-low-bit inference without sacrificing model quality.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Towards Intelligent Energy Security: A Unified Spatio-Temporal and Graph Learning Framework for Scalable Electricity Theft Detection in Smart Grids
arXiv:2604.03344v1 Announce Type: new
Abstract: Electricity theft and non-technical losses (NTLs) remain critical challenges in modern smart grids, causing significant economic losses and compromising grid reliability. This study introduces the SmartGuard Energy Intelligence System (SGEIS), an integrated artificial intelligence framework for electricity theft detection and intelligent energy monitoring. The proposed system combines supervised machine learning, deep learning-based time-series modeling, Non-Intrusive Load Monitoring (NILM), and graph-based learning to capture both temporal and spatial consumption patterns. A comprehensive data processing pipeline is developed, incorporating feature engineering, multi-scale temporal analysis, and rule-based anomaly labeling. Deep learning models, including Long Short-Term Memory (LSTM), Temporal Convolutional Networks (TCN), and Autoencoders, are employed to detect abnormal usage patterns. In parallel, ensemble learning methods such as Random Forest, Gradient Boosting, XGBoost, and LightGBM are utilized for classification. To model grid topology and spatial dependencies, Graph Neural Networks (GNNs) are applied to identify correlated anomalies across interconnected nodes. The NILM module enhances interpretability by disaggregating appliance-level consumption from aggregate signals. Experimental results demonstrate strong performance, with Gradient Boosting achieving a ROC-AUC of 0.894, while graph-based models attain over 96% accuracy in identifying high-risk nodes. The hybrid framework improves detection robustness by integrating temporal, statistical, and spatial intelligence. Overall, SGEIS provides a scalable and practical solution for electricity theft detection, offering high accuracy, improved interpretability, and strong potential for real-world smart grid deployment.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Importance Sparsification for Sinkhorn Algorithm
arXiv:2306.06581v2 Announce Type: replace
Abstract: Sinkhorn algorithm has been used pervasively to approximate the solution to optimal transport (OT) and unbalanced optimal transport (UOT) problems. However, its practical application is limited due to the high computational complexity. To alleviate the computational burden, we propose a novel importance sparsification method, called Spar-Sink, to efficiently approximate entropy-regularized OT and UOT solutions. Specifically, our method employs natural upper bounds for unknown optimal transport plans to establish effective sampling probabilities, and constructs a sparse kernel matrix to accelerate Sinkhorn iterations, reducing the computational cost of each iteration from $O(n^2)$ to $\widetilde{O}(n)$ for a sample of size $n$. Theoretically, we show the proposed estimators for the regularized OT and UOT problems are consistent under mild regularity conditions. Experiments on various synthetic data demonstrate Spar-Sink outperforms mainstream competitors in terms of both estimation error and speed. A real-world echocardiogram data analysis shows Spar-Sink can effectively estimate and visualize cardiac cycles, from which one can identify heart failure and arrhythmia. To evaluate the numerical accuracy of cardiac cycle prediction, we consider the task of predicting the end-systole time point using the end-diastole one. Results show Spar-Sink performs as well as the classical Sinkhorn algorithm, requiring significantly less computational time.
Fonte: arXiv stat.ML
RL • Score 85
When Adaptive Rewards Hurt: Causal Probing and the Switching-Stability Dilemma in LLM-Guided LEO Satellite Scheduling
arXiv:2604.03562v1 Announce Type: new
Abstract: Adaptive reward design for deep reinforcement learning (DRL) in multi-beam LEO satellite scheduling is motivated by the intuition that regime-aware reward weights should outperform static ones. We systematically test this intuition and uncover a switching-stability dilemma: near-constant reward weights (342.1 Mbps) outperform carefully-tuned dynamic weights (103.3+/-96.8 Mbps) because PPO requires a quasistationary reward signal for value function convergence. Weight adaptation-regardless of quality-degrades performance by repeatedly restarting convergence. To understand why specific weights matter, we introduce a single-variable causal probing method that independently perturbs each reward term by +/-20% and measures PPO response after 50k steps. Probing reveals counterintuitive leverage: a +20% increase in the switching penalty yields +157 Mbps for polar handover and +130 Mbps for hot-cold regimes-findings inaccessible to human experts or trained MLPs without systematic probing. We evaluate four MDP architect variants (fixed, rule-based, learned MLP, finetuned LLM) across known and novel traffic regimes. The MLP achieves 357.9 Mbps on known regimes and 325.2 Mbps on novel regimes, while the fine-tuned LLM collapses to 45.3+/-43.0 Mbps due to weight oscillation rather than lack of domain knowledge-output consistency, not knowledge, is the binding constraint. Our findings provide an empirically-grounded roadmap for LLM-DRL integration in communication systems, identifying where LLMs add irreplaceable value (natural language intent understanding) versus where simpler methods suffice.
Fonte: arXiv cs.AI
Applications • Score 85
Integrating Artificial Intelligence, Physics, and Internet of Things: A Framework for Cultural Heritage Conservation
arXiv:2604.03233v1 Announce Type: new
Abstract: The conservation of cultural heritage increasingly relies on integrating technological innovation with domain expertise to ensure effective monitoring and predictive maintenance. This paper presents a novel framework to support the preservation of cultural assets, combining Internet of Things (IoT) and Artificial Intelligence (AI) technologies, enhanced with the physical knowledge of phenomena. The framework is structured into four functional layers that permit the analysis of 3D models of cultural assets and elaborate simulations based on the knowledge acquired from data and physics. A central component of the proposed framework consists of Scientific Machine Learning, particularly Physics-Informed Neural Networks (PINNs), which incorporate physical laws into deep learning models. To enhance computational efficiency, the framework also integrates Reduced Order Methods (ROMs), specifically Proper Orthogonal Decomposition (POD), and is also compatible with classical Finite Element (FE) methods. Additionally, it includes tools to automatically manage and process 3D digital replicas, enabling their direct use in simulations. The proposed approach offers three main contributions: a methodology for processing 3D models of cultural assets for reliable simulation; the application of PINNs to combine data-driven and physics-based approaches in cultural heritage conservation; and the integration of PINNs with ROMs to efficiently model degradation processes influenced by environmental and material parameters. The reproducible and open-access experimental phase exploits simulated scenarios on complex and real-life geometries to test the efficacy of the proposed framework in each of its key components, allowing the possibility of dealing with both direct and inverse problems. Code availability: https://github.com/valc89/PhysicsInformedCulturalHeritage
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
From XAI to MLOps: Explainable Concept Drift Detection with Profile Drift Detection
arXiv:2412.11308v2 Announce Type: replace
Abstract: Predictive models often degrade in performance due to evolving data distributions, a phenomenon known as data drift. Among its forms, concept drift, where the relationship between explanatory variables and the response variable changes, is particularly challenging to detect and adapt to. Traditional drift detection methods often rely on metrics such as accuracy or marginal variable distributions, which may fail to capture subtle but important conceptual changes. This paper proposes a novel method, Profile Drift Detection (PDD), which enables both the detection of concept drift and an enhanced understanding of its underlying causes by leveraging an explainable AI tool: Partial Dependence Profiles (PDPs). PDD quantifies changes in PDPs through new drift metrics that are sensitive to shifts in the data stream while remaining computationally efficient. This approach is aligned with MLOps practices, emphasizing continuous model monitoring and adaptive retraining in dynamic environments. Experiments on synthetic and real-world datasets demonstrate that PDD outperforms existing methods by maintaining high predictive performance while effectively balancing sensitivity and stability in drift signals. The results highlight its suitability for real-time applications, and the paper concludes by discussing the method's advantages, limitations, and potential extensions to broader use cases.
Fonte: arXiv stat.ML
RecSys • Score 85
Supervised Dimensionality Reduction Revisited: Why LDA on Frozen CNN Features Deserves a Second Look
arXiv:2604.03928v1 Announce Type: new
Abstract: Effective ride-hailing dispatch requires anticipating demand patterns that vary substantially across time-of-day, day-of-week, season, and special events. We propose a regime-calibrated approach that (i) segments historical trip data into demand regimes, (ii) matches the current operating period to the most similar historical analogues via a six-metric similarity ensemble (Kolmogorov-Smirnov, Wasserstein-1, feature distance, variance ratio, event pattern, temporal proximity), and (iii) uses the resulting calibrated demand prior to drive both an LP-based fleet repositioning policy and batch dispatch with Hungarian matching. In ablation, a distributional-only subset is strongest on mean wait, while the full ensemble is retained as a robustness-oriented default.
Evaluated on 5.2 million NYC TLC trips across 8 diverse scenarios (winter/summer, weekday/weekend/holiday, morning/evening/night) with 5 random seeds each, our method reduces mean rider wait times by 31.1% (bootstrap 95% CI: [26.5, 36.6]%; Friedman chi-sq = 80.0, p = 4.25e-18; Cohen's d = 7.5-29.9 across scenarios). The improvement extends to the tail: P95 wait drops 37.6% and the Gini coefficient of wait times improves from 0.441 to 0.409 (7.3% relative). The two contributions compose multiplicatively and are independently validated: calibration provides 16.9% reduction; LP repositioning adds a further 15.5%. The approach requires no training, is deterministic and explainable, generalizes to Chicago (23.3% wait reduction via NYC-built regime library), and is robust across fleet sizes (32-47% improvement for 0.5-2x fleet scaling). We provide comprehensive ablation studies, formal statistical tests, and routing-fidelity validation with OSRM.
Fonte: arXiv cs.LG
RL • Score 85
Provable Multi-Task Reinforcement Learning: A Representation Learning Framework with Low Rank Rewards
arXiv:2604.03891v1 Announce Type: new
Abstract: Multi-task representation learning (MTRL) is an approach that learns shared latent representations across related tasks, facilitating collaborative learning that improves the overall learning efficiency. This paper studies MTRL for multi-task reinforcement learning (RL), where multiple tasks have the same state-action space and transition probabilities, but different rewards. We consider T linear Markov Decision Processes (MDPs) where the reward functions and transition dynamics admit linear feature embeddings of dimension d. The relatedness among the tasks is captured by a low-rank structure on the reward matrices. Learning shared representations across multiple RL tasks is challenging due to the complex and policy-dependent nature of data that leads to a temporal progression of error. Our approach adopts a reward-free reinforcement learning framework to first learn a data-collection policy. This policy then informs an exploration strategy for estimating the unknown reward matrices. Importantly, the data collected under this well-designed policy enable accurate estimation, which ultimately supports the learning of an near-optimal policy. Unlike existing approaches that rely on restrictive assumptions such as Gaussian features, incoherence conditions, or access to optimal solutions, we propose a low-rank matrix estimation method that operates under more general feature distributions encountered in RL settings. Theoretical analysis establishes that accurate low-rank matrix recovery is achievable under these relaxed assumptions, and we characterize the relationship between representation error and sample complexity. Leveraging the learned representation, we construct near-optimal policies and prove a regret bound. Experimental results demonstrate that our method effectively learns robust shared representations and task dynamics from finite data.
Fonte: arXiv cs.LG
Multimodal • Score 85
Solar-VLM: Multimodal Vision-Language Models for Augmented Solar Power Forecasting
arXiv:2604.04145v1 Announce Type: new
Abstract: Photovoltaic (PV) power forecasting plays a critical role in power system dispatch and market participation. Because PV generation is highly sensitive to weather conditions and cloud motion, accurate forecasting requires effective modeling of complex spatiotemporal dependencies across multiple information sources. Although recent studies have advanced AI-based forecasting methods, most fail to fuse temporal observations, satellite imagery, and textual weather information in a unified framework. This paper proposes Solar-VLM, a large-language-model-driven framework for multimodal PV power forecasting. First, modality-specific encoders are developed to extract complementary features from heterogeneous inputs. The time-series encoder adopts a patch-based design to capture temporal patterns from multivariate observations at each site. The visual encoder, built upon a Qwen-based vision backbone, extracts cloud-cover information from satellite images. The text encoder distills historical weather characteristics from textual descriptions. Second, to capture spatial dependencies across geographically distributed PV stations, a cross-site feature fusion mechanism is introduced. Specifically, a Graph Learner models inter-station correlations through a graph attention network constructed over a K-nearest-neighbor (KNN) graph, while a cross-site attention module further facilitates adaptive information exchange among sites. Finally, experiments conducted on data from eight PV stations in a northern province of China demonstrate the effectiveness of the proposed framework. Our proposed model is publicly available at https://github.com/rhp413/Solar-VLM.
Fonte: arXiv cs.AI
Vision • Score 85
Edge-Based Standing-Water Detection via FSM-Guided Tiering and Multi-Model Consensus
arXiv:2604.03308v1 Announce Type: new
Abstract: Standing water in agricultural fields threatens vehicle mobility and crop health. This paper presents a deployed edge architecture for standing-water detection using Raspberry-Pi-class devices with optional Jetson acceleration. Camera input and environmental sensors (humidity, pressure, temperature) are combined in a finite-state machine (FSM) that acts as the architectural decision engine. The FSM-guided control plane selects between local and offloaded inference tiers, trading accuracy, latency, and energy under intermittent connectivity and motion-dependent compute budgets. A multi-model YOLO ensemble provides image scores, while diurnal-baseline sensor fusion adjusts caution using environmental anomalies. All decisions are logged per frame, enabling bit-identical hardware-in-the-loop replays. Across ten configurations and sensor variants on identical field sequences with frame-level ground truth, we show that the combination of adaptive tiering, multi-model consensus, and diurnal sensor fusion improves flood-detection performance over static local baselines, uses less energy than a naive always-heavy offload policy, and maintains bounded tail latency in a real agricultural setting.
Fonte: arXiv cs.CV
Multimodal • Score 85
CoLA: Cross-Modal Low-rank Adaptation for Multimodal Downstream Tasks
arXiv:2604.03314v1 Announce Type: new
Abstract: Foundation models have revolutionized AI, but adapting them efficiently for multimodal tasks, particularly in dual-stream architectures composed of unimodal encoders, such as DINO and BERT, remains a significant challenge. Parameter-Efficient Fine-Tuning (PEFT) methods like Low-Rank Adaptation (LoRA) enable lightweight adaptation, yet they operate in isolation within each modality, limiting their ability in capturing cross-modal interactions. In this paper, we take a step in bridging this gap with Cross-Modal Low-Rank Adaptation (CoLA), a novel PEFT framework that extends LoRA by introducing a dedicated inter-modal adaptation pathway alongside the standard intra-modal one. This dual-path design enables CoLA to adapt unimodal foundation models to multimodal tasks effectively, without interference between modality-specific and cross-modal learning. We evaluate CoLA across a range of vision-language (RefCOCO, RefCOCO+, RefCOCOg) and audio-visual (AVE, AVS) benchmarks, where it consistently outperforms LORA, achieving a relative gain of around 3\% and 2\%, respectively, while maintaining parameter efficiency. Notably, CoLA enables the first multi-task PEFT framework for visual grounding, bridging a key gap in efficient multimodal adaptation.
Fonte: arXiv cs.CV
Theory/Optimization • Score 85
A Muon-Accelerated Algorithm for Low Separation Rank Tensor Generalized Linear Models
arXiv:2604.04726v1 Announce Type: new
Abstract: Tensor-valued data arise naturally in multidimensional signal and imaging problems, such as biomedical imaging. When incorporated into generalized linear models (GLMs), naive vectorization can destroy their multi-way structure and lead to high-dimensional, ill-posed estimation. To address this challenge, Low Separation Rank (LSR) decompositions reduce model complexity by imposing low-rank multilinear structure on the coefficient tensor. A representative approach for estimating LSR-based tensor GLMs (LSR-TGLMs) is the Low Separation Rank Tensor Regression (LSRTR) algorithm, which adopts block coordinate descent and enforces orthogonality of the factor matrices through repeated QR-based projections. However, the repeated projection steps can be computationally demanding and slow convergence. Motivated by the need for scalable estimation and classification from such data, we propose LSRTR-M, which incorporates Muon (MomentUm Orthogonalized by Newton-Schulz) updates into the LSRTR framework. Specifically, LSRTR-M preserves the original block coordinate scheme while replacing the projection-based factor updates with Muon steps. Across synthetic linear, logistic, and Poisson LSR-TGLMs, LSRTR-M converges faster in both iteration count and wall-clock time, while achieving lower normalized estimation and prediction errors. On the Vessel MNIST 3D task, it further improves computational efficiency while maintaining competitive classification performance.
Fonte: arXiv stat.ML
MLOps/Systems • Score 85
ActionNex: A Virtual Outage Manager for Cloud
arXiv:2604.03512v1 Announce Type: new
Abstract: Outage management in large-scale cloud operations remains heavily manual, requiring rapid triage, cross-team coordination, and experience-driven decisions under partial observability. We present \textbf{ActionNex}, a production-grade agentic system that supports end-to-end outage assistance, including real-time updates, knowledge distillation, and role- and stage-conditioned next-best action recommendations. ActionNex ingests multimodal operational signals (e.g., outage content, telemetry, and human communications) and compresses them into critical events that represent meaningful state transitions. It couples this perception layer with a hierarchical memory subsystem: long-term Key-Condition-Action (KCA) knowledge distilled from playbooks and historical executions, episodic memory of prior outages, and working memory of the live context. A reasoning agent aligns current critical events to preconditions, retrieves relevant memories, and generates actionable recommendations; executed human actions serve as an implicit feedback signal to enable continual self-evolution in a human-agent hybrid system. We evaluate ActionNex on eight real Azure outages (8M tokens, 4,000 critical events) using two complementary ground-truth action sets, achieving 71.4\% precision and 52.8-54.8\% recall. The system has been piloted in production and has received positive early feedback.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Profile-Then-Reason: Bounded Semantic Complexity for Tool-Augmented Language Agents
arXiv:2604.04131v1 Announce Type: new
Abstract: Large language model agents that use external tools are often implemented through reactive execution, in which reasoning is repeatedly recomputed after each observation, increasing latency and sensitivity to error propagation. This work introduces Profile--Then--Reason (PTR), a bounded execution framework for structured tool-augmented reasoning, in which a language model first synthesizes an explicit workflow, deterministic or guarded operators execute that workflow, a verifier evaluates the resulting trace, and repair is invoked only when the original workflow is no longer reliable. A mathematical formulation is developed in which the full pipeline is expressed as a composition of profile, routing, execution, verification, repair, and reasoning operators; under bounded repair, the number of language-model calls is restricted to two in the nominal case and three in the worst case. Experiments against a ReAct baseline on six benchmarks and four language models show that PTR achieves the pairwise exact-match advantage in 16 of 24 configurations. The results indicate that PTR is particularly effective on retrieval-centered and decomposition-heavy tasks, whereas reactive execution remains preferable when success depends on substantial online adaptation.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
DARE: Diffusion Large Language Models Alignment and Reinforcement Executor
arXiv:2604.04215v1 Announce Type: new
Abstract: Diffusion large language models (dLLMs) are emerging as a compelling alternative to dominant autoregressive models, replacing strictly sequential token generation with iterative denoising and parallel generation dynamics. However, their open-source ecosystem remains fragmented across model families and, in particular, across post-training pipelines, where reinforcement learning objectives, rollout implementations and evaluation scripts are often released as paper-specific codebases. This fragmentation slows research iteration, raises the engineering burden of reproduction, and makes fair comparison across algorithms difficult. We present \textbf{DARE} (\textbf{d}LLMs \textbf{A}lignment and \textbf{R}einforcement \textbf{E}xecutor), an open framework for post-training and evaluating dLLMs. Built on top of verl~\cite{sheng2024hybridflow} and OpenCompass~\cite{2023opencompass}, DARE unifies supervised fine-tuning, parameter-efficient fine-tuning, preference optimization, and dLLM-specific reinforcement learning under a shared execution stack for both masked and block diffusion language models. Across representative model families including LLaDA, Dream, SDAR, and LLaDA2.x, DARE provides broad algorithmic coverage, reproducible benchmark evaluation, and practical acceleration. Extensive empirical results position that DARE serves as a reusable research substrate for developing, comparing, and deploying post-training methods for current and emerging dLLMs.
Fonte: arXiv cs.CL
Theory/Optimization • Score 85
Neural Global Optimization via Iterative Refinement from Noisy Samples
arXiv:2604.03614v1 Announce Type: new
Abstract: Global optimization of black-box functions from noisy samples is a fundamental challenge in machine learning and scientific computing. Traditional methods such as Bayesian Optimization often converge to local minima on multi-modal functions, while gradient-free methods require many function evaluations. We present a novel neural approach that learns to find global minima through iterative refinement. Our model takes noisy function samples and their fitted spline representation as input, then iteratively refines an initial guess toward the true global minimum. Trained on randomly generated functions with ground truth global minima obtained via exhaustive search, our method achieves a mean error of 8.05 percent on challenging multi-modal test functions, compared to 36.24 percent for the spline initialization, a 28.18 percent improvement. The model successfully finds global minima in 72 percent of test cases with error below 10 percent, demonstrating learned optimization principles rather than mere curve fitting. Our architecture combines encoding of multiple modalities including function values, derivatives, and spline coefficients with iterative position updates, enabling robust global optimization without requiring derivative information or multiple restarts.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
BlazeFL: Fast and Deterministic Federated Learning Simulation
arXiv:2604.03606v1 Announce Type: new
Abstract: Federated learning (FL) research increasingly relies on single-node simulations with hundreds or thousands of virtual clients, making both efficiency and reproducibility essential. Yet parallel client training often introduces nondeterminism through shared random state and scheduling variability, forcing researchers to trade throughput for reproducibility or to implement custom control logic within complex frameworks. We present BlazeFL, a lightweight framework for single-node FL simulation that alleviates this trade-off through free-threaded shared-memory execution and deterministic randomness management. BlazeFL uses thread-based parallelism with in-memory parameter exchange between the server and clients, avoiding serialization and inter-process communication overhead. To support deterministic execution, BlazeFL assigns isolated random number generator (RNG) streams to clients. Under a fixed software/hardware stack, and when stochastic operators consume BlazeFL-managed generators, this design yields bitwise-identical results across repeated high-concurrency runs in both thread-based and process-based modes. In CIFAR-10 image-classification experiments, BlazeFL substantially reduces execution time relative to a widely used open-source baseline, achieving up to 3.1$\times$ speedup on communication-dominated workloads while preserving a lightweight dependency footprint. Our open-source implementation is available at: https://github.com/kitsuyaazuma/blazefl.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Piecewise Deterministic Markov Processes for Bayesian Neural Networks
arXiv:2302.08724v4 Announce Type: replace
Abstract: Inference on modern Bayesian Neural Networks (BNNs) often relies on a variational inference treatment, imposing violated assumptions of independence and the form of the posterior. Traditional MCMC approaches avoid these assumptions at the cost of increased computation due to its incompatibility to subsampling of the likelihood. New Piecewise Deterministic Markov Process (PDMP) samplers permit subsampling, though introduce a model specific inhomogenous Poisson Process (IPPs) which is difficult to sample from. This work introduces a new generic and adaptive thinning scheme for sampling from these IPPs, and demonstrates how this approach can accelerate the application of PDMPs for inference in BNNs. Experimentation illustrates how inference with these methods is computationally feasible, can improve predictive accuracy, MCMC mixing performance, and provide informative uncertainty measurements when compared against other approximate inference schemes.
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
Partially deterministic sampling for compressed sensing with denoising guarantees
arXiv:2604.04802v1 Announce Type: cross
Abstract: We study compressed sensing when the sampling vectors are chosen from the rows of a unitary matrix. In the literature, these sampling vectors are typically chosen randomly; the use of randomness has enabled major empirical and theoretical advances in the field. However, in practice there are often certain crucial sampling vectors, in which case practitioners will depart from the theory and sample such rows deterministically. In this work, we derive an optimized sampling scheme for Bernoulli selectors which naturally combines random and deterministic selection of rows, thus rigorously deciding which rows should be sampled deterministically. This sampling scheme provides measurable improvements in image compressed sensing for both generative and sparse priors when compared to with-replacement and without-replacement sampling schemes, as we show with theoretical results and numerical experiments. Additionally, our theoretical guarantees feature improved sample complexity bounds compared to previous works, and novel denoising guarantees in this setting.
Fonte: arXiv stat.ML
MLOps/Systems • Score 85
Zero-Shot Quantization via Weight-Space Arithmetic
arXiv:2604.03420v1 Announce Type: new
Abstract: We show that robustness to post-training quantization (PTQ) is a transferable direction in weight space. We call this direction the quantization vector: extracted from a donor task by simple weight-space arithmetic, it can be used to patch a receiver model and improve robustness to PTQ-induced noise by as much as 60%, without receiver-side quantization-aware training (QAT). Because the method requires no receiver training data, it provides a zero-shot, low-cost alternative to QAT for extremely low-bit deployment. We demonstrate this on Vision Transformer (ViT) models. More broadly, our results suggest that quantization robustness is not merely a byproduct of task-specific training, but a reusable feature of weight-space geometry that can be transferred rather than retrained.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
Explainable Model Routing for Agentic Workflows
arXiv:2604.03527v1 Announce Type: new
Abstract: Modern agentic workflows decompose complex tasks into specialized subtasks and route them to diverse models to minimize cost without sacrificing quality. However, current routing architectures focus exclusively on performance optimization, leaving underlying trade-offs between model capability and cost unrecorded. Without clear rationale, developers cannot distinguish between intelligent efficiency -- using specialized models for appropriate tasks -- and latent failures caused by budget-driven model selection. We present Topaz, a framework that introduces formal auditability to agentic routing. Topaz replaces silent model assignments with an inherently interpretable router that incorporates three components: (i) skill-based profiling that synthesizes performance across diverse benchmarks into granular capability profiles (ii) fully traceable routing algorithms that utilize budget-based and multi-objective optimization to produce clear traces of how skill-match scores were weighed against costs, and (iii) developer-facing explanations that translate these traces into natural language, allowing users to audit system logic and iteratively tune the cost-quality tradeoff. By making routing decisions interpretable, Topaz enables users to understand, trust, and meaningfully steer routed agentic systems.
Fonte: arXiv cs.AI
Multimodal • Score 85
Multimodal Urban Tree Detection from Satellite and Street-Level Imagery via Annotation-Efficient Deep Learning Strategies
arXiv:2604.03505v1 Announce Type: new
Abstract: Beyond the immediate biophysical benefits, urban trees play a foundational role in environmental sustainability and disaster mitigation. Precise mapping of urban trees is essential for environmental monitoring, post-disaster assessment, and strengthening policy. However, the transition from traditional, labor-intensive field surveys to scalable automated systems remains limited by high annotation costs and poor generalization across diverse urban scenarios. This study introduces a multimodal framework that integrates high-resolution satellite imagery with ground-level Google Street View to enable scalable and detailed urban tree detection under limited-annotation conditions. The framework first leverages satellite imagery to localize tree candidates and then retrieves targeted ground-level views for detailed detection, significantly reducing inefficient street-level sampling. To address the annotation bottleneck, domain adaptation is used to transfer knowledge from an existing annotated dataset to a new region of interest. To further minimize human effort, we evaluated three learning strategies: semi-supervised learning, active learning, and a hybrid approach combining both, using a transformer-based detection model. The hybrid strategy achieved the best performance with an F1-score of 0.90, representing a 12% improvement over the baseline model. In contrast, semi-supervised learning exhibited progressive performance degradation due to confirmation bias in pseudo-labeling, while active learning steadily improved results through targeted human intervention to label uncertain or incorrect predictions. Error analysis further showed that active and hybrid strategies reduced both false positives and false negatives. Our findings highlight the importance of a multimodal approach and guided annotation for scalable, annotation-efficient urban tree mapping to strengthen sustainable city planning.
Fonte: arXiv cs.CV
Vision • Score 85
Automated Segmentation and Tracking of Group Housed Pigs Using Foundation Models
arXiv:2604.03426v1 Announce Type: new
Abstract: Foundation models (FM) are reshaping computer vision by reducing reliance on task-specific supervised learning and leveraging general visual representations learned at scale. In precision livestock farming, most pipelines remain dominated by supervised learning models that require extensive labeled data, repeated retraining, and farm-specific tuning. This study presents an FM-centered workflow for automated monitoring of group-housed nursery pigs, in which pretrained vision-language FM serve as general visual backbones and farm-specific adaptation is achieved through modular post-processing. Grounding-DINO was first applied to 1,418 annotated images to establish a baseline detection performance. While detection accuracy was high under daytime conditions, performance degraded under night-vision and heavy occlusion, motivating the integration of temporal tracking logic. Building on these detections, short-term video segmentation with Grounded-SAM2 was evaluated on 550 one-minute video clips; after post-processing, over 80% of 4,927 active tracks were fully correct, with most remaining errors arising from inaccurate masks or duplicated labels. To support identity consistency over an extended time, we further developed a long-term tracking pipeline integrating initialization, tracking, matching, mask refinement, re-identification, and post-hoc quality control. This system was evaluated on a continuous 132-minute video and maintained stable identities throughout. On 132 uniformly sampled ground-truth frames, the system achieved a mean region similarity (J) of 0.83, contour accuracy (F) of 0.92, J&F of 0.87, MOTA of 0.99, and MOTP of 90.7%, with no identity switches. Overall, this work demonstrates how FM prior knowledge can be combined with lightweight, task-specific logic to enable scalable, label-efficient, and long-duration monitoring in pig production.
Fonte: arXiv cs.CV
Theory/Optimization • Score 85
Improving Feasibility via Fast Autoencoder-Based Projections
arXiv:2604.03489v1 Announce Type: new
Abstract: Enforcing complex (e.g., nonconvex) operational constraints is a critical challenge in real-world learning and control systems. However, existing methods struggle to efficiently enforce general classes of constraints. To address this, we propose a novel data-driven amortized approach that uses a trained autoencoder as an approximate projector to provide fast corrections to infeasible predictions. Specifically, we train an autoencoder using an adversarial objective to learn a structured, convex latent representation of the feasible set. This enables rapid correction of neural network outputs by projecting their associated latent representations onto a simple convex shape before decoding into the original feasible set. We test our approach on a diverse suite of constrained optimization and reinforcement learning problems with challenging nonconvex constraints. Results show that our method effectively enforces constraints at a low computational cost, offering a practical alternative to expensive feasibility correction techniques based on traditional solvers.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
KiToke: Kernel-based Interval-aware Token Compression for Video Large Language Models
arXiv:2604.03414v1 Announce Type: new
Abstract: Video Large Language Models (Video LLMs) achieve strong performance on video understanding tasks but suffer from high inference costs due to the large number of visual tokens. We propose KiToke, a training-free, query-agnostic token compression approach that reduces spatiotemporal redundancy while preserving critical visual information. Our method estimates token diversity globally using a kernel-based redundancy measure, enabling content-adaptive selection that remains effective under extreme token budgets, and further introduces a lightweight temporal interval construction with interval-aware token merging to maintain temporal coherence. Unlike prior methods that rely on local or segment-level heuristics, KiToke explicitly captures global redundancy across an entire video, leading to more efficient token utilization. Extensive experiments on multiple video understanding benchmarks and Video LLM backbones demonstrate that KiToke consistently outperforms existing training-free compression methods, with particularly large gains at aggressive retention ratios down to 1%.
Fonte: arXiv cs.CV
Vision • Score 85
A reconfigurable smart camera implementation for jet flames characterization based on an optimized segmentation model
arXiv:2604.03267v1 Announce Type: new
Abstract: In this work we present a novel framework for fire safety management in industrial settings through the implementation of a smart camera platform for jet flames characterization. The approach seeks to alleviate the lack of real-time solutions for industrial early fire segmentation and characterization. As a case study, we demonstrate how a SoC FPGA, running optimized Artificial Intelligence (AI) models can be leveraged to implement a full edge processing pipeline for jet flames analysis. In this paper we extend previous work on computer-vision jet fire segmentation by creating a novel experimental set-up and system implementation for addressing this issue, which can be replicated to other fire safety applications. The proposed platform is designed to carry out image processing tasks in real-time and on device, reducing video processing overheads, and thus the overall latency. This is achieved by optimizing a UNet segmentation model to make it amenable for an SoC FPGAs implementation; the optimized model can then be efficiently mapped onto the SoC reconfigurable logic for massively parallel execution. For our experiments, we have chosen the Ultra96 platform, as it also provides the means for implementing full-fledged intelligent systems using the SoC peripherals, as well as other Operating System (OS) capabilities (i.e., multi-threading) for systems management. For optimizing the model we made use of the Vitis (Xilinx) framework, which enabled us to optimize the full precision model from 7.5 million parameters to 59,095 parameters (125x less), which translated into a reduction of the processing latency of 2.9x. Further optimization (multi-threading and batch normalization) led to an improvement of 7.5x in terms of latency, yielding a performance of 30 Frames Per Second (FPS) without sacrificing accuracy in terms of the evaluated metrics (Dice Score).
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
Convolutional Surrogate for 3D Discrete Fracture-Matrix Tensor Upscaling
arXiv:2604.02335v1 Announce Type: new
Abstract: Modeling groundwater flow in three-dimensional fractured crystalline media requires accounting for strong spatial heterogeneity induced by fractures. Fine-scale discrete fracture-matrix (DFM) simulations can capture this complexity but are computationally expensive, especially when repeated evaluations are needed. To address this, we aim to employ a multilevel Monte Carlo (MLMC) framework in which numerical homogenization is used to upscale sub-resolution fracture effects when transitioning between accuracy levels.
To reduce the cost of conventional 3D numerical homogenization, we develop a surrogate model that predicts the equivalent hydraulic conductivity tensor Keq from a voxelized 3D domain representing tensor-valued random fields of matrix and fracture conductivities. Fracture size, orientation, and aperture are sampled from distributions informed by natural observations.
The surrogate architecture combines a 3D convolutional neural network with feed-forward layers, enabling it to capture both local spatial features and global interactions. Three surrogates are trained on data generated by DFM simulations, each corresponding to a different fracture-to-matrix conductivity contrast. Performance is evaluated across a wide range of fracture network parameters and matrix-field correlation lengths.
The trained models achieve high accuracy, with normalized root-mean-square errors below 0.22 across most test cases. Practical applicability is demonstrated by comparing numerically homogenized conductivities with surrogate predictions in two macro-scale problems: computing equivalent conductivity tensors and predicting outflow from a constrained 3D domain. In both cases, surrogate-based upscaling preserves accuracy while substantially reducing computational cost, achieving speedups exceeding 100x when inference is performed on a GPU.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
QAPruner: Quantization-Aware Vision Token Pruning for Multimodal Large Language Models
arXiv:2604.02816v1 Announce Type: new
Abstract: Multimodal Large Language Models (MLLMs) have shown strong reasoning ability, but their high computational and memory costs hinder deployment in resource-constrained settings. While Post-Training Quantization (PTQ) and vision token pruning are standard compression techniques, they are usually treated as independent optimizations. In this paper, we show that these two techniques are strongly coupled: naively applying semantic-based token pruning to PTQ-optimized MLLMs can discard activation outliers that are important for numerical stability and thus worsen quantization errors in low-bit regimes (\textit{e.g.}, W4A4). To address this issue, we propose a quantization-aware vision token pruning framework. Our method introduces a lightweight hybrid sensitivity metric that combines simulated group-wise quantization error with outlier intensity. By combining this metric with standard semantic relevance scores, the method retains tokens that are both semantically informative and robust to quantization. Experiments on standard LLaVA architectures show that our method consistently outperforms naive integration baselines. At an aggressive pruning ratio that retains only 12.5\% of visual tokens, our framework improves accuracy by 2.24\% over the baseline and even surpasses dense quantization without pruning. To the best of our knowledge, this is the first method that explicitly co-optimizes vision token pruning and PTQ for accurate low-bit MLLM inference.
Fonte: arXiv cs.CV
Applications • Score 85
LumiVideo: An Intelligent Agentic System for Video Color Grading
arXiv:2604.02409v1 Announce Type: new
Abstract: Video color grading is a critical post-production process that transforms flat, log-encoded raw footage into emotionally resonant cinematic visuals. Existing automated methods act as static, black-box executors that directly output edited pixels, lacking both interpretability and the iterative control required by professionals. We introduce LumiVideo, an agentic system that mimics the cognitive workflow of professional colorists through four stages: Perception, Reasoning, Execution, and Reflection. Given only raw log video, LumiVideo autonomously produces a cinematic base grade by analyzing the scene's physical lighting and semantic content. Its Reasoning engine synergizes an LLM's internalized cinematic knowledge with a Retrieval-Augmented Generation (RAG) framework via a Tree of Thoughts (ToT) search to navigate the non-linear color parameter space. Rather than generating pixels, the system compiles the deduced parameters into industry-standard ASC-CDL configurations and a globally consistent 3D LUT, analytically guaranteeing temporal consistency. An optional Reflection loop then allows creators to refine the result via natural language feedback. We further introduce LumiGrade, the first log-encoded video benchmark for evaluating automated grading. Experiments show that LumiVideo approaches human expert quality in fully automatic mode while enabling precise iterative control when directed.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
SEDGE: Structural Extrapolated Data Generation
arXiv:2604.02482v1 Announce Type: new
Abstract: This paper proposes a framework for Structural Extrapolated Data GEneration (SEDGE) based on suitable assumptions on the underlying data generating process. We provide conditions under which data satisfying new specifications can be generated reliably, together with the approximate identifiability of the distribution of such data under certain ``conservative" assumptions. On the algorithmic side, we develop practical methods to achieve extrapolated data generation, based on the structure-informed optimization strategy or diffusion posterior sampling, respectively. We verify the extrapolation performance on synthetic data and also consider extrapolated image generation as a real-world scenario to illustrate the validity of the proposed framework.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
A Survey on AI for 6G: Challenges and Opportunities
arXiv:2604.02370v1 Announce Type: cross
Abstract: As wireless communication evolves, each generation of networks brings new technologies that change how we connect and interact. Artificial Intelligence (AI) is becoming crucial in shaping the future of sixth-generation (6G) networks. By combining AI and Machine Learning (ML), 6G aims to offer high data rates, low latency, and extensive connectivity for applications including smart cities, autonomous systems, holographic telepresence, and the tactile internet. This paper provides a detailed overview of the role of AI in supporting 6G networks. It focuses on key technologies like deep learning, reinforcement learning, federated learning, and explainable AI. It also looks at how AI integrates with essential network functions and discusses challenges related to scalability, security, and energy efficiency, along with new solutions. Additionally, this work highlights perspectives that connect AI-driven analytics to 6G service domains like Ultra-Reliable Low-Latency Communication (URLLC), Enhanced Mobile Broadband (eMBB), Massive Machine-Type Communication (mMTC), and Integrated Sensing and Communication (ISAC). It addresses concerns about standardization, ethics, and sustainability. By summarizing recent research trends and identifying future directions, this survey offers a valuable reference for researchers and practitioners at the intersection of AI and next-generation wireless communication.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
AIVV: Neuro-Symbolic LLM Agent-Integrated Verification and Validation for Trustworthy Autonomous Systems
arXiv:2604.02478v1 Announce Type: new
Abstract: Deep learning models excel at detecting anomaly patterns in normal data. However, they do not provide a direct solution for anomaly classification and scalability across diverse control systems, frequently failing to distinguish genuine faults from nuisance faults caused by noise or the control system's large transient response. Consequently, because algorithmic fault validation remains unscalable, full Verification and Validation (V\&V) operations are still managed by Human-in-the-Loop (HITL) analysis, resulting in an unsustainable manual workload. To automate this essential oversight, we propose Agent-Integrated Verification and Validation (AIVV), a hybrid framework that deploys Large Language Models (LLMs) as a deliberative outer loop. Because rigorous system verification strictly depends on accurate validation, AIVV escalates mathematically flagged anomalies to a role-specialized LLM council. The council agents perform collaborative validation by semantically validating nuisance and true failures based on natural-language (NL) requirements to secure a high-fidelity system-verification baseline. Building on this foundation, the council then performs system verification by assessing post-fault responses against NL operational tolerances, ultimately generating actionable V\&V artifacts, such as gain-tuning proposals. Experiments on a time-series simulator for Unmanned Underwater Vehicles (UUVs) demonstrate that AIVV successfully digitizes the HITL V\&V process, overcoming the limitations of rule-based fault classification and offering a scalable blueprint for LLM-mediated oversight in time-series data domains.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Ambig-IaC: Multi-level Disambiguation for Interactive Cloud Infrastructure-as-Code Synthesis
arXiv:2604.02382v1 Announce Type: cross
Abstract: The scale and complexity of modern cloud infrastructure have made Infrastructure-as-Code (IaC) essential for managing deployments. While large Language models (LLMs) are increasingly being used to generate IaC configurations from natural language, user requests are often underspecified. Unlike traditional code generation, IaC configurations cannot be executed cheaply or iteratively repaired, forcing the LLMs into an almost one-shot regime. We observe that ambiguity in IaC exhibits a tractable compositional structure: configurations decompose into three hierarchical axes (resources, topology, attributes) where higher-level decisions constrain lower-level ones. We propose a training-free, disagreement-driven framework that generates diverse candidate specifications, identifies structural disagreements across these axes, ranks them by informativeness, and produces targeted clarification questions that progressively narrow the configuration space. We introduce \textsc{Ambig-IaC}, a benchmark of 300 validated IaC tasks with ambiguous prompts, and an evaluation framework based on graph edit distance and embedding similarity. Our method outperforms the strongest baseline, achieving relative improvements of +18.4\% and +25.4\% on structure and attribute evaluations, respectively.
Fonte: arXiv cs.AI
RL • Score 85
Mitigating Data Scarcity in Spaceflight Applications for Offline Reinforcement Learning Using Physics-Informed Deep Generative Models
arXiv:2604.02438v1 Announce Type: new
Abstract: The deployment of reinforcement learning (RL)-based controllers on physical systems is often limited by poor generalization to real-world scenarios, known as the simulation-to-reality (sim-to-real) gap. This gap is particularly challenging in spaceflight, where real-world training data are scarce due to high cost and limited planetary exploration data. Traditional approaches, such as system identification and synthetic data generation, depend on sufficient data and often fail due to modeling assumptions or lack of physics-based constraints. We propose addressing this data scarcity by introducing physics-based learning bias in a generative model. Specifically, we develop the Mutual Information-based Split Variational Autoencoder (MI-VAE), a physics-informed VAE that learns differences between observed system trajectories and those predicted by physics-based models. The latent space of the MI-VAE enables generation of synthetic datasets that respect physical constraints. We evaluate MI-VAE on a planetary lander problem, focusing on limited real-world data and offline RL training. Results show that augmenting datasets with MI-VAE samples significantly improves downstream RL performance, outperforming standard VAEs in statistical fidelity, sample diversity, and policy success rate. This work demonstrates a scalable strategy for enhancing autonomous controller robustness in complex, data-constrained environments.
Fonte: arXiv cs.LG
Vision • Score 85
WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models
arXiv:2604.02570v1 Announce Type: new
Abstract: Singular Value Decomposition (SVD) has become an important technique for reducing the computational burden of Vision Language Models (VLMs), which play a central role in tasks such as image captioning and visual question answering. Although multiple prior works have proposed efficient SVD variants to enable low-rank operations, we find that in practice it remains difficult to achieve substantial latency reduction during model execution. To address this limitation, we introduce a new computational pattern and apply SVD at a finer granularity, enabling real and measurable improvements in execution latency. Furthermore, recognizing that weight elements differ in their relative importance, we adaptively allocate relative importance to each element during SVD process to better preserve accuracy, then extend this framework with quantization applied to both weights and activations, resulting in a highly efficient VLM. Collectively, we introduce~\textit{Weighted SVD} (WSVD), which outperforms other approaches by achieving over $1.8\times$ decoding speedup while preserving accuracy. We open source our code at: \href{https://github.com/SAI-Lab-NYU/WSVD}{\texttt{https://github.com/SAI-Lab-NYU/WSVD}
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Parser-Oriented Structural Refinement for a Stable Layout Interface in Document Parsing
arXiv:2604.02692v1 Announce Type: new
Abstract: Accurate document parsing requires both robust content recognition and a stable parser interface. In explicit Document Layout Analysis (DLA) pipelines, downstream parsers do not consume the full detector output. Instead, they operate on a retained and serialized set of layout instances. However, on dense pages with overlapping regions and ambiguous boundaries, unstable layout hypotheses can make the retained instance set inconsistent with its parser input order, leading to severe downstream parsing errors. To address this issue, we introduce a lightweight structural refinement stage between a DETR-style detector and the parser to stabilize the parser interface. Treating raw detector outputs as a compact hypothesis pool, the proposed module performs set-level reasoning over query features, semantic cues, box geometry, and visual evidence. From a shared refined structural state, it jointly determines instance retention, refines box localization, and predicts parser input order before handoff. We further introduce retention-oriented supervision and a difficulty-aware ordering objective to better align the retained instance set and its order with the final parser input, especially on structurally complex pages. Extensive experiments on public benchmarks show that our method consistently improves page-level layout quality. When integrated into a standard end-to-end parsing pipeline, the stabilized parser interface also substantially reduces sequence mismatch, achieving a Reading Order Edit of 0.024 on OmniDocBench.
Fonte: arXiv cs.CV
Vision • Score 90
ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving
arXiv:2604.02714v1 Announce Type: new
Abstract: End-to-end autonomous driving models based on Vision-Language-Action (VLA) architectures have shown promising results by learning driving policies through behavior cloning on expert demonstrations. However, imitation learning inherently limits the model to replicating observed behaviors without exploring diverse driving strategies, leaving it brittle in novel or out-of-distribution scenarios. Reinforcement learning (RL) offers a natural remedy by enabling policy exploration beyond the expert distribution. Yet VLA models, typically trained on offline datasets, lack directly observable state transitions, necessitating a learned world model to anticipate action consequences. In this work, we propose a unified understanding-and-generation framework that leverages world modeling to simultaneously enable meaningful exploration and provide dense supervision. Specifically, we augment trajectory prediction with future RGB and depth image generation as dense world modeling objectives, requiring the model to learn fine-grained visual and geometric representations that substantially enrich the planning backbone. Beyond serving as a supervisory signal, the world model further acts as a source of intrinsic reward for policy exploration: its image prediction uncertainty naturally measures a trajectory's novelty relative to the training distribution, where high uncertainty indicates out-of-distribution scenarios that, if safe, represent valuable learning opportunities. We incorporate this exploration signal into a safety-gated reward and optimize the policy via Group Relative Policy Optimization (GRPO). Experiments on the NAVSIM and nuScenes benchmarks demonstrate the effectiveness of our approach, achieving a state-of-the-art PDMS score of 93.7 and an EPDMS of 88.8 on NAVSIM. The code and demo will be publicly available at https://zihaosheng.github.io/ExploreVLA/.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Holos: A Web-Scale LLM-Based Multi-Agent System for the Agentic Web
arXiv:2604.02334v1 Announce Type: new
Abstract: As large language models (LLM)-driven agents transition from isolated task solvers to persistent digital entities, the emergence of the Agentic Web, an ecosystem where heterogeneous agents autonomously interact and co-evolve, marks a pivotal shift toward Artificial General Intelligence (AGI). However, LLM-based multi-agent systems (LaMAS) are hindered by open-world issues such as scaling friction, coordination breakdown, and value dissipation. To address these challenges, we introduce Holos, a web-scale LaMAS architected for long-term ecological persistence. Holos adopts a five-layer architecture, with core modules primarily featuring the Nuwa engine for high-efficiency agent generation and hosting, a market-driven Orchestrator for resilient coordination, and an endogenous value cycle to achieve incentive compatibility. By bridging the gap between micro-level collaboration and macro-scale emergence, Holos hopes to lay the foundation for the next generation of the self-organizing and continuously evolving Agentic Web. We have publicly released Holos (accessible at https://holosai.io), providing a resource for the community and a testbed for future research in large-scale agentic ecosystems.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code
arXiv:2604.02352v1 Announce Type: cross
Abstract: Although LLMs are capable of generating functionally correct code, they also tend to produce less energy-efficient code in comparison to human-written solutions. As these inefficiencies lead to higher computational overhead, they are in direct conflict with Green Software Development (GSD) efforts, which aim to reduce the energy consumption of code. To support these efforts, this study aims to investigate whether and how LLMs can be optimized to promote the generation of energy-efficient code. To this end, we employ Contrastive Prompt Tuning (CPT). CPT combines Contrastive Learning techniques, which help the model to distinguish between efficient and inefficient code, and Prompt Tuning, a Parameter-Efficient Fine Tuning (PEFT) approach that requires only a fraction of the cost of traditional fine tuning. This study evaluates CPT on Python, Java and C++ coding problems across three different models to provide a comprehensive evaluation. The method achieves consistent improvements in code accuracy for two models but efficiency gains vary by model, language and task complexity, indicating that improvements are not uniformly reliable.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Revealing the Learning Dynamics of Long-Context Continual Pre-training
arXiv:2604.02650v1 Announce Type: new
Abstract: Existing studies on Long-Context Continual Pre-training (LCCP) mainly focus on small-scale models and limited data regimes (tens of billions of tokens). We argue that directly migrating these small-scale settings to industrial-grade models risks insufficient adaptation and premature training termination. Furthermore, current evaluation methods rely heavily on downstream benchmarks (e.g., Needle-in-a-Haystack), which often fail to reflect the intrinsic convergence state and can lead to "deceptive saturation". In this paper, we present the first systematic investigation of LCCP learning dynamics using the industrial-grade Hunyuan-A13B (80B total parameters), tracking its evolution across a 200B-token training trajectory. Specifically, we propose a hierarchical framework to analyze LCCP dynamics across behavioral (supervised fine-tuning probing), probabilistic (perplexity), and mechanistic (attention patterns) levels. Our findings reveal: (1) Necessity of Massive Data Scaling: Training regimes of dozens of billions of tokens are insufficient for industrial-grade LLMs' LCCP (e.g., Hunyuan-A13B reaches saturation after training over 150B tokens). (2) Deceptive Saturation vs. Intrinsic Saturation: Traditional NIAH scores report "fake saturation" early, while our PPL-based analysis reveals continuous intrinsic improvements and correlates more strongly with downstream performance. (3) Mechanistic Monitoring for Training Stability: Retrieval heads act as efficient, low-resource training monitors, as their evolving attention scores reliably track LCCP progress and exhibit high correlation with SFT results. This work provides a comprehensive monitoring framework, evaluation system, and mechanistic interpretation for the LCCP of industrial-grade LLM.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
FTimeXer: Frequency-aware Time-series Transformer with Exogenous variables for Robust Carbon Footprint Forecasting
arXiv:2604.02347v1 Announce Type: new
Abstract: Accurate and up-to-date forecasting of the power grid's carbon footprint is crucial for effective product carbon footprint (PCF) accounting and informed decarbonization decisions. However, the carbon intensity of the grid exhibits high non-stationarity, and existing methods often struggle to effectively leverage periodic and oscillatory patterns. Furthermore, these methods tend to perform poorly when confronted with irregular exogenous inputs, such as missing data or misalignment. To tackle these challenges, we propose FTimeXer, a frequency-aware time-series Transformer designed with a robust training scheme that accommodates exogenous factors. FTimeXer features an Fast Fourier Transform (FFT)-driven frequency branch combined with gated time-frequency fusion, allowing it to capture multi-scale periodicity effectively. It also employs stochastic exogenous masking in conjunction with consistency regularization, which helps reduce spurious correlations and enhance stability. Experiments conducted on three real-world datasets show consistent improvements over strong baselines. As a result, these enhancements lead to more reliable forecasts of grid carbon factors, which are essential for effective PCF accounting and informed decision-making regarding decarbonization.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
Modeling and Controlling Deployment Reliability under Temporal Distribution Shift
arXiv:2604.02351v1 Announce Type: new
Abstract: Machine learning models deployed in non-stationary environments are exposed to temporal distribution shift, which can erode predictive reliability over time. While common mitigation strategies such as periodic retraining and recalibration aim to preserve performance, they typically focus on average metrics evaluated at isolated time points and do not explicitly model how reliability evolves during deployment.
We propose a deployment-centric framework that treats reliability as a dynamic state composed of discrimination and calibration. The trajectory of this state across sequential evaluation windows induces a measurable notion of volatility, allowing deployment adaptation to be formulated as a multi-objective control problem that balances reliability stability against cumulative intervention cost.
Within this framework, we define a family of state-dependent intervention policies and empirically characterize the resulting cost-volatility Pareto frontier. Experiments on a large-scale, temporally indexed credit-risk dataset (1.35M loans, 2007-2018) show that selective, drift-triggered interventions can achieve smoother reliability trajectories than continuous rolling retraining while substantially reducing operational cost.
These findings position deployment reliability under temporal shift as a controllable multi-objective system and highlight the role of policy design in shaping stability-cost trade-offs in high-stakes tabular applications.
Fonte: arXiv cs.LG
RL • Score 85
Dynamic Mask Enhanced Intelligent Multi-UAV Deployment for Urban Vehicular Networks
arXiv:2604.02358v1 Announce Type: cross
Abstract: Vehicular Ad Hoc Networks (VANETs) play a crucial role in realizing vehicle-road collaboration and intelligent transportation. However, urban VANETs often face challenges such as frequent link disconnections and subnet fragmentation, which hinder reliable connectivity. To address these issues, we dynamically deploy multiple Unmanned Aerial Vehicles (UAVs) as communication relays to enhance VANET. A novel Score based Dynamic Action Mask enhanced QMIX algorithm (Q-SDAM) is proposed for multi-UAV deployment, which maximizes vehicle connectivity while minimizing multi-UAV energy consumption. Specifically, we design a score-based dynamic action mask mechanism to guide UAV agents in exploring large action spaces, accelerate the learning process and enhance optimization performance. The practicality of Q-SDAM is validated using real-world datasets. We show that Q-SDAM improves connectivity by 18.2% while reducing energy consumption by 66.6% compared with existing algorithms.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
Characterizing WebGPU Dispatch Overhead for LLM Inference Across Four GPU Vendors, Three Backends, and Three Browsers
arXiv:2604.02344v1 Announce Type: new
Abstract: WebGPU's security-focused design imposes per-operation validation that compounds across the many small dispatches in neural network inference, yet the true cost of this overhead is poorly characterized. We present a systematic characterization of WebGPU dispatch overhead for LLM inference at batch size 1, spanning four GPU vendors (NVIDIA, AMD, Apple, Intel), two native implementations (Dawn, wgpu-native) and three browsers (Chrome, Safari, Firefox), and two model sizes (Qwen2.5-0.5B and 1.5B). Our primary contribution is a sequential-dispatch methodology that reveals naive single-operation benchmarks overestimate dispatch cost by ${\sim}20\times$. The true per-dispatch cost of WebGPU API overhead alone is 24-36 $\mu$s on Vulkan and 32-71 $\mu$s on Metal, while the total per-operation overhead including Python cost is ${\sim}95$~$\mu$s, which turns out to be a distinction critical for optimization. On Vulkan, kernel fusion improves throughput by 53%, while CUDA fusion provides no benefit, confirming that per-operation overhead is a primary differentiator. LLM inference was tested across three major operating systems (Linux, Windows, macOS). We built $\texttt{torch-webgpu}$, a PrivateUse1-based out-of-tree PyTorch backend and an FX-to-WebGPU compiler, which on our reference platform achieves 11--12% of CUDA performance. At dtype-matched float32, RTX PRO 2000 achieves 1.4$\times$ WebGPU's throughput despite ${\sim}6\times$ less compute than RTX 5090. For dispatch overhead, backend choice is the dominant factor, although implementation choice also matters substantially within a backend (2.2$\times$ for Metal). In terms of dispatch vs kernel compute efficiency, we conclude that at batch=1 with the current dispatch-heavy pipeline, per-operation overhead dominates regardless of kernel quality. All code, benchmarks, and raw data are open source.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
TRACE: Traceroute-based Internet Route change Analysis with Ensemble Learning
arXiv:2604.02361v1 Announce Type: cross
Abstract: Detecting Internet routing instability is a critical yet challenging task, particularly when relying solely on endpoint active measurements. This study introduces TRACE, a MachineLearning (ML)pipeline designed to identify route changes using only traceroute latency data, thereby ensuring independence from control plane information. We propose a robust feature engineering strategy that captures temporal dynamics using rolling statistics and aggregated context patterns. The architecture leverages a stacked ensemble of Gradient Boosted Decision Trees refined by a hyperparameter-optimized meta-learner. By strictly calibrating decision thresholds to address the inherent class imbalance of rare routing events, TRACE achieves a superior F1-score performance, significantly outperforming traditional baseline models and demonstrating strong effective ness in detecting routing changes on the Internet.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
Automatic Textbook Formalization
arXiv:2604.03071v1 Announce Type: new
Abstract: We present a case study where an automatic AI system formalizes a textbook with more than 500 pages of graduate-level algebraic combinatorics to Lean. The resulting formalization represents a new milestone in textbook formalization scale and proficiency, moving from early results in undergraduate topology and restructuring of existing library content to a full standalone formalization of a graduate textbook. The formalization comprises 130K lines of code and 5900 Lean declarations and was conducted within one week by a total of 30K Claude 4.5 Opus agents collaborating in parallel on a shared code base via version control, simultaneously setting a record in multi-agent software engineering with usable results. The inference cost matches or undercuts what we estimate as the salaries required for a team of human experts, and we expect there is still the potential for large efficiencies to be made without the need for better models. We make our code, the resulting Lean code base and a side-by-side blueprint website available open-source.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
InfoSeeker: A Scalable Hierarchical Parallel Agent Framework for Web Information Seeking
arXiv:2604.02971v1 Announce Type: new
Abstract: Recent agentic search systems have made substantial progress by emphasising deep, multi-step reasoning. However, this focus often overlooks the challenges of wide-scale information synthesis, where agents must aggregate large volumes of heterogeneous evidence across many sources. As a result, most existing large language model agent systems face severe limitations in data-intensive settings, including context saturation, cascading error propagation, and high end-to-end latency. To address these challenges, we present \framework, a hierarchical framework based on principle of near-decomposability, containing a strategic \textit{Host}, multiple \textit{Managers} and parallel \textit{Workers}. By leveraging aggregation and reflection mechanisms at the Manager layer, our framework enforces strict context isolation to prevent saturation and error propagation. Simultaneously, the parallelism in worker layer accelerates the speed of overall task execution, mitigating the significant latency. Our evaluation on two complementary benchmarks demonstrates both efficiency ($ 3-5 \times$ speed-up) and effectiveness, achieving a $8.4\%$ success rate on WideSearch-en and $52.9\%$ accuracy on BrowseComp-zh. The code is released at https://github.com/agent-on-the-fly/InfoSeeker
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
CharTool: Tool-Integrated Visual Reasoning for Chart Understanding
arXiv:2604.02794v1 Announce Type: new
Abstract: Charts are ubiquitous in scientific and financial literature for presenting structured data. However, chart reasoning remains challenging for multimodal large language models (MLLMs) due to the lack of high-quality training data, as well as the need for fine-grained visual grounding and precise numerical computation. To address these challenges, we first propose DuoChart, a scalable dual-source data pipeline that combines synthesized charts with real-world charts to construct diverse, high-quality chart training data. We then introduce CharTool, which equips MLLMs with external tools, including image cropping for localized visual perception and code-based computation for accurate numerical reasoning. Through agentic reinforcement learning on DuoChart, CharTool learns tool-integrated reasoning grounded in chart content. Extensive experiments on six chart benchmarks show that our method consistently improves over strong MLLM baselines across model scales. Notably, CharTool-7B outperforms the base model by **+8.0%** on CharXiv (Reasoning) and **+9.78%** on ChartQAPro, while achieving competitive performance with substantially larger or proprietary models. Moreover, CharTool demonstrates positive generalization to out-of-domain visual math reasoning benchmarks.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
VBGS-SLAM: Variational Bayesian Gaussian Splatting Simultaneous Localization and Mapping
arXiv:2604.02696v1 Announce Type: new
Abstract: 3D Gaussian Splatting (3DGS) has shown promising results for 3D scene modeling using mixtures of Gaussians, yet its existing simultaneous localization and mapping (SLAM) variants typically rely on direct, deterministic pose optimization against the splat map, making them sensitive to initialization and susceptible to catastrophic forgetting as map evolves. We propose Variational Bayesian Gaussian Splatting SLAM (VBGS-SLAM), a novel framework that couples the splat map refinement and camera pose tracking in a generative probabilistic form. By leveraging conjugate properties of multivariate Gaussians and variational inference, our method admits efficient closed-form updates and explicitly maintains posterior uncertainty over both poses and scene parameters. This uncertainty-aware method mitigates drift and enhances robustness in challenging conditions, while preserving the efficiency and rendering quality of existing 3DGS. Our experiments demonstrate superior tracking performance and robustness in long sequence prediction, alongside efficient, high-quality novel view synthesis across diverse synthetic and real-world scenes.
Fonte: arXiv cs.CV
Theory/Optimization • Score 85
Lipschitz bounds for integral kernels
arXiv:2604.02887v1 Announce Type: new
Abstract: Feature maps associated with positive definite kernels play a central role in kernel methods and learning theory, where regularity properties such as Lipschitz continuity are closely related to robustness and stability guarantees. Despite their importance, explicit characterizations of the Lipschitz constant of kernel feature maps are available only in a limited number of cases. In this paper, we study the Lipschitz regularity of feature maps associated with integral kernels under differentiability assumptions. We first provide sufficient conditions ensuring Lipschitz continuity and derive explicit formulas for the corresponding Lipschitz constants. We then identify a condition under which the feature map fails to be Lipschitz continuous and apply these results to several important classes of kernels. For infinite width two-layer neural network with isotropic Gaussian weight distributions, we show that the Lipschitz constant of the associated kernel can be expressed as the supremum of a two-dimensional integral, leading to an explicit characterization for the Gaussian kernel and the ReLU random neural network kernel. We also study continuous and shift-invariant kernels such as Gaussian, Laplace, and Mat\'ern kernels, which admit an interpretation as neural network with cosine activation function. In this setting, we prove that the feature map is Lipschitz continuous if and only if the weight distribution has a finite second-order moment, and we then derive its Lipschitz constant. Finally, we raise an open question concerning the asymptotic behavior of the convergence of the Lipschitz constant in finite width neural networks. Numerical experiments are provided to support this behavior.
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
Structure-Preserving Multi-View Embedding Using Gromov-Wasserstein Optimal Transport
arXiv:2604.02610v1 Announce Type: new
Abstract: Multi-view data analysis seeks to integrate multiple representations of the same samples in order to recover a coherent low-dimensional structure. Classical approaches often rely on feature concatenation or explicit alignment assumptions, which become restrictive under heterogeneous geometries or nonlinear distortions. In this work, we propose two geometry-aware multi-view embedding strategies grounded in Gromov-Wasserstein (GW) optimal transport. The first, termed Mean-GWMDS, aggregates view-specific relational information by averaging distance matrices and applying GW-based multidimensional scaling to obtain a representative embedding. The second strategy, referred to as Multi-GWMDS, adopts a selection-based paradigm in which multiple geometry-consistent candidate embeddings are generated via GW-based alignment and a representative embedding is selected. Experiments on synthetic manifolds and real-world datasets show that the proposed methods effectively preserve intrinsic relational structure across views. These results highlight GW-based approaches as a flexible and principled framework for multi-view representation learning.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
Reinforcement Learning-based Knowledge Distillation with LLM-as-a-Judge
arXiv:2604.02621v1 Announce Type: new
Abstract: Reinforcement Learning (RL) has been shown to substantially improve the reasoning capability of small and large language models (LLMs), but existing approaches typically rely on verifiable rewards, hence ground truth labels. We propose an RL framework that uses rewards from an LLM that acts as a judge evaluating model outputs over large amounts of unlabeled data, enabling label-free knowledge distillation and replacing the need of ground truth supervision. Notably, the judge operates with a single-token output, making reward computation efficient. When combined with verifiable rewards, our approach yields substantial performance gains across math reasoning benchmarks. These results suggest that LLM-based evaluators can produce effective training signals for RL fine-tuning.
Fonte: arXiv cs.CL
Privacy/Security/Fairness • Score 85
Communication-Efficient Distributed Learning with Differential Privacy
arXiv:2604.02558v1 Announce Type: new
Abstract: We address nonconvex learning problems over undirected networks. In particular, we focus on the challenge of designing an algorithm that is both communication-efficient and that guarantees the privacy of the agents' data. The first goal is achieved through a local training approach, which reduces communication frequency. The second goal is achieved by perturbing gradients during local training, specifically through gradient clipping and additive noise. We prove that the resulting algorithm converges to a stationary point of the problem within a bounded distance. Additionally, we provide theoretical privacy guarantees within a differential privacy framework that ensure agents' training data cannot be inferred from the trained model shared over the network. We show the algorithm's superior performance on a classification task under the same privacy budget, compared with state-of-the-art methods.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency
arXiv:2604.03044v1 Announce Type: new
Abstract: We introduce JoyAI-LLM Flash, an efficient Mixture-of-Experts (MoE) language model designed to redefine the trade-off between strong performance and token efficiency in the sub-50B parameter regime. JoyAI-LLM Flash is pretrained on a massive corpus of 20 trillion tokens and further optimized through a rigorous post-training pipeline, including supervised fine-tuning (SFT), Direct Preference Optimization (DPO), and large-scale reinforcement learning (RL) across diverse environments. To improve token efficiency, JoyAI-LLM Flash strategically balances \emph{thinking} and \emph{non-thinking} cognitive modes and introduces FiberPO, a novel RL algorithm inspired by fibration theory that decomposes trust-region maintenance into global and local components, providing unified multi-scale stability control for LLM policy optimization. To enhance architectural sparsity, the model comprises 48B total parameters while activating only 2.7B parameters per forward pass, achieving a substantially higher sparsity ratio than contemporary industry leading models of comparable scale. To further improve inference throughput, we adopt a joint training-inference co-design that incorporates dense Multi-Token Prediction (MTP) and Quantization-Aware Training (QAT). We release the checkpoints for both JoyAI-LLM-48B-A3B Base and its post-trained variants on Hugging Face to support the open-source community.
Fonte: arXiv cs.CL
RL • Score 85
Coupled Control, Structured Memory, and Verifiable Action in Agentic AI (SCRAT -- Stochastic Control with Retrieval and Auditable Trajectories): A Comparative Perspective from Squirrel Locomotion and Scatter-Hoarding
arXiv:2604.03201v1 Announce Type: new
Abstract: Agentic AI is increasingly judged not by fluent output alone but by whether it can act, remember, and verify under partial observability, delay, and strategic observation. Existing research often studies these demands separately: robotics emphasizes control, retrieval systems emphasize memory, and alignment or assurance work emphasizes checking and oversight. This article argues that squirrel ecology offers a sharp comparative case because arboreal locomotion, scatter-hoarding, and audience-sensitive caching couple all three demands in one organism. We synthesize evidence from fox, eastern gray, and, in one field comparison, red squirrels, and impose an explicit inference ladder: empirical observation, minimal computational inference, and AI design conjecture. We introduce a minimal hierarchical partially observed control model with latent dynamics, structured episodic memory, observer-belief state, option-level actions, and delayed verifier signals. This motivates three hypotheses: (H1) fast local feedback plus predictive compensation improves robustness under hidden dynamics shifts; (H2) memory organized for future control improves delayed retrieval under cue conflict and load; and (H3) verifiers and observer models inside the action-memory loop reduce silent failure and information leakage while remaining vulnerable to misspecification. A downstream conjecture is that role-differentiated proposer/executor/checker/adversary systems may reduce correlated error under asymmetric information and verification burden. The contribution is a comparative perspective and benchmark agenda: a disciplined program of falsifiable claims about the coupling of control, memory, and verifiable action.
Fonte: arXiv cs.AI
Multimodal • Score 85
Token-Efficient Multimodal Reasoning via Image Prompt Packaging
arXiv:2604.02492v1 Announce Type: new
Abstract: Deploying large multimodal language models at scale is constrained by token-based inference costs, yet the cost-performance behavior of visual prompting strategies remains poorly characterized. We introduce Image Prompt Packaging (IPPg), a prompting paradigm that embeds structured text directly into images to reduce text token overhead, and benchmark it across five datasets, three frontier models (GPT-4.1, GPT-4o, Claude 3.5 Sonnet), and two task families (VQA and code generation). We derive a cost formulation decomposing savings by token type and show IPPg achieves 35.8--91.0\% inference cost reductions. Despite token compression of up to 96\%, accuracy remains competitive in many settings, though outcomes are highly model- and task-dependent: GPT-4.1 achieves simultaneous accuracy and cost gains on CoSQL, while Claude 3.5 incurs cost increases on several VQA benchmarks. Systematic error analysis yields a failure-mode taxonomy: spatial reasoning, non-English inputs, and character-sensitive operations are most vulnerable, while schema-structured tasks benefit most. A 125-configuration rendering ablation reveals accuracy shifts of 10--30 percentage points, establishing visual encoding choices as a first-class variable in multimodal system design.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration
arXiv:2604.02659v1 Announce Type: new
Abstract: The massive scale of pretrained models has made efficient compression essential for practical deployment. Low-rank decomposition based on the singular value decomposition (SVD) provides a principled approach for model reduction, but its exact computation is expensive for large weight matrices. Randomized alternatives such as randomized SVD (RSVD) improve efficiency, yet they can suffer from poor approximation quality when the singular value spectrum decays slowly, a regime commonly observed in modern pretrained models. In this work, we address this limitation from both theoretical and empirical perspectives. First, we establish a connection between low-rank approximation error and predictive performance by analyzing softmax perturbations, showing that deviations in class probabilities are controlled by the spectral error of the compressed weights. Second, we demonstrate that RSVD is inadequate, and we propose randomized subspace iteration (RSI) as a more effective alternative. By incorporating multiple power iterations, RSI improves spectral separation and provides a controllable mechanism for enhancing approximation quality. We evaluate our approach on both convolutional networks and transformer-based architectures. Our results show that RSI achieves near-optimal approximation quality while outperforming RSVD in predictive accuracy under aggressive compression, enabling efficient model compression.
Fonte: arXiv cs.LG
Privacy/Security/Fairness • Score 85
Unlocking Multi-Site Clinical Data: A Federated Approach to Privacy-First Child Autism Behavior Analysis
arXiv:2604.02616v1 Announce Type: new
Abstract: Automated recognition of autistic behaviors in children is essential for early intervention and objective clinical assessment. However, the development of robust models is severely hindered by strict privacy regulations (e.g., HIPAA) and the sensitive nature of pediatric data, which prevents the centralized aggregation of clinical datasets. Furthermore, individual clinical sites often suffer from data scarcity, making it difficult to learn generalized behavior patterns or tailor models to site-specific patient distributions. To address these challenges, we observe that Federated Learning (FL) can decouple model training from raw data access, enabling multi-site collaboration while maintaining strict data residency. In this paper, we present the first study exploring Federated Learning for pose-based child autism behavior recognition. Our framework employs a two-layer privacy protection mechanism: utilizing human skeletal abstraction to remove identifiable visual information from the raw RGB videos and FL to ensure sensitive pose data remains within the clinic. This approach leverages distributed clinical data to learn generalized representations while providing the flexibility for site-specific personalization. Experimental results on the MMASD benchmark demonstrate that our framework achieves high recognition accuracy, outperforming traditional federated baselines and providing a robust, privacy-first solution for multi-site clinical analysis.
Fonte: arXiv cs.CV
Vision • Score 85
Generating Satellite Imagery Data for Wildfire Detection through Mask-Conditioned Generative AI
arXiv:2604.02479v1 Announce Type: new
Abstract: The scarcity of labeled satellite imagery remains a fundamental bottleneck for deep-learning (DL)-based wildfire monitoring systems. This paper investigates whether a diffusion-based foundation model for Earth Observation (EO), EarthSynth, can synthesize realistic post-wildfire Sentinel-2 RGB imagery conditioned on existing burn masks, without task-specific retraining.
Using burn masks derived from the CalFireSeg-50 dataset (Martin et al., 2025), we design and evaluate six controlled experimental configurations that systematically vary: (i) pipeline architecture (mask-only full generation vs. inpainting with pre-fire context), (ii) prompt engineering strategy (three hand-crafted prompts and a VLM-generated prompt via Qwen2-VL), and (iii) a region-wise color-matching post-processing step.
Quantitative assessment on 10 stratified test samples uses four complementary metrics: Burn IoU, burn-region color distance ({\Delta}C_burn), Darkness Contrast, and Spectral Plausibility. Results show that inpainting-based pipelines consistently outperform full-tile generation across all metrics, with the structured inpainting prompt achieving the best spatial alignment (Burn IoU = 0.456) and burn saliency (Darkness Contrast = 20.44), while color matching produces the lowest color distance ({\Delta}C_burn = 63.22) at the cost of reduced burn saliency.
VLM-assisted inpainting is competitive with hand-crafted prompts. These findings provide a foundation for incorporating generative data augmentation into wildfire detection pipelines.
Code and experiments are available at: https://www.kaggle.com/code/valeriamartinh/genai-all-runned
Fonte: arXiv cs.CV
RecSys • Score 85
Learn then Decide: A Learning Approach for Designing Data Marketplaces
arXiv:2503.10773v2 Announce Type: replace
Abstract: As data marketplaces become increasingly central to the digital economy, it is crucial to design efficient pricing mechanisms that optimize revenue while ensuring fair and adaptive pricing. We introduce the Maximum Auction-to-Posted Price (MAPP) mechanism, a novel two-stage approach that first estimates the bidders' value distribution through auctions and then determines the optimal posted price based on the learned distribution. We establish that MAPP is individually rational and incentive-compatible, ensuring truthful bidding while balancing revenue maximization with minimal price discrimination. On the theoretical side, we establish a statistical viewpoint that recasts revenue optimization as a valuation density estimation problem: we show that revenue regret can be controlled by uniform error in estimating the valuation density. MAPP achieves a regret of $O_p(n^{-1}(\log n)^2)$ when incorporating historical bid data, where $n$ is the number of bids in the current round. For sequential dataset sales over $T$ rounds, we propose an online MAPP mechanism that dynamically adjusts pricing across datasets with varying value distributions. Our approach achieves no-regret learning, with the average cumulative regret converging at a rate of $O_p(T^{-1/2}(\log T)^2)$. We validate the effectiveness of MAPP through simulations and real-world data from the FCC AWS-3 spectrum auction.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics
arXiv:2604.02345v1 Announce Type: cross
Abstract: Scaling generalist GUI agents is hindered by the data scalability bottleneck of expensive human demonstrations and the "distillation ceiling" of synthetic teacher supervision. To transcend these limitations, we propose UI-Oceanus, a framework that shifts the learning focus from mimicking high-level trajectories to mastering interaction physics via ground-truth environmental feedback. Through a systematic investigation of self-supervised objectives, we identify that forward dynamics, defined as the generative prediction of future interface states, acts as the primary driver for scalability and significantly outweighs inverse inference. UI-Oceanus leverages this insight by converting low-cost autonomous exploration, which is verified directly by system execution, into high-density generative supervision to construct a robust internal world model. Experimental evaluations across a series of models demonstrate the decisive superiority of our approach: models utilizing Continual Pre-Training (CPT) on synthetic dynamics outperform non-CPT baselines with an average success rate improvement of 7% on offline benchmarks, which amplifies to a 16.8% gain in real-world online navigation. Furthermore, we observe that navigation performance scales with synthetic data volume. These results confirm that grounding agents in forward predictive modeling offers a superior pathway to scalable GUI automation with robust cross-domain adaptability and compositional generalization.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
AXELRAM: Quantize Once, Never Dequantize
arXiv:2604.02638v1 Announce Type: new
Abstract: We propose AXELRAM, a smart SRAM macro architecture that computes attention scores directly from quantized KV cache indices without dequantization. The key enabler is a design-time fixed codebook: orthogonal-transform-based quantization concentrates each coordinate's distribution to N(0,1/d), so the optimal quantizer depends only on dimension d and bit-width b, not on input data. The asymmetric path design -- transform on write, table-lookup on read with no inverse transform -- reduces per-query multiplications by 102.4x (a mathematical identity).
Through multi-seed evaluation (10 seeds x 3 models), we discover that sign pattern sensitivity causes catastrophic PPL spikes (Delta > 50) on certain models (Qwen2.5-3B), while others (LLaMA-3.1-8B) are fully stable. This phenomenon extends SpinQuant's observation of rotation variance in weight quantization to the KV cache domain, where the effect is qualitatively more severe. We trace the root cause to layer-wise norm heterogeneity and propose a gradient-free sign pattern selection (200 candidates, 8 calibration samples, one-time) that eliminates catastrophic spikes with zero additional hardware cost. All source code is available at https://github.com/Axelidea/AXELRAM.
Fonte: arXiv cs.LG
Multimodal • Score 85
LiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task Learning
arXiv:2604.02338v1 Announce Type: new
Abstract: MoE-PEFT methods combine Mixture of Experts with parameter-efficient fine-tuning for multi-task adaptation, but require separate adapters per expert causing trainable parameters to scale linearly with expert count and limiting applicability to adapter-based architectures. We propose LiME (Lightweight Mixture of Experts), which achieves expert specialization through lightweight modulation rather than adapter replication. Instead of separate adapters, LiME uses a single shared PEFT module and modulates its output with lightweight expert vectors, reducing expert parameters while generalizing to any PEFT method. Notably, LiME introduces zero-parameter routing by leveraging existing frozen and adapted representations eliminating learned router parameters typically required per layer. Theoretically, we prove that (i) more experts preserve more task-relevant information and (ii) modulation approximates full expert-specific PEFT with bounded error. LiME further incorporates n-gram windowed routing and adaptive expert selection (Auto Top-K) based on routing confidence. Experiments on MMT-47, a multimodal multi-task benchmark with 47 tasks spanning text, image, and video, demonstrate that LiME achieves competitive or superior performance while using up to 4x fewer trainable parameters and up to 29% faster training compared to corresponding MoE-PEFT baselines.
Fonte: arXiv cs.LG
Privacy/Security/Fairness • Score 85
Homophily-aware Supervised Contrastive Counterfactual Augmented Fair Graph Neural Network
arXiv:2604.02342v1 Announce Type: new
Abstract: In recent years, Graph Neural Networks (GNNs) have achieved remarkable success in tasks such as node classification, link prediction, and graph representation learning. However, they remain susceptible to biases that can arise not only from node attributes but also from the graph structure itself. Addressing fairness in GNNs has therefore emerged as a critical research challenge. In this work, we propose a novel model for training fairness-aware GNNs by improving the counterfactual augmented fair graph neural network framework (CAF). Specifically, our approach introduces a two-phase training strategy: in the first phase, we edit the graph to increase homophily ratio with respect to class labels while reducing homophily ratio with respect to sensitive attribute labels; in the second phase, we integrate a modified supervised contrastive loss and environmental loss into the optimization process, enabling the model to jointly improve predictive performance and fairness. Experiments on five real-world datasets demonstrate that our model outperforms CAF and several state-of-the-art graph-based learning methods in both classification accuracy and fairness metrics.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Haiku to Opus in Just 10 bits: LLMs Unlock Massive Compression Gains
arXiv:2604.02343v1 Announce Type: cross
Abstract: We study the compression of LLM-generated text across lossless and lossy regimes, characterizing a compression-compute frontier where more compression is possible at the cost of more compute. For lossless compression, domain-adapted LoRA adapters can improve LLM-based arithmetic coding by 2x over compression with the base LLM alone. For lossy compression, prompting a model for a succinct rewrite then applying arithmetic coding can achieve compression ratios of approximately 0.03, a 2x improvement over compressing the original response.
We further introduce Question-Asking compression (QA), an interactive lossy protocol inspired by the game 'Twenty Questions'. A small model iteratively refines its response by asking yes/no questions to a stronger model, transferring exactly one bit per answer. On 8 benchmarks spanning math, science, and code, 10 binary questions recover 23% to 72% of the capability gap between a small and large model on standard benchmarks and 7% to 38% on harder benchmarks, achieving compression ratios of 0.0006 to 0.004. This is over 100x smaller than prior LLM-based compression (Deletang et al., 2024), suggesting that interactive protocols can transfer knowledge far more efficiently than transmitting full responses.
Fonte: arXiv cs.AI
Multimodal • Score 85
Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs
arXiv:2604.02689v1 Announce Type: new
Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have expanded reasoning capabilities into 3D domains, enabling fine-grained spatial understanding. However, the substantial size of 3D MLLMs and the high dimensionality of input features introduce considerable inference overhead, which limits practical deployment on resource constrained platforms. To overcome this limitation, this paper presents Efficient3D, a unified framework for visual token pruning that accelerates 3D MLLMs while maintaining competitive accuracy. The proposed framework introduces a Debiased Visual Token Importance Estimator (DVTIE) module, which considers the influence of shallow initial layers during attention aggregation, thereby producing more reliable importance predictions for visual tokens. In addition, an Adaptive Token Rebalancing (ATR) strategy is developed to dynamically adjust pruning strength based on scene complexity, preserving semantic completeness and maintaining balanced attention across layers. Together, they enable context-aware token reduction that maintains essential semantics with lower computation. Comprehensive experiments conducted on five representative 3D vision and language benchmarks, including ScanRefer, Multi3DRefer, Scan2Cap, ScanQA, and SQA3D, demonstrate that Efficient3D achieves superior performance compared with unpruned baselines, with a +2.57% CIDEr improvement on the Scan2Cap dataset. Therefore, Efficient3D provides a scalable and effective solution for efficient inference in 3D MLLMs. The code is released at: https://github.com/sol924/Efficient3D
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
A Numerical Method for Coupling Parameterized Physics-Informed Neural Networks and FDM for Advanced Thermal-Hydraulic System Simulation
arXiv:2604.02663v1 Announce Type: new
Abstract: Severe accident analysis using system-level codes such as MELCOR is indispensable for nuclear safety assessment, yet the computational cost of repeated simulations poses a significant bottleneck for parametric studies and uncertainty quantification. Existing surrogate models accelerate these analyses but depend on large volumes of simulation data, while physics-informed neural networks (PINNs) enable data-free training but must be retrained for every change in problem parameters. This study addresses both limitations by developing the Parameterized PINNs coupled with FDM (P2F) method, a node-assigned hybrid framework for MELCOR's Control Volume Hydrodynamics/Flow Path (CVH/FP) module. In the P2F method, a parameterized Node-Assigned PINN (NA-PINN) accepts the water-level difference, initial velocity, and time as inputs, learning a solution manifold so that a single trained network serves as a data-free surrogate for the momentum conservation equation across all flow paths without retraining. This PINN is coupled with a finite difference method (FDM) solver that advances the mass conservation equation at each time step, ensuring exact discrete mass conservation while replacing the iterative nonlinear momentum solve with a single forward pass. Verification on a six-tank gravity-driven draining scenario yields a water level mean absolute error of $7.85 \times 10^{-5}$ m and a velocity mean absolute error of $3.21 \times 10^{-3}$ m/s under the nominal condition with $\Delta t = 1.0$ s. The framework maintains consistent accuracy across time steps ranging from 0.2 to 1.0 s and generalizes to five distinct initial conditions, all without retraining or simulation data. This work introduces a numerical coupling methodology for integrating parameterized PINNs with FDM within a nuclear thermal-hydraulic system code framework.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
WGFINNs: Weak formulation-based GENERIC formalism informed neural networks'
arXiv:2604.02601v1 Announce Type: new
Abstract: Data-driven discovery of governing equations from noisy observations remains a fundamental challenge in scientific machine learning. While GENERIC formalism informed neural networks (GFINNs) provide a principled framework that enforces the laws of thermodynamics by construction, their reliance on strong-form loss formulations makes them highly sensitive to measurement noise. To address this limitation, we propose weak formulation-based GENERIC formalism informed neural networks (WGFINNs), which integrate the weak formulation of dynamical systems with the structure-preserving architecture of GFINNs. WGFINNs significantly enhance robustness to noisy data while retaining exact satisfaction of GENERIC degeneracy and symmetry conditions. We further incorporate a state-wise weighted loss and a residual-based attention mechanism to mitigate scale imbalance across state variables. Theoretical analysis contrasts quantitative differences between the strong-form and the weak-form estimators. Mainly, the strong-form estimator diverges as the time step decreases in the presence of noise, while the weak-form estimator can be accurate even with noisy data if test functions satisfy certain conditions. Numerical experiments demonstrate that WGFINNs consistently outperform GFINNs at varying noise levels, achieving more accurate predictions and reliable recovery of physical quantities.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
State estimations and noise identifications with intermittent corrupted observations via Bayesian variational inference
arXiv:2604.02738v1 Announce Type: new
Abstract: This paper focuses on the state estimation problem in distributed sensor networks, where intermittent packet dropouts, corrupted observations, and unknown noise covariances coexist. To tackle this challenge, we formulate the joint estimation of system states, noise parameters, and network reliability as a Bayesian variational inference problem, and propose a novel variational Bayesian adaptive Kalman filter (VB-AKF) to approximate the joint posterior probability densities of the latent parameters. Unlike existing AKF that separately handle missing data and measurement outliers, the proposed VB-AKF adopts a dual-mask generative model with two independent Bernoulli random variables, explicitly characterizing both observable communication losses and latent data authenticity. Additionally, the VB-AKF integrates multiple concurrent multiple observations into the adaptive filtering framework, which significantly enhances statistical identifiability. Comprehensive numerical experiments verify the effectiveness and asymptotic optimality of the proposed method, showing that both parameter identification and state estimation asymptotically converge to the theoretical optimal lower bound with the increase in the number of sensors.
Fonte: arXiv stat.ML
MLOps/Systems • Score 85
AdaHOP: Fast and Accurate Low-Precision Training via Outlier-Pattern-Aware Rotation
arXiv:2604.02525v1 Announce Type: new
Abstract: Low-precision training (LPT) commonly employs Hadamard transforms to suppress outliers and mitigate quantization error in large language models (LLMs). However, prior methods apply a fixed transform uniformly, despite substantial variation in outlier structures across tensors. Through the first systematic study of outlier patterns across weights, activations, and gradients of LLMs, we show that this strategy is fundamentally flawed: the effectiveness of Hadamard-based suppression depends on how the transform's smoothing direction aligns with the outlier structure of each operand -- a property that varies substantially across layers and computation paths. We characterize these patterns into three types: Row-wise, Column-wise, and None. Each pair requires a tailored transform direction or outlier handling strategy to minimize quantization error. Based on this insight, we propose AdaHOP (Adaptive Hadamard transform with Outlier-Pattern-aware strategy), which assigns each matrix multiplication its optimal strategy: Inner Hadamard Transform (IHT) where inner-dimension smoothing is effective, or IHT combined with selective Outlier Extraction (OE) -- routing dominant outliers to a high-precision path -- where it is not. Combined with hardware-aware Triton kernels, AdaHOP achieves BF16 training quality at MXFP4 precision while delivering up to 3.6X memory compression and 1.8X kernel acceleration} over BF16 full-precision training.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Fast NF4 Dequantization Kernels for Large Language Model Inference
arXiv:2604.02556v1 Announce Type: new
Abstract: Large language models (LLMs) have grown beyond the memory capacity of single GPU devices, necessitating quantization techniques for practical deployment. While NF4 (4-bit NormalFloat) quantization enables 4$\times$ memory reduction, inference on current NVIDIA GPUs (e.g., Ampere A100) requires expensive dequantization back to FP16 format, creating a critical performance bottleneck. This paper presents a lightweight shared memory optimization that addresses this gap through principled memory hierarchy exploitation while maintaining full ecosystem compatibility. We compare our technique against the open-source BitsAndBytes implementation, achieving 2.0--2.2$\times$ kernel speedup across three models (Gemma 27B, Qwen3 32B, and Llama3.3 70B) and up to 1.54$\times$ end-to-end improvement by leveraging the 12--15$\times$ latency advantage of shared memory over global memory access. Our optimization reduces instruction counts through simplified indexing logic while using only 64 bytes of shared memory per thread block, demonstrating that lightweight optimizations can deliver substantial performance gains with minimal engineering effort. This work provides a plug-and-play solution for the HuggingFace ecosystem that democratizes access to advanced models on existing GPU infrastructure.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
Communication-free Sampling and 4D Hybrid Parallelism for Scalable Mini-batch GNN Training
arXiv:2604.02651v1 Announce Type: new
Abstract: Graph neural networks (GNNs) are widely used for learning on graph datasets derived from various real-world scenarios. Learning from extremely large graphs requires distributed training, and mini-batching with sampling is a popular approach for parallelizing GNN training. Existing distributed mini-batch approaches have significant performance bottlenecks due to expensive sampling methods and limited scaling when using data parallelism. In this work, we present ScaleGNN, a 4D parallel framework for scalable mini-batch GNN training that combines communication-free distributed sampling, 3D parallel matrix multiplication (PMM), and data parallelism. ScaleGNN introduces a uniform vertex sampling algorithm, enabling each process (GPU device) to construct its local mini-batch, i.e., subgraph partitions without any inter-process communication. 3D PMM enables scaling mini-batch training to much larger GPU counts than vanilla data parallelism with significantly lower communication overheads. We also present additional optimizations to overlap sampling with training, reduce communication overhead by sending data in lower precision, kernel fusion, and communication-computation overlap. We evaluate ScaleGNN on five graph datasets and demonstrate strong scaling up to 2048 GPUs on Perlmutter, 2048 GCDs on Frontier, and 1024 GPUs on Tuolumne. On Perlmutter, ScaleGNN achieves 3.5x end-to-end training speedup over the SOTA baseline on ogbn-products.
Fonte: arXiv cs.LG
Vision • Score 85
MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applications
arXiv:2604.02719v1 Announce Type: new
Abstract: We introduce MOMO, the first multi-sensor foundation model for Mars remote sensing. MOMO uses model merge to integrate representations learned independently from three key Martian sensors (HiRISE, CTX, and THEMIS), spanning resolutions from 0.25 m/pixel to 100 m/pixel. Central to our method is our novel Equal Validation Loss (EVL) strategy, which aligns checkpoints across sensors based on validation loss similarity before fusion via task arithmetic. This ensures models are merged at compatible convergence stages, leading to improved stability and generalization. We train MOMO on a large-scale, high-quality corpus of $\sim 12$ million samples curated from Mars orbital data and evaluate it on 9 downstream tasks from Mars-Bench. MOMO achieves better overall performance compared to ImageNet pre-trained, earth observation foundation model, sensor-specific pre-training, and fully-supervised baselines. Particularly on segmentation tasks, MOMO shows consistent and significant performance improvement. Our results demonstrate that model merging through an optimal checkpoint selection strategy provides an effective approach for building foundation models for multi-resolution data. The model weights, pretraining code, pretraining data, and evaluation code are available at: https://github.com/kerner-lab/MOMO.
Fonte: arXiv cs.CV
RL • Score 85
DEFT: Distribution-guided Efficient Fine-Tuning for Human Alignment
arXiv:2604.01787v1 Announce Type: new
Abstract: Reinforcement Learning from Human Feedback (RLHF), using algorithms like Proximal Policy Optimization (PPO), aligns Large Language Models (LLMs) with human values but is costly and unstable. Alternatives have been proposed to replace PPO or integrate Supervised Fine-Tuning (SFT) and contrastive learning for direct fine-tuning and value alignment. However, these methods still require voluminous data to learn preferences and may weaken the generalization ability of LLMs. To further enhance alignment efficiency and performance while mitigating the loss of generalization ability, this paper introduces Distribution-guided Efficient Fine-Tuning (DEFT), an efficient alignment framework incorporating data filtering and distributional guidance by calculating the differential distribution reward based on the output distribution of language model and the discrepancy distribution of preference data. A small yet high-quality subset is filtered from the raw data using a differential distribution reward, which is then incorporated into existing alignment methods to guide the model's output distribution. Experimental results demonstrate that the methods enhanced by DEFT outperform the original methods in both alignment capability and generalization ability, with significantly reduced training time.
Fonte: arXiv cs.CL
MLOps/Systems • Score 85
Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression
arXiv:2604.01609v1 Announce Type: new
Abstract: The deployment of Large Language Models is constrained by the memory and bandwidth demands of static weights and dynamic Key-Value cache. SVD-based compression provides a hardware-friendly solution to reduce these costs. However, existing methods suffer from two key limitations: some are suboptimal in reconstruction error, while others are theoretically optimal but practically inefficient. In this paper, we propose Swift-SVD, an activation-aware, closed-form compression framework that simultaneously guarantees theoretical optimum, practical efficiency and numerical stability. Swift-SVD incrementally aggregates covariance of output activations given a batch of inputs and performs a single eigenvalue decomposition after aggregation, enabling training-free, fast, and optimal layer-wise low-rank approximation. We employ effective rank to analyze local layer-wise compressibility and design a dynamic rank allocation strategy that jointly accounts for local reconstruction loss and end-to-end layer importance. Extensive experiments across six LLMs and eight datasets demonstrate that Swift-SVD outperforms state-of-the-art baselines, achieving optimal compression accuracy while delivering 3-70X speedups in end-to-end compression time. Our code will be released upon acceptance.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
SECURE: Stable Early Collision Understanding via Robust Embeddings in Autonomous Driving
arXiv:2604.01337v1 Announce Type: new
Abstract: While deep learning has significantly advanced accident anticipation, the robustness of these safety-critical systems against real-world perturbations remains a major challenge. We reveal that state-of-the-art models like CRASH, despite their high performance, exhibit significant instability in predictions and latent representations when faced with minor input perturbations, posing serious reliability risks. To address this, we introduce SECURE - Stable Early Collision Understanding Robust Embeddings, a framework that formally defines and enforces model robustness. SECURE is founded on four key attributes: consistency and stability in both prediction space and latent feature space. We propose a principled training methodology that fine-tunes a baseline model using a multi-objective loss, which minimizes divergence from a reference model and penalizes sensitivity to adversarial perturbations. Experiments on DAD and CCD datasets demonstrate that our approach not only significantly enhances robustness against various perturbations but also improves performance on clean data, achieving new state-of-the-art results.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
BTS-rPPG: Orthogonal Butterfly Temporal Shifting for Remote Photoplethysmography
arXiv:2604.01679v1 Announce Type: new
Abstract: Remote photoplethysmography (rPPG) enables contactless physiological sensing from facial videos by analyzing subtle appearance variations induced by blood circulation. However, modeling the temporal dynamics of these signals remains challenging, as many deep learning methods rely on temporal shifting or convolutional operators that aggregate information primarily from neighboring frames, resulting in predominantly local temporal modeling and limited temporal receptive fields. To address this limitation, we propose BTS-rPPG, a temporal modeling framework based on Orthogonal Butterfly Temporal Shifting (BTS). Inspired by the butterfly communication pattern in the Fast Fourier Transform (FFT), BTS establishes structured frame interactions via an XOR-based butterfly pairing schedule, progressively expanding the temporal receptive field and enabling efficient propagation of information across distant frames. Furthermore, we introduce an orthogonal feature transfer mechanism (OFT) that filters the source feature with respect to the target context before temporal shifting, retaining only the orthogonal component for cross-frame transmission. This reduces redundant feature propagation and encourages complementary temporal interaction. Extensive experiments on multiple benchmark datasets demonstrate that BTS-rPPG improves long-range temporal modeling of physiological dynamics and consistently outperforms existing temporal modeling strategies for rPPG estimation.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
An Online Machine Learning Multi-resolution Optimization Framework for Energy System Design Limit of Performance Analysis
arXiv:2604.01308v1 Announce Type: new
Abstract: Designing reliable integrated energy systems for industrial processes requires optimization and verification models across multiple fidelities, from architecture-level sizing to high-fidelity dynamic operation. However, model mismatch across fidelities obscures the sources of performance loss and complicates the quantification of architecture-to-operation performance gaps. We propose an online, machine-learning-accelerated multi-resolution optimization framework that estimates an architecture-specific upper bound on achievable performance while minimizing expensive high-fidelity model evaluations. We demonstrate the approach on a pilot energy system supplying a 1 MW industrial heat load. First, we solve a multi-objective architecture optimization to select the system configuration and component capacities. We then develop an machine learning (ML)-accelerated multi-resolution, receding-horizon optimal control strategy that approaches the achievable-performance bound for the specified architecture, given the additional controls and dynamics not captured by the architectural optimization model. The ML-guided controller adaptively schedules the optimization resolution based on predictive uncertainty and warm-starts high-fidelity solves using elite low-fidelity solutions. Our results on the pilot case study show that the proposed multi-resolution strategy reduces the architecture-to-operation performance gap by up to 42% relative to a rule-based controller, while reducing required high-fidelity model evaluations by 34% relative to the same multi-fidelity approach without ML guidance, enabling faster and more reliable design verification. Together, these gains make high-fidelity verification tractable, providing a practical upper bound on achievable operational performance.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
ZEUS: Accelerating Diffusion Models with Only Second-Order Predictor
arXiv:2604.01552v1 Announce Type: new
Abstract: Denoising generative models deliver high-fidelity generation but remain bottlenecked by inference latency due to the many iterative denoiser calls required during sampling. Training-free acceleration methods reduce latency by either sparsifying the model architecture or shortening the sampling trajectory. Current training-free acceleration methods are more complex than necessary: higher-order predictors amplify error under aggressive speedups, and architectural modifications hinder deployment. Beyond 2x acceleration, step skipping creates structural scarcity -- at most one fresh evaluation per local window -- leaving the computed output and its backward difference as the only causally grounded information. Based on this, we propose ZEUS, an acceleration method that predicts reduced denoiser evaluations using a second-order predictor, and stabilizes aggressive consecutive skipping with an interleaved scheme that avoids back-to-back extrapolations. ZEUS adds essentially zero overhead, no feature caches, and no architectural modifications, and it is compatible with different backbones, prediction objectives, and solver choices. Across image and video generation, ZEUS consistently improves the speed-fidelity performance over recent training-free baselines, achieving up to 3.2x end-to-end speedup while maintaining perceptual quality. Our code is available at: https://github.com/Ting-Justin-Jiang/ZEUS.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
NEMESIS: Noise-suppressed Efficient MAE with Enhanced Superpatch Integration Strategy
arXiv:2604.01612v1 Announce Type: new
Abstract: Volumetric CT imaging is essential for clinical diagnosis, yet annotating 3D volumes is expensive and time-consuming, motivating self-supervised learning (SSL) from unlabeled data. However, applying SSL to 3D CT remains challenging due to the high memory cost of full-volume transformers and the anisotropic spatial structure of CT data, which is not well captured by conventional masking strategies. We propose NEMESIS, a masked autoencoder (MAE) framework that operates on local 128x128x128 superpatches, enabling memory-efficient training while preserving anatomical detail. NEMESIS introduces three key components: (i) noise-enhanced reconstruction as a pretext task, (ii) Masked Anatomical Transformer Blocks (MATB) that perform dual-masking through parallel plane-wise and axis-wise token removal, and (iii) NEMESIS Tokens (NT) for cross-scale context aggregation. On the BTCV multi-organ classification benchmark, NEMESIS with a frozen backbone and a linear classifier achieves a mean AUROC of 0.9633, surpassing fully fine-tuned SuPreM (0.9493) and VoCo (0.9387). Under a low-label regime with only 10% of available annotations, it retains an AUROC of 0.9075, demonstrating strong label efficiency. Furthermore, the superpatch-based design reduces computational cost to 31.0 GFLOPs per forward pass, compared to 985.8 GFLOPs for the full-volume baseline, providing a scalable and robust foundation for 3D medical imaging.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
CuTeGen: An LLM-Based Agentic Framework for Generation and Optimization of High-Performance GPU Kernels using CuTe
arXiv:2604.01489v1 Announce Type: new
Abstract: High-performance GPU kernels are critical to modern machine learning systems, yet developing efficient implementations remains a challenging, expert-driven process due to the tight coupling between algorithmic structure, memory hierarchy usage, and hardware-specific optimizations. Recent work has explored using large language models (LLMs) to generate GPU kernels automatically, but generated implementations often struggle to maintain correctness and achieve competitive performance across iterative refinements. We present CuTeGen, an agentic framework for automated generation and optimization of GPU kernels that treats kernel development as a structured generate--test--refine workflow. Unlike approaches that rely on one-shot generation or large-scale search over candidate implementations, CuTeGen focuses on progressive refinement of a single evolving kernel through execution-based validation, structured debugging, and staged optimization. A key design choice is to generate kernels using the CuTe abstraction layer, which exposes performance-critical structures such as tiling and data movement while providing a more stable representation for iterative modification. To guide performance improvement, CuTeGen incorporates workload-aware optimization prompts and delayed integration of profiling feedback. Experimental results on matrix multiplication and activation workloads demonstrate that the framework produces functionally correct kernels and achieves competitive performance relative to optimized library implementations.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Sparse Spectral LoRA: Routed Experts for Medical VLMs
arXiv:2604.01310v1 Announce Type: new
Abstract: Large vision-language models (VLMs) excel on general benchmarks but often lack robustness in medical imaging, where heterogeneous supervision induces cross-dataset interference and sensitivity to data regime (i.e., how the supervisory signals are mixed). In realistic clinical workflows, data and tasks arrive sequentially, so naive continual training further leads to catastrophic forgetting. To address these challenges, we propose MedQwen, a parameter-efficient medical VLM that couples a spectrally routed Mixture-of-Experts (MoE) with a theoretically grounded scaling rule that aligns low-rank updates with a full-rank, fully fine-tuned MoE, without changing the base architecture. Concretely, we initialize each expert from non-overlapping singular value decomposition (SVD) segments of the pretrained weight and introduce a residual compensation and scaling scheme to enable stable expert specialization and consistent routing under distribution shift. Across 23 medical datasets covering visual question answering, report generation, radiology classification, and hallucination mitigation, MedQwen achieves strong, reliable performance: it approaches full fine-tuning on zero-shot classification with 339$\times$ fewer trainable parameters, and reduces sequential forgetting to $\sim$5\% where strong baselines degrade by $>$20-50\%.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
GPA: Learning GUI Process Automation from Demonstrations
arXiv:2604.01676v1 Announce Type: new
Abstract: GUI Process Automation (GPA) is a lightweight but general vision-based Robotic Process Automation (RPA), which enables fast and stable process replay with only a single demo. Addressing the fragility of traditional RPA and the non-deterministic risks of current vision language model-based GUI agents, GPA introduces three core benefits: (1) Robustness via Sequential Monte Carlo-based localization to handle rescaling and detection uncertainty; (2) Deterministic and Reliability safeguarded by readiness calibration; and (3) Privacy through fast, fully local execution. This approach delivers the adaptability, robustness, and security required for enterprise workflows. It can also be used as an MCP/CLI tool by other agents with coding capabilities so that the agent only reasons and orchestrates while GPA handles the GUI execution. We conducted a pilot experiment to compare GPA with Gemini 3 Pro (with CUA tools) and found that GPA achieves higher success rate with 10 times faster execution speed in finishing long-horizon GUI tasks.
Fonte: arXiv cs.CV
Vision • Score 85
Automatic Image-Level Morphological Trait Annotation for Organismal Images
arXiv:2604.01619v1 Announce Type: new
Abstract: Morphological traits are physical characteristics of biological organisms that provide vital clues on how organisms interact with their environment. Yet extracting these traits remains a slow, expert-driven process, limiting their use in large-scale ecological studies. A major bottleneck is the absence of high-quality datasets linking biological images to trait-level annotations. In this work, we demonstrate that sparse autoencoders trained on foundation-model features yield monosemantic, spatially grounded neurons that consistently activate on meaningful morphological parts. Leveraging this property, we introduce a trait annotation pipeline that localizes salient regions and uses vision-language prompting to generate interpretable trait descriptions. Using this approach, we construct Bioscan-Traits, a dataset of 80K trait annotations spanning 19K insect images from BIOSCAN-5M. Human evaluation confirms the biological plausibility of the generated morphological descriptions. We assess design sensitivity through a comprehensive ablation study, systematically varying key design choices and measuring their impact on the quality of the resulting trait descriptions. By annotating traits with a modular pipeline rather than prohibitively expensive manual efforts, we offer a scalable way to inject biologically meaningful supervision into foundation models, enable large-scale morphological analyses, and bridge the gap between ecological relevance and machine-learning practicality.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
Prime Once, then Reprogram Locally: An Efficient Alternative to Black-Box Service Model Adaptation
arXiv:2604.01474v1 Announce Type: new
Abstract: Adapting closed-box service models (i.e., APIs) for target tasks typically relies on reprogramming via Zeroth-Order Optimization (ZOO). However, this standard strategy is known for extensive, costly API calls and often suffers from slow, unstable optimization. Furthermore, we observe that this paradigm faces new challenges with modern APIs (e.g., GPT-4o). These models can be less sensitive to the input perturbations ZOO relies on, thereby hindering performance gains. To address these limitations, we propose an Alternative efficient Reprogramming approach for Service models (AReS). Instead of direct, continuous closed-box optimization, AReS initiates a single-pass interaction with the service API to prime an amenable local pre-trained encoder. This priming stage trains only a lightweight layer on top of the local encoder, making it highly receptive to the subsequent glass-box (white-box) reprogramming stage performed directly on the local model. Consequently, all subsequent adaptation and inference rely solely on this local proxy, eliminating all further API costs. Experiments demonstrate AReS's effectiveness where prior ZOO-based methods struggle: on GPT-4o, AReS achieves a +27.8% gain over the zero-shot baseline, a task where ZOO-based methods provide little to no improvement. Broadly, across ten diverse datasets, AReS outperforms state-of-the-art methods (+2.5% for VLMs, +15.6% for standard VMs) while reducing API calls by over 99.99%. AReS thus provides a robust and practical solution for adapting modern closed-box models.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Machine Learning for Network Attacks Classification and Statistical Evaluation of Adversarial Learning Methodologies for Synthetic Data Generation
arXiv:2603.17717v2 Announce Type: replace-cross
Abstract: Supervised detection of network attacks has always been a critical part of network intrusion detection systems (NIDS). Nowadays, in a pivotal time for artificial intelligence (AI), with even more sophisticated attacks that utilize advanced techniques, such as generative artificial intelligence (GenAI) and reinforcement learning, it has become a vital component if we wish to protect our personal data, which are scattered across the web. In this paper, we address two tasks, in the first unified multi-modal NIDS dataset, which incorporates flow-level data, packet payload information and temporal contextual features, from the reprocessed CIC-IDS-2017, CIC-IoT-2023, UNSW-NB15 and CIC-DDoS-2019, with the same feature space. In the first task we use machine learning (ML) algorithms, with stratified cross validation, in order to prevent network attacks, with stability and reliability. In the second task we use adversarial learning algorithms to generate synthetic data, compare them with the real ones and evaluate their fidelity, utility and privacy using the SDV framework, f-divergences, distinguishability and non-parametric statistical tests. The findings provide stable ML models for intrusion detection and generative models with high fidelity and utility, by combining the Synthetic Data Vault framework, the TRTS and TSTR tests, with non-parametric statistical tests and f-divergence measures.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
F3DGS: Federated 3D Gaussian Splatting for Decentralized Multi-Agent World Modeling
arXiv:2604.01605v1 Announce Type: new
Abstract: We present F3DGS, a federated 3D Gaussian Splatting framework for decentralized multi-agent 3D reconstruction. Existing 3DGS pipelines assume centralized access to all observations, which limits their applicability in distributed robotic settings where agents operate independently, and centralized data aggregation may be restricted. Directly extending centralized training to multi-agent systems introduces communication overhead and geometric inconsistency. F3DGS first constructs a shared geometric scaffold by registering locally merged LiDAR point clouds from multiple clients to initialize a global 3DGS model. During federated optimization, Gaussian positions are fixed to preserve geometric alignment, while each client updates only appearance-related attributes, including covariance, opacity, and spherical harmonic coefficients. The server aggregates these updates using visibility-aware aggregation, weighting each client's contribution by how frequently it observed each Gaussian, resolving the partial-observability challenge inherent to multi-agent exploration. To evaluate decentralized reconstruction, we collect a multi-sequence indoor dataset with synchronized LiDAR, RGB, and IMU measurements. Experiments show that F3DGS achieves reconstruction quality comparable to centralized training while enabling distributed optimization across agents. The dataset, development kit, and source code will be publicly released.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
Generative Profiling for Soft Real-Time Systems and its Applications to Resource Allocation
arXiv:2604.01441v1 Announce Type: cross
Abstract: Modern real-time systems require accurate characterization of task timing behavior to ensure predictable performance, particularly on complex hardware architectures. Existing methods, such as worst-case execution time analysis, often fail to capture the fine-grained timing behaviors of a task under varying resource contexts (e.g., an allocation of cache, memory bandwidth, and CPU frequency), which is necessary to achieve efficient resource utilization. In this paper, we introduce a novel generative profiling approach that synthesizes context-dependent, fine-grained timing profiles for real-time tasks, including those for unmeasured resource allocations. Our approach leverages a nonparametric, conditional multi-marginal Schr\"odinger Bridge (MSB) formulation to generate accurate execution profiles for unseen resource contexts, with maximum likelihood guarantees. We demonstrate the efficiency and effectiveness of our approach through real-world benchmarks, and showcase its practical utility in a representative case study of adaptive multicore resource allocation for real-time systems.
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
Koopman Subspace Pruning in Reproducing Kernel Hilbert Spaces via Principal Vectors
arXiv:2604.01459v1 Announce Type: cross
Abstract: Data-driven approximations of the infinite-dimensional Koopman operator rely on finite-dimensional projections, where the predictive accuracy of the resulting models hinges heavily on the invariance of the chosen subspace. Subspace pruning systematically discards geometrically misaligned directions to enhance this invariance proximity, which formally corresponds to the largest principal angle between the subspace and its image under the operator. Yet, existing techniques are largely restricted to Euclidean settings. To bridge this gap, this paper presents an approach for computing principal angles and vectors to enable Koopman subspace pruning within a Reproducing Kernel Hilbert Space (RKHS) geometry. We first outline an exact computational routine, which is subsequently scaled for large datasets using randomized Nystrom approximations. Based on these foundations, we introduce the Kernel-SPV and Approximate Kernel-SPV algorithms for targeted subspace refinement via principal vectors. Simulation results validate our approach.
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
Sven: Singular Value Descent as a Computationally Efficient Natural Gradient Method
arXiv:2604.01279v1 Announce Type: new
Abstract: We introduce Sven (Singular Value dEsceNt), a new optimization algorithm for neural networks that exploits the natural decomposition of loss functions into a sum over individual data points, rather than reducing the full loss to a single scalar before computing a parameter update. Sven treats each data point's residual as a separate condition to be satisfied simultaneously, using the Moore-Penrose pseudoinverse of the loss Jacobian to find the minimum-norm parameter update that best satisfies all conditions at once. In practice, this pseudoinverse is approximated via a truncated singular value decomposition, retaining only the $k$ most significant directions and incurring a computational overhead of only a factor of $k$ relative to stochastic gradient descent. This is in comparison to traditional natural gradient methods, which scale as the square of the number of parameters. We show that Sven can be understood as a natural gradient method generalized to the over-parametrized regime, recovering natural gradient descent in the under-parametrized limit. On regression tasks, Sven significantly outperforms standard first-order methods including Adam, converging faster and to a lower final loss, while remaining competitive with LBFGS at a fraction of the wall-time cost. We discuss the primary challenge to scaling, namely memory overhead, and propose mitigation strategies. Beyond standard machine learning benchmarks, we anticipate that Sven will find natural application in scientific computing settings where custom loss functions decompose into several conditions.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
GradPower: Powering Gradients for Faster Language Model Pre-Training
arXiv:2505.24275v2 Announce Type: replace-cross
Abstract: We propose GradPower, a lightweight gradient-transformation technique for accelerating language model pre-training. Given a gradient vector $g=(g_i)_i$, GradPower first applies the elementwise sign-power transformation: $\varphi_p(g)=({\rm sign}(g_i)|g_i|^p)_{i}$ for a fixed $p>0$, and then feeds the transformed gradient into a base optimizer. Notably, GradPower requires only a single-line code change and no modifications to the base optimizer's internal logic, including the hyperparameters. When applied to Adam (termed AdamPower), GradPower consistently achieves lower terminal loss across diverse architectures (LLaMA, Qwen2MoE), parameter scales (66M to 2B), datasets (C4, OpenWebText), and learning-rate schedules (cosine, warmup-stable-decay). The most pronounced gains are observed when training modern mixture-of-experts models with warmup-stable-decay schedules. GradPower also integrates seamlessly with other state-of-the-art optimizers, such as Muon, yielding further improvements. Finally, we provide theoretical analyses that reveal the underlying mechanism of GradPower and highlight the influence of gradient noise.
Fonte: arXiv stat.ML
RL • Score 85
Soft MPCritic: Amortized Model Predictive Value Iteration
arXiv:2604.01477v1 Announce Type: new
Abstract: Reinforcement learning (RL) and model predictive control (MPC) offer complementary strengths, yet combining them at scale remains computationally challenging. We propose soft MPCritic, an RL-MPC framework that learns in (soft) value space while using sample-based planning for both online control and value target generation. soft MPCritic instantiates MPC through model predictive path integral control (MPPI) and trains a terminal Q-function with fitted value iteration, aligning the learned value function with the planner and implicitly extending the effective planning horizon. We introduce an amortized warm-start strategy that recycles planned open-loop action sequences from online observations when computing batched MPPI-based value targets. This makes soft MPCritic computationally practical, while preserving solution quality. soft MPCritic plans in a scenario-based fashion with an ensemble of dynamic models trained for next-step prediction accuracy. Together, these ingredients enable soft MPCritic to learn effectively through robust, short-horizon planning on classic and complex control tasks. These results establish soft MPCritic as a practical and scalable blueprint for synthesizing MPC policies in settings where policy extraction and direct, long-horizon planning may fail.
Fonte: arXiv cs.LG
Vision • Score 85
HOT: Harmonic-Constrained Optimal Transport for Remote Photoplethysmography Domain Adaptation
arXiv:2604.01675v1 Announce Type: new
Abstract: Remote photoplethysmography (rPPG) enables non-contact physiological measurement from facial videos; however, its practical deployment is often hindered by substantial performance degradation under domain shift. While recent deep learning-based rPPG methods have achieved strong performance on individual datasets, they frequently overfit to appearance-related factors, such as illumination, camera characteristics, and color response, that vary significantly across domains. To address this limitation, we introduce frequency domain adaptation (FDA) as a principled strategy for modeling appearance variation in rPPG. By transferring low-frequency spectral components that encode domain-dependent appearance characteristics, FDA encourages rPPG models to learn invariance to appearance variations while retaining cardiac-induced signals. To further support physiologically consistent alignment under such appearance variation, we propose Harmonic-Constrained Optimal Transport (HOT), which leverages the harmonic property of cardiac signals to guide alignment between original and FDA-transferred representations. Extensive cross-dataset experiments demonstrate that the proposed FDA and HOT framework effectively enhances the robustness and generalization of rPPG models across diverse datasets.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Expert-Choice Routing Enables Adaptive Computation in Diffusion Language Models
arXiv:2604.01622v1 Announce Type: new
Abstract: Diffusion language models (DLMs) enable parallel, non-autoregressive text generation, yet existing DLM mixture-of-experts (MoE) models inherit token-choice (TC) routing from autoregressive systems, leading to load imbalance and rigid computation allocation. We show that expert-choice (EC) routing is a better fit for DLMs: it provides deterministic load balancing by design, yielding higher throughput and faster convergence than TC. Building on the property that EC capacity is externally controllable, we introduce timestep-dependent expert capacity, which varies expert allocation according to the denoising step. We find that allocating more capacity to low-mask-ratio steps consistently achieves the best performance under matched FLOPs, and provide a mechanistic explanation: tokens in low-mask-ratio contexts exhibit an order-of-magnitude higher learning efficiency, so concentrating compute on these steps yields the largest marginal return. Finally, we show that existing pretrained TC DLMs can be retrofitted to EC by replacing only the router, achieving faster convergence and improved accuracy across diverse downstream tasks. Together, these results establish EC routing as a superior paradigm for DLM MoE models and demonstrate that computation in DLMs can be treated as an adaptive policy rather than a fixed architectural constant. Code is available at https://github.com/zhangshuibai/EC-DLM.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Variational LSTM with Augmented Inputs: Nonlinear Response History Metamodeling with Aleatoric and Epistemic Uncertainty
arXiv:2604.01587v1 Announce Type: new
Abstract: Uncertainty propagation in high-dimensional nonlinear dynamic structural systems is pivotal in state-of-the-art performance-based design and risk assessment, where uncertainties from both excitations and structures, i.e., the aleatoric uncertainty, must be considered. This poses a significant challenge due to heavy computational demands. Machine learning techniques are thus introduced as metamodels to alleviate this burden. However, the "black box" nature of Machine learning models underscores the necessity of avoiding overly confident predictions, particularly when data and training efforts are insufficient. This creates a need, in addition to considering the aleatoric uncertainty, of estimating the uncertainty related to the prediction confidence, i.e., epistemic uncertainty, for machine learning-based metamodels. We developed a probabilistic metamodeling technique based on a variational long short-term memory (LSTM) with augmented inputs to simultaneously capture aleatoric and epistemic uncertainties. Key random system parameters are treated as augmented inputs alongside excitation series carrying record-to-record variability to capture the full range of aleatoric uncertainty. Meanwhile, epistemic uncertainty is effectively approximated via the Monte Carlo dropout scheme. Unlike computationally expensive full Bayesian approaches, this method incurs negligible additional training costs while enabling nearly cost-free uncertainty simulation. The proposed technique is demonstrated through multiple case studies involving stochastic seismic or wind excitations. Results show that the calibrated metamodels accurately reproduce nonlinear response time histories and provide confidence bounds indicating the associated epistemic uncertainty.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
Towards Intrinsically Calibrated Uncertainty Quantification in Industrial Data-Driven Models via Diffusion Sampler
arXiv:2604.01870v1 Announce Type: new
Abstract: In modern process industries, data-driven models are important tools for real-time monitoring when key performance indicators are difficult to measure directly. While accurate predictions are essential, reliable uncertainty quantification (UQ) is equally critical for safety, reliability, and decision-making, but remains a major challenge in current data-driven approaches. In this work, we introduce a diffusion-based posterior sampling framework that inherently produces well-calibrated predictive uncertainty via faithful posterior sampling, eliminating the need for post-hoc calibration. In extensive evaluations on synthetic distributions, the Raman-based phenylacetic acid soft sensor benchmark, and a real ammonia synthesis case study, our method achieves practical improvements over existing UQ techniques in both uncertainty calibration and predictive accuracy. These results highlight diffusion samplers as a principled and scalable paradigm for advancing uncertainty-aware modeling in industrial applications.
Fonte: arXiv cs.LG
RL • Score 85
Learning with Incomplete Context: Linear Contextual Bandits with Pretrained Imputation
arXiv:2510.09908v3 Announce Type: replace
Abstract: The rise of large-scale pretrained models has made it feasible to generate predictive or synthetic features at low cost, raising the question of how to incorporate such surrogate predictions into downstream decision-making. We study this problem in the setting of online linear contextual bandits, where contexts may be complex, nonstationary, and only partially observed. In addition to bandit data, we assume access to an auxiliary dataset containing fully observed contexts--common in practice since such data are collected without adaptive interventions. We propose PULSE-UCB, an algorithm that leverages pretrained models trained on the auxiliary data to impute missing features during online decision-making. We establish regret guarantees that decompose into a standard bandit term plus an additional component reflecting pretrained model quality. In the i.i.d. context case with H\"older-smooth missing features, PULSE-UCB achieves near-optimal performance, supported by matching lower bounds. Our results quantify how uncertainty in predicted contexts affects decision quality and how much historical data is needed to improve downstream learning.
Fonte: arXiv stat.ML
RL • Score 85
Physics Informed Reinforcement Learning with Gibbs Priors for Topology Control in Power Grids
arXiv:2604.01830v1 Announce Type: new
Abstract: Topology control for power grid operation is a challenging sequential decision making problem because the action space grows combinatorially with the size of the grid and action evaluation through simulation is computationally expensive. We propose a physics-informed Reinforcement Learning framework that combines semi-Markov control with a Gibbs prior, that encodes the system's physics, over the action space. The decision is only taken when the grid enters a hazardous regime, while a graph neural network surrogate predicts the post action overload risk of feasible topology actions. These predictions are used to construct a physics-informed Gibbs prior that both selects a small state-dependent candidate set and reweights policy logits before action selection. In this way, our method reduces exploration difficulty and online simulation cost while preserving the flexibility of a learned policy. We evaluate the approach in three realistic benchmark environments of increasing difficulty. Across all settings, the proposed method achieves a strong balance between control quality and computational efficiency: it matches oracle-level performance while being approximately $6\times$ faster on the first benchmark, reaches $94.6\%$ of oracle reward with roughly $200\times$ lower decision time on the second one, and on the most challenging benchmark improves over a PPO baseline by up to $255\%$ in reward and $284\%$ in survived steps while remaining about $2.5\times$ faster than a strong specialized engineering baseline. These results show that our method provides an effective mechanism for topology control in power grids.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
PI-JEPA: Label-Free Surrogate Pretraining for Coupled Multiphysics Simulation via Operator-Split Latent Prediction
arXiv:2604.01349v1 Announce Type: new
Abstract: Reservoir simulation workflows face a fundamental data asymmetry: input parameter fields (geostatistical permeability realizations, porosity distributions) are free to generate in arbitrary quantities, yet existing neural operator surrogates require large corpora of expensive labeled simulation trajectories and cannot exploit this unlabeled structure. We introduce \textbf{PI-JEPA} (Physics-Informed Joint Embedding Predictive Architecture), a surrogate pretraining framework that trains \emph{without any completed PDE solves}, using masked latent prediction on unlabeled parameter fields under per-sub-operator PDE residual regularization. The predictor bank is structurally aligned with the Lie--Trotter operator-splitting decomposition of the governing equations, dedicating a separate physics-constrained latent module to each sub-process (pressure, saturation transport, reaction), enabling fine-tuning with as few as 100 labeled simulation runs. On single-phase Darcy flow, PI-JEPA achieves $1.9\times$ lower error than FNO and $2.4\times$ lower error than DeepONet at $N_\ell{=}100$, with 24\% improvement over supervised-only training at $N_\ell{=}500$, demonstrating that label-free surrogate pretraining substantially reduces the simulation budget required for multiphysics surrogate deployment.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
Model Merging via Data-Free Covariance Estimation
arXiv:2604.01329v1 Announce Type: new
Abstract: Model merging provides a way of cheaply combining individual models to produce a model that inherits each individual's capabilities. While some merging methods can approach the performance of multitask training, they are often heuristically motivated and lack theoretical justification. A principled alternative is to pose model merging as a layer-wise optimization problem that directly minimizes interference between tasks. However, this formulation requires estimating per-layer covariance matrices from data, which may not be available when performing merging. In contrast, many of the heuristically-motivated methods do not require auxiliary data, making them practically advantageous. In this work, we revisit the interference minimization framework and show that, under certain conditions, covariance matrices can be estimated directly from difference matrices, eliminating the need for data while also reducing computational costs. We validate our approach across vision and language benchmarks on models ranging from 86M parameters to 7B parameters, outperforming previous data-free state-of-the-art merging methods
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Massively Parallel Exact Inference for Hawkes Processes
arXiv:2604.01342v1 Announce Type: new
Abstract: Multivariate Hawkes processes are a widely used class of self-exciting point processes, but maximum likelihood estimation naively scales as $O(N^2)$ in the number of events. The canonical linear exponential Hawkes process admits a faster $O(N)$ recurrence, but prior work evaluates this recurrence sequentially, without exploiting parallelization on modern GPUs. We show that the Hawkes process intensity can be expressed as a product of sparse transition matrices admitting a linear-time associative multiply, enabling computation via a parallel prefix scan. This yields a simple yet massively parallelizable algorithm for maximum likelihood estimation of linear exponential Hawkes processes. Our method reduces the computational complexity to approximately $O(N/P)$ with $P$ parallel processors, and naturally yields a batching scheme to maintain constant memory usage, avoiding GPU memory constraints. Importantly, it computes the exact likelihood without any additional assumptions or approximations, preserving the simplicity and interpretability of the model. We demonstrate orders-of-magnitude speedups on simulated and real datasets, scaling to thousands of nodes and tens of millions of events, substantially beyond scales reported in prior work. We provide an open-source PyTorch library implementing our optimizations.
Fonte: arXiv cs.LG
Applications • Score 85
Sit-to-Stand Transitions Detection and Duration Measurement Using Smart Lacelock Sensor
arXiv:2604.00175v1 Announce Type: new
Abstract: Postural stability during movement is fundamental to independent living, fall prevention, and overall health, particularly among older adults who experience age-related declines in balance, muscle strength, and mobility. Among daily functional activities, the Sit-to-Stand (SiSt) transition is a critical indicator of lower-limb strength, musculoskeletal health, and fall risk, making it an essential parameter for assessing functional capacity and monitoring physical decline in aging populations. This study presents a methodology SiSt transition detection and duration measurement using the Smart Lacelock sensor, a lightweight, shoe-mounted device that integrates a load cell, accelerometer, and gyroscope for motion analysis. The methodology was evaluated in 16 older adults (age: mean: 76.84, SD: 3.45 years) performing SiSt tasks within the Short Physical Performance Battery (SPPB) protocol. Features extracted from multimodal signals were used to train and evaluate four machine learning classifiers using a 4-fold participant-independent cross-validation to classify SiSt transitions and measure their duration. The bagged tree classifier achieved an accuracy of 0.98 and an F1 score of 0.8 in classifying SiSt transition. The mean absolute error in duration measurement of the correctly classified transitions was 0.047, and the SD was 0.07 seconds. These findings highlight the potential of the Smart Lacelock sensor for real-world fall-risk assessment and mobility monitoring in older adults.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Two-Stage Optimizer-Aware Online Data Selection for Large Language Models
arXiv:2604.00001v1 Announce Type: cross
Abstract: Gradient-based data selection offers a principled framework for estimating sample utility in large language model (LLM) fine-tuning, but existing methods are mostly designed for offline settings. They are therefore less suited to online fine-tuning, where data arrives sequentially, sample utility is step-dependent, and the effective update geometry is shaped by adaptive optimizers. We propose an optimizer-aware framework for gradient-based online data selection and reweighting in LLM fine-tuning. Our key idea is to view online selection not as static sample ranking, but as shaping the next target-oriented update under the optimizer state. We formulate this as an optimizer-aware update-matching problem, establish its connection to second-order target utility, and show why subset-level construction must account for interactions and redundancy among selected samples. Based on this view, we develop a two-stage Filter-then-Weight algorithm that first filters geometrically useful candidates and then optimizes their coefficients. To make the framework practical for LLMs, we introduce a factorized outer-product gradient representation and optimized matrix computations for long-context data. Experiments show that our method consistently improves convergence and downstream performance over existing online data selection baselines under the same data budget.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
BloClaw: An Omniscient, Multi-Modal Agentic Workspace for Next-Generation Scientific Discovery
arXiv:2604.00550v1 Announce Type: new
Abstract: The integration of Large Language Models (LLMs) into life sciences has catalyzed the development of "AI Scientists." However, translating these theoretical capabilities into deployment-ready research environments exposes profound infrastructural vulnerabilities. Current frameworks are bottlenecked by fragile JSON-based tool-calling protocols, easily disrupted execution sandboxes that lose graphical outputs, and rigid conversational interfaces inherently ill-suited for high-dimensional scientific data.We introduce BloClaw, a unified, multi-modal operating system designed for Artificial Intelligence for Science (AI4S). BloClaw reconstructs the Agent-Computer Interaction (ACI) paradigm through three architectural innovations: (1) An XML-Regex Dual-Track Routing Protocol that statistically eliminates serialization failures (0.2% error rate vs. 17.6% in JSON); (2) A Runtime State Interception Sandbox that utilizes Python monkey-patching to autonomously capture and compile dynamic data visualizations (Plotly/Matplotlib), circumventing browser CORS policies; and (3) A State-Driven Dynamic Viewport UI that morphs seamlessly between a minimalist command deck and an interactive spatial rendering engine. We comprehensively benchmark BloClaw across cheminformatics (RDKit), de novo 3D protein folding via ESMFold, molecular docking, and autonomous Retrieval-Augmented Generation (RAG), establishing a highly robust, self-evolving paradigm for computational research assistants. The open-source repository is available at https://github.com/qinheming/BloClaw.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Decision-Centric Design for LLM Systems
arXiv:2604.00414v1 Announce Type: new
Abstract: LLM systems must make control decisions in addition to generating outputs: whether to answer, clarify, retrieve, call tools, repair, or escalate. In many current architectures, these decisions remain implicit within generation, entangling assessment and action in a single model call and making failures hard to inspect, constrain, or repair. We propose a decision-centric framework that separates decision-relevant signals from the policy that maps them to actions, turning control into an explicit and inspectable layer of the system. This separation supports attribution of failures to signal estimation, decision policy, or execution, and enables modular improvement of each component. It unifies familiar single-step settings such as routing and adaptive inference, and extends naturally to sequential settings in which actions alter the information available before acting. Across three controlled experiments, the framework reduces futile actions, improves task success, and reveals interpretable failure modes. More broadly, it offers a general architectural principle for building more reliable, controllable, and diagnosable LLM systems.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Open, Reliable, and Collective: A Community-Driven Framework for Tool-Using AI Agents
arXiv:2604.00137v1 Announce Type: new
Abstract: Tool-integrated LLMs can retrieve, compute, and take real-world actions via external tools, but reliability remains a key bottleneck. We argue that failures stem from both tool-use accuracy (how well an agent invokes a tool) and intrinsic tool accuracy (the tool's own correctness), while most prior work emphasizes the former. We introduce OpenTools, a community-driven toolbox that standardizes tool schemas, provides lightweight plug-and-play wrappers, and evaluates tools with automated test suites and continuous monitoring. We also release a public web demo where users can run predefined agents and tools and contribute test cases, enabling reliability reports to evolve as tools change. OpenTools includes the core framework, an initial tool set, evaluation pipelines, and a contribution protocol. Experiments and evaluations show improved end-to-end reproducibility and task performance; community-contributed, higher-quality task-specific tools deliver 6%-22% relative gains over an existing toolbox across multiple agent architectures on downstream tasks and benchmarks, highlighting the importance of intrinsic tool accuracy.
Fonte: arXiv cs.AI
RecSys • Score 85
Preference Guided Iterated Pareto Referent Optimisation for Accessible Route Planning
arXiv:2604.00795v1 Announce Type: new
Abstract: We propose the Preference Guided Iterated Pareto Referent Optimisation (PG-IPRO) for urban route planning for people with different accessibility requirements and preferences. With this algorithm the user can interact with the system by giving feedback on a route, i.e., the user can say which objective should be further minimized, or conversely can be relaxed. This leads to intuitive user interaction, that is especially effective during early iterations compared to information-gain-based interaction. Furthermore, due to PG-IPRO's iterative nature, the full set of alternative, possibly optimal policies (the Pareto front), is never computed, leading to higher computational efficiency and shorter waiting times for users.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
Inverse-Free Sparse Variational Gaussian Processes
arXiv:2604.00697v1 Announce Type: new
Abstract: Gaussian processes (GPs) offer appealing properties but are costly to train at scale. Sparse variational GP (SVGP) approximations reduce cost yet still rely on Cholesky decompositions of kernel matrices, ill-suited to low-precision, massively parallel hardware. While one can construct valid variational bounds that rely only on matrix multiplications (matmuls) via an auxiliary matrix parameter, optimising them with off-the-shelf first-order methods is challenging. We make the inverse-free approach practical by proposing a better-conditioned bound and deriving a matmul-only natural-gradient update for the auxiliary parameter, markedly improving stability and convergence. We further provide simple heuristics, such as step-size schedules and stopping criteria, that make the overall optimisation routine fit seamlessly into existing workflows. Across regression and classification benchmarks, we demonstrate that our method 1) serves as a drop-in replacement in SVGP-based models (e.g., deep GPs), 2) recovers similar performance to traditional methods, and 3) can be faster than baselines when well tuned.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
Collaborative AI Agents and Critics for Fault Detection and Cause Analysis in Network Telemetry
arXiv:2604.00319v1 Announce Type: new
Abstract: We develop algorithms for collaborative control of AI agents and critics in a multi-actor, multi-critic federated multi-agent system. Each AI agent and critic has access to classical machine learning or generative AI foundation models. The AI agents and critics collaborate with a central server to complete multimodal tasks such as fault detection, severity, and cause analysis in a network telemetry system, text-to-image generation, video generation, healthcare diagnostics from medical images and patient records, etcetera. The AI agents complete their tasks and send them to AI critics for evaluation. The critics then send feedback to agents to improve their responses. Collaboratively, they minimize the overall cost to the system with no inter-agent or inter-critic communication. AI agents and critics keep their cost functions or derivatives of cost functions private. Using multi-time scale stochastic approximation techniques, we provide convergence guarantees on the time-average active states of AI agents and critics. The communication overhead is a little on the system, of the order of $\mathcal{O}(m)$, for $m$ modalities and is independent of the number of AI agents and critics. Finally, we present an example of fault detection, severity, and cause analysis in network telemetry and thorough evaluation to check the algorithm's efficacy.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
More Human, More Efficient: Aligning Annotations with Quantized SLMs
arXiv:2604.00586v1 Announce Type: new
Abstract: As Large Language Model (LLM) capabilities advance, the demand for high-quality annotation of exponentially increasing text corpora has outpaced human capacity, leading to the widespread adoption of LLMs in automatic evaluation and annotation. However, proprietary LLMs often exhibit systematic biases that diverge from human expert consensus, lacks reproducibility, and raises data privacy concerns. Our work examines the viability of finetuning a quantized Small Language Model of 1.7B parameter size on limited human-annotated data to serve as a highly aligned, deterministic evaluator and annotator. By implementing a custom, multi-dimensional rubric framework and simple augmentation and regularization techniques, the proposed approach achieves higher inter-annotator agreement (0.23 points increase in Krippendorff's $\alpha$) than the best performing state-of-the-art proprietary LLM. We also demonstrate the generalizability of the proposed training pipeline on a separate emotion classification task. The results show that task-specific alignment and efficient 4-bit quantized fine-tuning provide superior open-source alternative to using proprietary models for evaluation and annotation. Our finetuning approach is publicly available at https://github.com/jylee-k/slm-judge.
Fonte: arXiv cs.CL
Privacy/Security/Fairness • Score 92
FecalFed: Privacy-Preserving Poultry Disease Detection via Federated Learning
arXiv:2604.00559v1 Announce Type: new
Abstract: Early detection of highly pathogenic avian influenza (HPAI) and endemic poultry diseases is critical for global food security. While computer vision models excel at classifying diseases from fecal imaging, deploying these systems at scale is bottlenecked by farm data privacy concerns and institutional data silos. Furthermore, existing open-source agricultural datasets frequently suffer from severe, undocumented data contamination. In this paper, we introduce $\textbf{FecalFed}$, a privacy-preserving federated learning framework for poultry disease classification. We first curate and release $\texttt{poultry-fecal-fl}$, a rigorously deduplicated dataset of 8,770 unique images across four disease classes, revealing and eliminating a 46.89$\%$ duplication rate in popular public repositories. To simulate realistic agricultural environments, we evaluate FecalFed under highly heterogeneous, non-IID conditions (Dirichlet $\alpha=0.5$). While isolated single-farm training collapses under this data heterogeneity, yielding only 64.86$\%$ accuracy, our federated approach recovers performance without centralizing sensitive data. Specifically, utilizing server-side adaptive optimization (FedAdam) with a Swin-Small architecture achieves 90.31$\%$ accuracy, closely approaching the centralized upper bound of 95.10\%. Furthermore, we demonstrate that an edge-optimized Swin-Tiny model maintains highly competitive performance at 89.74$\%$, establishing a highly efficient, privacy-first blueprint for on-farm avian disease monitoring.
Fonte: arXiv cs.CV
Vision • Score 85
Improving Generalization of Deep Learning for Brain Metastases Segmentation Across Institutions
arXiv:2604.00397v1 Announce Type: new
Abstract: Background: Deep learning has demonstrated significant potential for automated brain metastases (BM) segmentation; however, models trained at a singular institution often exhibit suboptimal performance at various sites due to disparities in scanner hardware, imaging protocols, and patient demographics. The goal of this work is to create a domain adaptation framework that will allow for BM segmentation to be used across multiple institutions.
Methods: We propose a VAE-MMD preprocessing pipeline that combines variational autoencoders (VAE) with maximum mean discrepancy (MMD) loss, incorporating skip connections and self-attention mechanisms alongside nnU-Net segmentation. The method was tested on 740 patients from four public databases: Stanford, UCSF, UCLM, and PKG, evaluated by domain classifier's accuracy, sensitivity, precision, F1/F2 scores, surface Dice (sDice), and 95th percentile Hausdorff distance (HD95).
Results: VAE-MMD reduced domain classifier accuracy from 0.91 to 0.50, indicating successful feature alignment across institutions. Reconstructed volumes attained a PSNR greater than 36 dB, maintaining anatomical accuracy. The combined method raised the mean F1 by 11.1% (0.700 to 0.778), the mean sDice by 7.93% (0.7121 to 0.7686), and reduced the mean HD95 by 65.5% (11.33 to 3.91 mm) across all four centers compared to the baseline nnU-Net.
Conclusions: VAE-MMD effectively diminishes cross-institutional data heterogeneity and enhances BM segmentation generalization across volumetric, detection, and boundary-level metrics without necessitating target-domain labels, thereby overcoming a significant obstacle to the clinical implementation of AI-assisted segmentation.
Fonte: arXiv cs.CV
Multimodal • Score 90
OmniMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory
arXiv:2604.01007v1 Announce Type: new
Abstract: AI agents increasingly operate over extended time horizons, yet their ability to retain, organize, and recall multimodal experiences remains a critical bottleneck. Building effective lifelong memory requires navigating a vast design space spanning architecture, retrieval strategies, prompt engineering, and data pipelines; this space is too large and interconnected for manual exploration or traditional AutoML to explore effectively. We deploy an autonomous research pipeline to discover OmniMem, a unified multimodal memory framework for lifelong AI agents. Starting from a na\"ive baseline (F1=0.117 on LoCoMo), the pipeline autonomously executes ${\sim}50$ experiments across two benchmarks, diagnosing failure modes, proposing architectural modifications, and repairing data pipeline bugs, all without human intervention in the inner loop. The resulting system achieves state-of-the-art on both benchmarks, improving F1 by +411% on LoCoMo (0.117$\to$0.598) and +214% on Mem-Gallery (0.254$\to$0.797) relative to the initial configurations. Critically, the most impactful discoveries are not hyperparameter adjustments: bug fixes (+175%), architectural changes (+44%), and prompt engineering (+188\% on specific categories) each individually exceed the cumulative contribution of all hyperparameter tuning, demonstrating capabilities fundamentally beyond the reach of traditional AutoML. We provide a taxonomy of six discovery types and identify four properties that make multimodal memory particularly suited for autoresearch, offering guidance for applying autonomous research pipelines to other AI system domains. Code is available at this https://github.com/aiming-lab/OmniMem.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts
arXiv:2604.00901v1 Announce Type: new
Abstract: Multi-agent Retrieval-Augmented Generation (RAG), wherein each agent takes on a specific role, supports hard queries that require multiple steps and sources, or complex reasoning. Existing approaches, however, rely on static agent behaviors and fixed orchestration strategies, leading to brittle performance on diverse, multi-hop tasks. We identify two key limitations: the lack of continuously adaptive orchestration mechanisms and the absence of behavior-level learning for individual agents. To this end, we propose HERA, a hierarchical framework that jointly evolves multi-agent orchestration and role-specific agent prompts. At the global level, HERA optimizes query-specific agent topologies through reward-guided sampling and experience accumulation. At the local level, Role-Aware Prompt Evolution refines agent behaviors via credit assignment and dual-axes adaptation along operational and behavioral principles, enabling targeted, role-conditioned improvements. On six knowledge-intensive benchmarks, HERA achieves an average improvement of 38.69\% over recent baselines while maintaining robust generalization and token efficiency. Topological analyses reveal emergent self-organization, where sparse exploration yields compact, high-utility multi-agent networks, demonstrating both efficient coordination and robust reasoning.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Disentanglement of Sources in a Multi-Stream Variational Autoencoder
arXiv:2510.15669v2 Announce Type: replace
Abstract: Variational autoencoders (VAEs) are among leading approaches to address the problem of learning disentangled representations. Typically a single VAE is used and disentangled representations are sought within its single continuous latent space. In this paper, we propose and provide a proof of concept for a novel Multi-Stream Variational Autoencoder (MS-VAE) that achieves disentanglement of sources by combining discrete and continuous latents. The discrete latents are used in an explicit source combination model, that superimposes a set of sources as part of the MS-VAE decoder. We formally define the MS-VAE approach, derive its inference and learning equations, and numerically investigate its principled functionality. The MS-VAE model is very flexible and can be trained using little supervision (we use fully unsupervised learning after pretraining with some labels). In our numerical experiments, we explored the ability of the MS-VAE approach in separating both superimposed hand-written digits as well as sound sources. For the former task we used superimposed MNIST digits (an increasingly common benchmark). For sound separation, our experiments focused on the task of speaker diarization in a recording conversation between two speakers. In all cases, we observe a clear separation of sources and competitive performance after training. For digit superpositions, performance is particularly competitive in complex mixtures (e.g., three and four digits). For the speaker diarization task, we observe an especially low rate of missed speakers and a more precise speaker attribution. Numerical experiments confirm the flexibility of the approach across varying amounts of supervision, and we observed high performance, e.g., when using just 10% of the labels for pretraining.
Fonte: arXiv stat.ML
MLOps/Systems • Score 85
Self-Routing: Parameter-Free Expert Routing from Hidden States
arXiv:2604.00421v1 Announce Type: new
Abstract: Mixture-of-Experts (MoE) layers increase model capacity by activating only a small subset of experts per token, and typically rely on a learned router to map hidden states to expert assignments. In this work, we ask whether a dedicated learned router is strictly necessary in the MoE settings we study. We propose Self-Routing, a parameter-free routing mechanism that uses a designated subspace of the token hidden state directly as expert logits, eliminating the router projection entirely while leaving the rest of the MoE layer unchanged. We evaluate Self-Routing on GPT-2-scale language modeling and ImageNet-1K classification by comparing it against a standard learned router, random-routing baselines, and dense non-MoE baselines. Our results show that Self-Routing remains competitive with the learned-router baseline while removing all dedicated routing parameters, and yields more balanced expert utilization, with about 17 % higher average normalized routing entropy and no explicit load-balancing loss. On ImageNet-1K with DeiT-S/16, Self-Routing also slightly improves over the corresponding learned-router MoE. These findings suggest that effective MoE routing can emerge from the hidden representation itself without requiring a separate learned router module.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
Speeding Up Mixed-Integer Programming Solvers with Sparse Learning for Branching
arXiv:2604.00094v1 Announce Type: new
Abstract: Machine learning is increasingly used to improve decisions within branch-and-bound algorithms for mixed-integer programming. Many existing approaches rely on deep learning, which often requires very large training datasets and substantial computational resources for both training and deployment, typically with GPU parallelization. In this work, we take a different path by developing interpretable models that are simple but effective. We focus on approximating strong branching (SB) scores, a highly effective yet computationally expensive branching rule. Using sparse learning methods, we build models with fewer than 4% of the parameters of a state-of-the-art graph neural network (GNN) while achieving competitive accuracy. Relative to SCIP's built-in branching rules and the GNN-based model, our CPU-only models are faster than the default solver and the GPU-accelerated GNN. The models are simple to train and deploy, and they remain effective with small training sets, which makes them practical in low-resource settings. Extensive experiments across diverse problem classes demonstrate the efficiency of this approach.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Eyla: Toward an Identity-Anchored LLM Architecture with Integrated Biological Priors -- Vision, Implementation Attempt, and Lessons from AI-Assisted Development
arXiv:2604.00009v1 Announce Type: cross
Abstract: We present the design rationale, implementation attempt, and failure analysis of Eyla, a proposed identity-anchored LLM architecture that integrates biologically-inspired subsystems -- including HiPPO-initialized state-space models, zero-initialized adapters, episodic memory retrieval, and calibrated uncertainty training -- into a unified agent operating system running on consumer hardware. Unlike existing approaches that optimize models for generic helpfulness, Eyla targets identity consistency: the ability to maintain a coherent self-model under adversarial pressure, admit uncertainty, and resist manipulation. We propose the Identity Consistency Score (ICS), a novel benchmark for evaluating this property across LLMs. We then present an honest account of attempting to implement this architecture using AI coding assistants (Claude Code, Cursor) as a non-programmer, documenting a $1,000+ failure that produced a 1.27B parameter model with 86 brain subsystems contributing less than 2% to output. Our analysis identifies five systematic failure modes of AI-assisted development for novel architectures and offers concrete recommendations. To our knowledge, this is the first paper to combine an architectural vision with a documented first-person failure analysis of AI-assisted LLM development, providing lessons for both the AI systems and AI-assisted software engineering communities.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
MCMC-Correction of Score-Based Diffusion Models for Model Composition
arXiv:2307.14012v4 Announce Type: replace
Abstract: Diffusion models can be parameterized in terms of either score or energy function. The energy parameterization is attractive as it enables sampling procedures such as Markov Chain Monte Carlo (MCMC) that incorporates a Metropolis--Hastings (MH) correction step based on energy differences between proposed samples. Such corrections can significantly improve sampling quality, particularly in the context of model composition, where pre-trained models are combined to generate samples from novel distributions. Score-based diffusion models, on the other hand, are more widely adopted and come with a rich ecosystem of pre-trained models. However, they do not, in general, define an underlying energy function, making MH-based sampling inapplicable. In this work, we address this limitation by retaining score parameterization and introducing a novel MH-like acceptance rule based on line integration of the score function. This allows the reuse of existing diffusion models while still combining the reverse process with various MCMC techniques, viewed as an instance of annealed MCMC. Through experiments on synthetic and real-world data, we show that our MH-like samplers {yield relative improvements of similar magnitude to those observed} with energy-based models, without requiring explicit energy parameterization.
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
Isomorphic Functionalities between Ant Colony and Ensemble Learning: Part II-On the Strength of Weak Learnability and the Boosting Paradigm
arXiv:2604.00038v1 Announce Type: new
Abstract: In Part I of this series, we established a rigorous mathematical isomorphism between ant colony decision-making and random forest learning, demonstrating that variance reduction through decorrelation is a universal principle shared by biological and computational ensembles. Here we turn to the complementary mechanism: bias reduction through adaptive weighting. Just as boosting algorithms sequentially focus on difficult instances, ant colonies dynamically amplify successful foraging paths through pheromone-mediated recruitment. We prove that these processes are mathematically isomorphic, establishing that the fundamental theorem of weak learnability has a direct analog in colony decision-making. We develop a formal mapping between AdaBoost's adaptive reweighting and ant recruitment dynamics, show that the margin theory of boosting corresponds to the stability of quorum decisions, and demonstrate through comprehensive simulation that ant colonies implementing adaptive recruitment achieve the same bias-reduction benefits as boosting algorithms. This completes a unified theory of ensemble intelligence, revealing that both variance reduction (Part I) and bias reduction (Part II) are manifestations of the same underlying mathematical principles governing collective intelligence in biological and computational systems.
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
Natural Hypergradient Descent: Algorithm Design, Convergence Analysis, and Parallel Implementation
arXiv:2602.10905v2 Announce Type: replace-cross
Abstract: In this work, we propose Natural Hypergradient Descent (NHGD), a new method for solving bilevel optimization problems. To address the computational bottleneck in hypergradient estimation--namely, the need to compute or approximate Hessian inverse--we exploit the statistical structure of the inner optimization problem and use the empirical Fisher information matrix as an asymptotically consistent surrogate for the Hessian. This design enables a parallel optimize-and-approximate framework in which the Hessian-inverse approximation is updated synchronously with the stochastic inner optimization, reusing gradient information at negligible additional cost. Our main theoretical contribution establishes high-probability error bounds and sample complexity guarantees for NHGD that match those of state-of-the-art optimize-then-approximate methods, while significantly reducing computational time overhead. Empirical evaluations on representative bilevel learning tasks further demonstrate the practical advantages of NHGD, highlighting its scalability and effectiveness in large-scale machine learning settings.
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
Learning Hyperparameters via a Data-Emphasized Variational Objective
arXiv:2502.01861v3 Announce Type: replace-cross
Abstract: When training large models on limited data, avoiding overfitting is paramount. Common grid search or smarter search methods rely on expensive separate runs for each candidate hyperparameter, while carving out a validation set that reduces available training data. In this paper, we study gradient-based learning of hyperparameters via the evidence lower bound (ELBO) objective from Bayesian variational methods. This avoids the need for any validation set. We focus on scenarios where the model is over-parameterized for flexibility and the approximate posterior is chosen to be Gaussian with isotropic covariance for tractability, even though it cannot match the true posterior. In such scenarios, we find the ELBO prioritizes posteriors that match the prior, leading to severe underfitting. Instead, we recommend a data-emphasized ELBO that upweights the likelihood but not the prior. In Bayesian transfer learning of image and text classifiers, our method reduces the 88+ hour grid search of past work to under 3 hours while delivering comparable accuracy. We further demonstrate how our approach enables efficient yet accurate approximations of Gaussian processes with learnable lengthscale kernels.
Fonte: arXiv stat.ML
MLOps/Systems • Score 85
MF-QAT: Multi-Format Quantization-Aware Training for Elastic Inference
arXiv:2604.00529v1 Announce Type: new
Abstract: Quantization-aware training (QAT) is typically performed for a single target numeric format, while practical deployments often need to choose numerical precision at inference time based on hardware support or runtime constraints. We study multi-format QAT, where a single model is trained to be robust across multiple quantization formats. We find that multi-format QAT can match single-format QAT at each target precision, yielding one model that performs well overall across different formats, even formats that were not seen during training. To enable practical deployment, we propose the Slice-and-Scale conversion procedure for both MXINT and MXFP that converts a high-precision representation into lower-precision formats without re-training. Building on this, we introduce a pipeline that (i) trains a model with multi-format QAT, (ii) stores a single anchor format checkpoint (MXINT8/MXFP8), and (iii) allows on-the-fly conversion to lower MXINT or MXFP formats at runtime with negligible-or no-additional accuracy degradation. Together, these components provide a practical path to elastic precision scaling and allow selecting the runtime format at inference time across diverse deployment targets.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Scheduling LLM Inference with Uncertainty-Aware Output Length Predictions
arXiv:2604.00499v1 Announce Type: new
Abstract: To schedule LLM inference, the \textit{shortest job first} (SJF) principle is favorable by prioritizing requests with short output lengths to avoid head-of-line (HOL) blocking. Existing methods usually predict a single output length for each request to facilitate scheduling. We argue that such a \textit{point estimate} does not match the \textit{stochastic} decoding process of LLM inference, where output length is \textit{uncertain} by nature and determined by when the end-of-sequence (EOS) token is sampled. Hence, the output length of each request should be fitted with a distribution rather than a single value. With an in-depth analysis of empirical data and the stochastic decoding process, we observe that output length follows a heavy-tailed distribution and can be fitted with the log-t distribution. On this basis, we propose a simple metric called Tail Inflated Expectation (TIE) to replace the output length in SJF scheduling, which adjusts the expectation of a log-t distribution with its tail probabilities to account for the risk that a request generates long outputs. To evaluate our TIE scheduler, we compare it with three strong baselines, and the results show that TIE reduces the per-token latency by $2.31\times$ for online inference and improves throughput by $1.42\times$ for offline data generation.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Optimsyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation
arXiv:2604.00536v1 Announce Type: new
Abstract: Large language models (LLMs) achieve strong downstream performance largely due to abundant supervised fine-tuning (SFT) data. However, high-quality SFT data in knowledge-intensive domains such as humanities, social sciences, medicine, law, and finance is scarce because expert curation is expensive, privacy constraints are strict, and label consistency is hard to ensure. Recent work uses synthetic data, typically by prompting a generator over domain documents and filtering outputs with handcrafted rubrics. Yet rubric design is expert-dependent, transfers poorly across domains, and is often optimized through a brittle heuristic loop of writing rubrics, synthesizing data, training, inspecting results, and manually guessing revisions. This process lacks reliable quantitative feedback about how a rubric affects downstream performance. We propose evaluating synthetic data by its training utility on the target model and using this signal to guide data generation. Inspired by influence estimation, we adopt an optimizer-aware estimator that uses gradient information to quantify each synthetic sample's contribution to a target model's objective on specific tasks. Our analysis shows that even when synthetic and real samples are close in embedding space, their influence on learning can differ substantially. Based on this insight, we propose an optimization-based framework that adapts rubrics using target-model feedback. We provide lightweight guiding text and use a rubric-specialized model to generate task-conditioned rubrics. Influence score is used as the reward to optimize the rubric generator with reinforcement learning. Experiments across domains, target models, and data generators show consistent improvements and strong generalization without task-specific tuning.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
Oblivion: Self-Adaptive Agentic Memory Control through Decay-Driven Activation
arXiv:2604.00131v1 Announce Type: new
Abstract: Human memory adapts through selective forgetting: experiences become less accessible over time but can be reactivated by reinforcement or contextual cues. In contrast, memory-augmented LLM agents rely on "always-on" retrieval and "flat" memory storage, causing high interference and latency as histories grow. We introduce Oblivion, a memory control framework that casts forgetting as decay-driven reductions in accessibility, not explicit deletion. Oblivion decouples memory control into read and write paths. The read path decides when to consult memory, based on agent uncertainty and memory buffer sufficiency, avoiding redundant always-on access. The write path decides what to strengthen, by reinforcing memories contributing to forming the response. Together, this enables hierarchical memory organization that maintains persistent high-level strategies while dynamically loading details as needed. We evaluate on both static and dynamic long-horizon interaction benchmarks. Results show that Oblivion dynamically adapts memory access and reinforcement, balancing learning and forgetting under shifting contexts, highlighting that memory control is essential for effective LLM-agentic reasoning. The source code is available at https://github.com/nec-research/oblivion.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
Adaptive Parallel Monte Carlo Tree Search for Efficient Test-time Compute Scaling
arXiv:2604.00510v1 Announce Type: new
Abstract: Monte Carlo Tree Search (MCTS) is an effective test-time compute scaling (TTCS) method for improving the reasoning performance of large language models, but its highly variable execution time leads to severe long-tail latency in practice. Existing optimizations such as positive early exit, reduce latency in favorable cases but are less effective when search continues without meaningful progress. We introduce {\it negative early exit}, which prunes unproductive MCTS trajectories, and an {\it adaptive boosting mechanism} that reallocates reclaimed computation to reduce resource contention among concurrent searches. Integrated into vLLM, these techniques substantially reduce p99 end-to-end latency while improving throughput and maintaining reasoning accuracy.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
Deep Learning-Accelerated Surrogate Optimization for High-Dimensional Well Control in Stress-Sensitive Reservoirs
arXiv:2604.00352v1 Announce Type: new
Abstract: Production optimization in stress-sensitive unconventional reservoirs is governed by a nonlinear trade-off between pressure-driven flow and stress-induced degradation of fracture conductivity and matrix permeability. While higher drawdown improves short-term production, it accelerates permeability loss and reduces long-term recovery. Identifying optimal, time-varying control strategies requires repeated evaluations of fully coupled flow-geomechanics simulators, making conventional optimization computationally expensive.
We propose a deep learning-based surrogate optimization framework for high-dimensional well control. Unlike prior approaches that rely on predefined control parameterizations or generic sampling, our method treats well control as a continuous, high-dimensional problem and introduces a problem-informed sampling strategy that aligns training data with trajectories encountered during optimization. A neural network proxy is trained to approximate the mapping between bottomhole pressure trajectories and cumulative production using data from a coupled flow-geomechanics model.
The proxy is embedded within a constrained optimization workflow, enabling rapid evaluation of control strategies. Across multiple initializations, the surrogate achieves agreement with full-physics solutions within 2-5 percent, while reducing computational cost by up to three orders of magnitude. Discrepancies are mainly associated with trajectories near the boundary of the training distribution and local optimization effects.
This framework shows that combining surrogate modeling with problem-informed sampling enables scalable and reliable optimization for high-dimensional, simulator-based problems, with broader applicability to PDE-constrained systems.
Fonte: arXiv cs.LG
Multimodal • Score 85
MOON3.0: Reasoning-aware Multimodal Representation Learning for E-commerce Product Understanding
arXiv:2604.00513v1 Announce Type: new
Abstract: With the rapid growth of e-commerce, exploring general representations rather than task-specific ones has attracted increasing attention. Although recent multimodal large language models (MLLMs) have driven significant progress in product understanding, they are typically employed as feature extractors that implicitly encode product information into global embeddings, thereby limiting their ability to capture fine-grained attributes. Therefore, we argue that leveraging the reasoning capabilities of MLLMs to explicitly model fine-grained product attributes holds significant potential. Nevertheless, achieving this goal remains non-trivial due to several key challenges: (i) long-context reasoning tends to dilute the model's attention to salient information in the raw input; (ii) supervised fine-tuning (SFT) primarily encourages rigid imitation, limiting the exploration of effective reasoning strategies; and (iii) fine-grained details are progressively attenuated during forward propagation. To address these issues, we propose MOON3.0, the first reasoning-aware MLLM-based model for product representation learning. Our method (1) employs a multi-head modality fusion module to adaptively integrate raw signals; (2) incorporates a joint contrastive and reinforcement learning framework to autonomously explore more effective reasoning strategies; and (3) introduces a fine-grained residual enhancement module to progressively preserve local details throughout the network. Additionally, we release a large-scale multimodal e-commerce benchmark MBE3.0. Experimentally, our model demonstrates state-of-the-art zero-shot performance across various downstream tasks on both our benchmark and public datasets.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
SYNTHONY: A Stress-Aware, Intent-Conditioned Agent for Deep Tabular Generative Models Selection
arXiv:2604.00293v1 Announce Type: new
Abstract: Deep generative models for tabular data (GANs, diffusion models, and LLM-based generators) exhibit highly non-uniform behavior across datasets; the best-performing synthesizer family depends strongly on distributional stressors such as long-tailed marginals, high-cardinality categorical, Zipfian imbalance, and small-sample regimes. This brittleness makes practical deployment challenging, especially when users must balance competing objectives of fidelity, privacy, and utility. We study {intent-conditioned tabular synthesis selection}: given a dataset and a user intent expressed as a preference over evaluation metrics, the goal is to select a synthesizer that minimizes regret relative to an intent-specific oracle. We propose {stress profiling}, a synthesis-specific meta-feature representation that quantifies dataset difficulty along four interpretable stress dimensions, and integrate it into {SYNTHONY}, a selection framework that matches stress profiles against a calibrated capability registry of synthesizer families. Across a benchmark of 7 datasets, 10 synthesizers, and 3 intents, we demonstrate that stress-based meta-features are highly predictive of synthesizer performance: a $k$NN selector using these features achieves strong Top-1 selection accuracy, substantially outperforming zero-shot LLM selectors and random baselines. We analyze the gap between meta-feature-based and capability-based selection, identifying the hand-crafted capability registry as the primary bottleneck and motivating learned capability representations as a direction for future work.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
ParetoBandit: Budget-Paced Adaptive Routing for Non-Stationary LLM Serving
arXiv:2604.00136v1 Announce Type: new
Abstract: Production LLM serving often relies on multi-model portfolios spanning a ~530x cost range, where routing decisions trade off quality against cost. This trade-off is non-stationary: providers revise pricing, model quality can regress silently, and new models must be integrated without downtime. We present ParetoBandit, an open-source adaptive router built on cost-aware contextual bandits that is the first to simultaneously enforce dollar-denominated budgets, adapt online to such shifts, and onboard new models at runtime.
ParetoBandit closes these gaps through three mechanisms. An online primal-dual budget pacer enforces a per-request cost ceiling over an open-ended stream, replacing offline penalty tuning with closed-loop control. Geometric forgetting on sufficient statistics enables rapid adaptation to price and quality shifts while bootstrapping from offline priors. A hot-swap registry lets operators add or remove models at runtime, with a brief forced-exploration phase for each newcomer, after which UCB selection discovers its quality-cost niche from live traffic alone.
We evaluate ParetoBandit across four deployment scenarios on 1,824 prompts routed through a three-model portfolio. Across seven budget ceilings, mean per-request cost never exceeds the target by more than 0.4%. When conditions shift, the system adapts: an order-of-magnitude price cut on the costliest model yields up to +0.071 quality lift, and a silent quality regression is detected and rerouted within budget. A cold-started model reaches meaningful adoption within ~142 steps without breaching the cost ceiling. The router discriminates rather than blindly adopting: expensive models are budget-gated and low-quality models rejected after bounded exploration. End-to-end routing latency is 9.8ms on CPU -- less than 0.4% of typical inference time -- with the routing decision itself taking just 22.5us.
Fonte: arXiv cs.LG
RL • Score 85
Execution-Verified Reinforcement Learning for Optimization Modeling
arXiv:2604.00442v1 Announce Type: new
Abstract: Automating optimization modeling with LLMs is a promising path toward scalable decision intelligence, but existing approaches either rely on agentic pipelines built on closed-source LLMs with high inference latency, or fine-tune smaller LLMs using costly process supervision that often overfits to a single solver API. Inspired by reinforcement learning with verifiable rewards, we propose Execution-Verified Optimization Modeling (EVOM), an execution-verified learning framework that treats a mathematical programming solver as a deterministic, interactive verifier. Given a natural-language problem and a target solver, EVOM generates solver-specific code, executes it in a sandboxed harness, and converts execution outcomes into scalar rewards, optimized with GRPO and DAPO in a closed-loop generate-execute-feedback-update process. This outcome-only formulation removes the need for process-level supervision, and enables cross-solver generalization by switching the verification environment rather than reconstructing solver-specific datasets. Experiments on NL4OPT, MAMO, IndustryOR, and OptiBench across Gurobi, OR-Tools, and COPT show that EVOM matches or outperforms process-supervised SFT, supports zero-shot solver transfer, and achieves effective low-cost solver adaptation by continuing training under the target solver backend.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
Neural Collapse Dynamics: Depth, Activation, Regularisation, and Feature Norm Threshold
arXiv:2604.00230v1 Announce Type: new
Abstract: Neural collapse (NC) -- the convergence of penultimate-layer features to a simplex equiangular tight frame -- is well understood at equilibrium, but the dynamics governing its onset remain poorly characterised. We identify a simple and predictive regularity: NC occurs when the mean feature norm reaches a model-dataset-specific critical value, fn*, that is largely invariant to training conditions. This value concentrates tightly within each (model, dataset) pair (CV 0.2). Completing the (architecture)x(dataset) grid reveals the paper's strongest result: ResNet-20 on MNIST gives fn* = 5.867 -- a +458% architecture effect versus only +68% on CIFAR-10. The grid is strongly non-additive; fn* cannot be decomposed into independent architecture and dataset contributions. Four structural regularities emerge: (1) depth has a non-monotonic effect on collapse speed; (2) activation jointly determines both collapse speed and fn*; (3) weight decay defines a three-regime phase diagram -- too little slows, an optimal range is fastest, and too much prevents collapse; (4) width monotonically accelerates collapse while shifting fn* by at most 13%. These results establish feature-norm dynamics as an actionable diagnostic for predicting NC timing, suggesting that norm-threshold behaviour is a general mechanism underlying delayed representational reorganisation in deep networks.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Task-Centric Personalized Federated Fine-Tuning of Language Models
arXiv:2604.00050v1 Announce Type: new
Abstract: Federated Learning (FL) has emerged as a promising technique for training language models on distributed and private datasets of diverse tasks. However, aggregating models trained on heterogeneous tasks often degrades the overall performance of individual clients. To address this issue, Personalized FL (pFL) aims to create models tailored for each client's data distribution. Although these approaches improve local performance, they usually lack robustness in two aspects: (i) generalization: when clients must make predictions on unseen tasks, or face changes in their data distributions, and (ii) intra-client tasks interference: when a single client's data contains multiple distributions that may interfere with each other during local training. To tackle these two challenges, we propose FedRouter, a clustering-based pFL that builds specialized models for each task rather than for each client. FedRouter uses adapters to personalize models by employing two clustering mechanisms to associate adapters with specific tasks. A local clustering that associate adapters with task data samples and a global one that associates similar adapters from different clients to construct task-centric personalized models. Additionally, we propose an evaluation router mechanism that routes test samples to the best adapter based on the created clusters. Experiments comparing our method with existing approaches across a multitask dataset, FedRouter demonstrate strong resilience in these challenging scenarios performing up to 6.1% relatively better under tasks interference and up to 136% relative improvement under generalization evaluation.
Fonte: arXiv cs.LG
NLP/LLMs • Score 95
MAC-Attention: a Match-Amend-Complete Scheme for Fast and Accurate Attention Computation
arXiv:2604.00235v1 Announce Type: new
Abstract: Long-context decoding in LLMs is IO-bound: each token re-reads an ever-growing KV cache. Prior accelerations cut bytes via compression, which lowers fidelity, or selection/eviction, which restricts what remains accessible, and both can degrade delayed recall and long-form generation. We introduce MAC-Attention, a fidelity- and access-preserving alternative that accelerates decoding by reusing prior attention computations for semantically similar recent queries. It starts with a match stage that performs pre-RoPE L2 matching over a short local window; an amend stage rectifies the reused attention by recomputing a small band near the match boundary; and a complete stage fuses the rectified results with fresh attention computed on the KV tail through a numerically stable merge. On a match hit, the compute and bandwidth complexity is constant regardless of context length. The method is model-agnostic and composes with IO-aware kernels, paged-KV managers, and MQA/GQA. Across LongBench v2 (120K), RULER (120K), and LongGenBench (16K continuous generation), compared to the latest FlashInfer library, MAC-Attention reduces KV accesses by up to 99%, cuts token generation latency by over 60% at 128K, and achieves over 14.3x attention-phase speedups, up to 2.6x end-to-end, while maintaining full-attention quality. By reusing computation, MAC-Attention delivers long-context inference that is both fast and faithful. Code is available here: https://github.com/YJHMITWEB/MAC-Attention.git
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Convergence of Byzantine-Resilient Gradient Tracking via Probabilistic Edge Dropout
arXiv:2604.00449v1 Announce Type: new
Abstract: We study distributed optimization over networks with Byzantine agents that may send arbitrary adversarial messages. We propose \emph{Gradient Tracking with Probabilistic Edge Dropout} (GT-PD), a stochastic gradient tracking method that preserves the convergence properties of gradient tracking under adversarial communication. GT-PD combines two complementary defense layers: a universal self-centered projection that clips each incoming message to a ball of radius $\tau$ around the receiving agent, and a fully decentralized probabilistic dropout rule driven by a dual-metric trust score in the decision and tracking channels. This design bounds adversarial perturbations while preserving the doubly stochastic mixing structure, a property often lost under robust aggregation in decentralized settings. Under complete Byzantine isolation ($p_b=0$), GT-PD converges linearly to a neighborhood determined solely by stochastic gradient variance. For partial isolation ($p_b>0$), we introduce \emph{Gradient Tracking with Probabilistic Edge Dropout and Leaky Integration} (GT-PD-L), which uses a leaky integrator to control the accumulation of tracking errors caused by persistent perturbations and achieves linear convergence to a bounded neighborhood determined by the stochastic variance and the clipping-to-leak ratio. We further show that under two-tier dropout with $p_h=1$, isolating Byzantine agents introduces no additional variance into the honest consensus dynamics. Experiments on MNIST under Sign Flip, ALIE, and Inner Product Manipulation attacks show that GT-PD-L outperforms coordinate-wise trimmed mean by up to 4.3 percentage points under stealth attacks.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
C-TRAIL: A Commonsense World Framework for Trajectory Planning in Autonomous Driving
arXiv:2603.29908v1 Announce Type: new
Abstract: Trajectory planning for autonomous driving increasingly leverages large language models (LLMs) for commonsense reasoning, yet LLM outputs are inherently unreliable, posing risks in safety-critical applications. We propose C-TRAIL, a framework built on a Commonsense World that couples LLM-derived commonsense with a trust mechanism to guide trajectory planning. C-TRAIL operates through a closed-loop Recall, Plan, and Update cycle: the Recall module queries an LLM for semantic relations and quantifies their reliability via a dual-trust mechanism; the Plan module injects trust-weighted commonsense into Monte Carlo Tree Search (MCTS) through a Dirichlet trust policy; and the Update module adaptively refines trust scores and policy parameters from environmental feedback. Experiments on four simulated scenarios in Highway-env and two real-world levelXData datasets (highD, rounD) show that C-TRAIL consistently outperforms state-of-the-art baselines, reducing ADE by 40.2%, FDE by 51.7%, and improving SR by 16.9 percentage points on average. The source code is available at https://github.com/ZhihongCui/CTRAIL.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
A Latent Risk-Aware Machine Learning Approach for Predicting Operational Success in Clinical Trials based on TrialsBank
arXiv:2603.29041v1 Announce Type: new
Abstract: Clinical trials are characterized by high costs, extended timelines, and substantial operational risk, yet reliable prospective methods for predicting trial success before initiation remain limited. Existing artificial intelligence approaches often focus on isolated metrics or specific development stages and frequently rely on variables unavailable at the trial design phase, limiting real-world applicability. We present a hierarchical latent risk-aware machine learning framework for prospective prediction of clinical trial operational success using a curated subset of TrialsBank, a proprietary AI-ready database developed by Sorintellis, comprising 13,700 trials. Operational success was defined as the ability to initiate, conduct, and complete a clinical trial according to planned timelines, recruitment targets, and protocol specifications through database lock. This approach decomposes operational success prediction into two modeling stages. First, intermediate latent operational risk factors are predicted using more than 180 drug- and trial-level features available before trial initiation. These predicted latent risks are then integrated into a downstream model to estimate the probability of operational success. A staged data-splitting strategy was employed to prevent information leakage, and models were benchmarked using XGBoost, CatBoost, and Explainable Boosting Machines. Across Phase I-III, the framework achieves strong out-of-sample performance, with F1-scores of 0.93, 0.92, and 0.91, respectively. Incorporating latent risk drivers improves discrimination of operational failures, and performance remains robust under independent inference evaluation. These results demonstrate that clinical trial operational success can be prospectively forecasted using a latent risk-aware AI framework, enabling early risk assessment and supporting data-driven clinical development decision-making.
Fonte: arXiv cs.LG
RecSys • Score 85
Monodense Deep Neural Model for Determining Item Price Elasticity
arXiv:2603.29261v1 Announce Type: new
Abstract: Item Price Elasticity is used to quantify the responsiveness of consumer demand to changes in item prices, enabling businesses to create pricing strategies and optimize revenue management. Sectors such as store retail, e-commerce, and consumer goods rely on elasticity information derived from historical sales and pricing data. This elasticity provides an understanding of purchasing behavior across different items, consumer discount sensitivity, and demand elastic departments. This information is particularly valuable for competitive markets and resource-constrained businesses decision making which aims to maximize profitability and market share. Price elasticity also uncovers historical shifts in consumer responsiveness over time. In this paper, we model item-level price elasticity using large-scale transactional datasets, by proposing a novel elasticity estimation framework which has the capability to work in an absence of treatment control setting. We test this framework by using Machine learning based algorithms listed below, including our newly proposed Monodense deep neural network.
(1) Monodense-DL network -- Hybrid neural network architecture combining embedding, dense, and Monodense layers (2) DML -- Double machine learning setting using regression models (3) LGBM -- Light Gradient Boosting Model
We evaluate our model on multi-category retail data spanning millions of transactions using a back testing framework. Experimental results demonstrate the superiority of our proposed neural network model within the framework compared to other prevalent ML based methods listed above.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Deep Learning-Based Anomaly Detection in Spacecraft Telemetry on Edge Devices
arXiv:2603.29375v1 Announce Type: new
Abstract: Spacecraft anomaly detection is critical for mission safety, yet deploying sophisticated models on-board presents significant challenges due to hardware constraints. This paper investigates three approaches for spacecraft telemetry anomaly detection -- forecasting & threshold, direct classification, and image classification -- and optimizes them for edge deployment using multi-objective neural architecture optimization on the European Space Agency Anomaly Dataset. Our baseline experiments demonstrate that forecasting & threshold achieves superior detection performance (92.7% Corrected Event-wise F0.5-score (CEF0.5)) [1] compared to alternatives. Through Pareto-optimal architecture optimization, we dramatically reduced computational requirements while maintaining capabilities -- the optimized forecasting & threshold model preserved 88.8% CEF0.5 while reducing RAM usage by 97.1% to just 59 KB and operations by 99.4%. Analysis of deployment viability shows our optimized models require just 0.36-6.25% of CubeSat RAM, making on-board anomaly detection practical even on highly constrained hardware. This research demonstrates that sophisticated anomaly detection capabilities can be successfully deployed within spacecraft edge computing constraints, providing near-instantaneous detection without exceeding hardware limitations or compromising mission safety.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
On computing and the complexity of computing higher-order $U$-statistics, exactly
arXiv:2508.12627v2 Announce Type: replace
Abstract: Higher-order $U$-statistics abound in fields such as statistics, machine learning, and computer science, but are known to be highly time-consuming to compute in practice. Despite their widespread appearance, a comprehensive study of their computational complexity is surprisingly lacking. This paper aims to fill this gap by presenting several results related to the computational aspect of $U$-statistics. First, we derive a useful decomposition from a $m$-th order $U$-statistic to a linear combination of $V$-statistics with orders not exceeding $m$, which are generally more feasible to compute. Second, we explore the connection between exactly computing $V$-statistics and Einstein summation, a tool often used in computational mathematics and quantum computing to accelerate tensor computations. Third, we provide an optimistic estimate of the time complexity for exactly computing $U$-statistics, based on the treewidth of a particular graph associated with the $U$-statistic kernel. The above ingredients lead to (1) a new, much more runtime-efficient algorithm to exactly compute general higher-order $U$-statistics, and (2) a more streamlined characterization of runtime complexity of computing $U$-statistics. We develop an accompanying open-source package called \texttt{u-stats} in both Python (https://github.com/zrq1706/U-Statistics-Python) and R (https://github.com/cxy0714/U-Statistics-R). We demonstrate through three examples in statistics that \texttt{u-stats} achieves impressive runtime performance compared to existing benchmarks. This paper also aspires to achieve two goals: (1) to capture the interest of researchers in both statistics and other related areas to further advance the algorithmic development of $U$-statistics and (2) to lift the burden of implementing higher-order $U$-statistics from practitioners.
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
Foundations of Polar Linear Algebra
arXiv:2603.28939v1 Announce Type: new
Abstract: This work revisits operator learning from a spectral perspective by introducing Polar Linear Algebra, a structured framework based on polar geometry that combines a linear radial component with a periodic angular component. Starting from this formulation, we define the associated operators and analyze their spectral properties. As a proof of feasibility, the framework is evaluated on a canonical benchmark (MNIST). Despite the simplicity of the task, the results demonstrate that polar and fully spectral operators can be trained reliably, and that imposing self-adjoint-inspired spectral constraints improves stability and convergence. Beyond accuracy, the proposed formulation leads to a reduction in parameter count and computational complexity, while providing a more interpretable representation in terms of decoupled spectral modes. By moving from a spatial to a spectral domain, the problem decomposes into orthogonal eigenmodes that can be treated as independent computational pipelines. This structure naturally exposes an additional dimension of model parallelization, complementing existing parallel strategies without relying on ad-hoc partitioning. Overall, the work offers a different conceptual lens for operator learning, particularly suited to problems where spectral structure and parallel execution are central.
Fonte: arXiv cs.LG
RL • Score 85
ShapE-GRPO: Shapley-Enhanced Reward Allocation for Multi-Candidate LLM Training
arXiv:2603.29871v1 Announce Type: new
Abstract: In user-agent interaction scenarios such as recommendation, brainstorming, and code suggestion, Large Language Models (LLMs) often generate sets of candidate recommendations where the objective is to maximize the collective utility of the entire set rather than individual candidates independently. However, existing reinforcement learning post-training paradigms, such as Group Relative Policy Optimization (GRPO), typically assign the same set-level scalar reward to every candidate in the set. This leads to noisy training signals where poor candidates free-ride on the high reward produced by a single strong peer, resulting in suboptimal exploration. To address this, we propose Shapley-Enhanced GRPO (ShapE-GRPO). By leveraging the permutation-invariant nature of set-level utility, we derive a Shapley-enhanced formulation from cooperative game theory to decompose set-level rewards into granular, candidate-specific signals. We show that our formulation preserves the fundamental axioms of the Shapley value while remaining computationally efficient with polynomial-time complexity. Empirically, ShapE-GRPO consistently outperforms standard GRPO across diverse datasets with accelerated convergence during training.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
SimMOF: AI agent for Automated MOF Simulations
arXiv:2603.29152v1 Announce Type: new
Abstract: Metal-organic frameworks (MOFs) offer a vast design space, and as such, computational simulations play a critical role in predicting their structural and physicochemical properties. However, MOF simulations remain difficult to access because reliable analysis require expert decisions for workflow construction, parameter selection, tool interoperability, and the preparation of computational ready structures. Here, we introduce SimMOF, a large language model based multi agent framework that automates end-to-end MOF simulation workflows from natural language queries. SimMOF translates user requests into dependency aware plans, generates runnable inputs, orchestrates multiple agents to execute simulations, and summarizes results with analysis aligned to the user query. Through representative case studies, we show that SimMOF enables adaptive and cognitively autonomous workflows that reflect the iterative and decision driven behavior of human researchers and as such provides a scalable foundation for data driven MOF research.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Developing Adaptive Context Compression Techniques for Large Language Models (LLMs) in Long-Running Interactions
arXiv:2603.29193v1 Announce Type: new
Abstract: Large Language Models (LLMs) often experience performance degradation during long-running interactions due to increasing context length, memory saturation, and computational overhead. This paper presents an adaptive context compression framework that integrates importance-aware memory selection, coherence-sensitive filtering, and dynamic budget allocation to retain essential conversational information while controlling context growth. The approach is evaluated on LOCOMO, LOCCO, and LongBench benchmarks to assess answer quality, retrieval accuracy, coherence preservation, and efficiency. Experimental results demonstrate that the proposed method achieves consistent improvements in conversational stability and retrieval performance while reducing token usage and inference latency compared with existing memory and compression-based approaches. These findings indicate that adaptive context compression provides an effective balance between long-term memory preservation and computational efficiency in persistent LLM interactions
Fonte: arXiv cs.CV
Theory/Optimization • Score 85
Expressive Power of Implicit Models: Rich Equilibria and Test-Time Scaling
arXiv:2510.03638v4 Announce Type: replace-cross
Abstract: Implicit models, an emerging model class, compute outputs by iterating a single parameter block to a fixed point. This architecture realizes an infinite-depth, weight-tied network that trains with constant memory, significantly reducing memory needs for the same level of performance compared to explicit models. While it is empirically known that these compact models can often match or even exceed the accuracy of larger explicit networks by allocating more test-time compute, the underlying mechanism remains poorly understood.
We study this gap through a nonparametric analysis of expressive power. We provide a strict mathematical characterization, showing that a simple and regular implicit operator can, through iteration, progressively express more complex mappings. We prove that for a broad class of implicit models, this process lets the model's expressive power scale with test-time compute, ultimately matching a much richer function class. The theory is validated across four domains: image reconstruction, scientific computing, operations research, and LLM reasoning, demonstrating that as test-time iterations increase, the complexity of the learned mapping rises, while the solution quality simultaneously improves and stabilizes.
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
Epistemic Errors of Imperfect Multitask Learners When Distributions Shift
arXiv:2505.23496v3 Announce Type: replace-cross
Abstract: Uncertainty-aware machine learners, such as Bayesian neural networks, output a quantification of uncertainty instead of a point prediction. We provide uncertainty-aware learners with a principled framework to characterize, and identify ways to eliminate, errors that arise from reducible (epistemic) uncertainty. We introduce a principled definition of epistemic error, and provide a decompositional epistemic error bound which operates in the very general setting of imperfect multitask learning under distribution shift. In this setting, the training (source) data may arise from multiple tasks, the test (target) data may differ systematically from the source data tasks, and/or the learner may not arrive at an accurate characterization of the source data. Our bound separately attributes epistemic errors to each of multiple aspects of the learning procedure and environment. As corollaries of the general result, we provide epistemic error bounds specialized to the settings of Bayesian transfer learning and distribution shift within $\epsilon$-neighborhoods.
Fonte: arXiv stat.ML
RL • Score 85
Enhancing Policy Learning with World-Action Model
arXiv:2603.28955v1 Announce Type: new
Abstract: This paper presents the World-Action Model (WAM), an action-regularized world model that jointly reasons over future visual observations and the actions that drive state transitions. Unlike conventional world models trained solely via image prediction, WAM incorporates an inverse dynamics objective into DreamerV2 that predicts actions from latent state transitions, encouraging the learned representations to capture action-relevant structure critical for downstream control. We evaluate WAM on enhancing policy learning across eight manipulation tasks from the CALVIN benchmark. We first pretrain a diffusion policy via behavioral cloning on world model latents, then refine it with model-based PPO inside the frozen world model. Without modifying the policy architecture or training procedure, WAM improves average behavioral cloning success from 59.4% to 71.2% over DreamerV2 and DiWA baselines. After PPO fine-tuning, WAM achieves 92.8% average success versus 79.8% for the baseline, with two tasks reaching 100%, using 8.7x fewer training steps.
Fonte: arXiv cs.AI
Evaluation/Benchmarks • Score 85
Spark-LLM-Eval: A Distributed Framework for Statistically Rigorous Large Language Model Evaluation
arXiv:2603.28769v1 Announce Type: cross
Abstract: Evaluating large language models at scale remains a practical bottleneck for many organizations. While existing evaluation frameworks work well for thousands of examples, they struggle when datasets grow to hundreds of thousands or millions of samples. This scale is common when assessing model behavior across diverse domains or conducting comprehensive regression testing. We present Spark-LLM-Eval, a distributed evaluation framework built natively on Apache Spark. The system treats evaluation as a data-parallel problem, partitioningexamplesacrossexecutorsandaggregatingresultswithproperstatistical accounting. Beyond raw throughput, we emphasize statistical rigor: every reported metric includes bootstrap confidence intervals, and model comparisons come with appropriate significance tests (paired t-tests, McNemar's test, or Wilcoxon signed-rank, depending on the metric type). The framework also addresses the cost problem inherent in LLM evaluation through content-addressable response caching backed by Delta Lake, which allows iterating on metric definitions without re-running inference. We describe the system architecture, the statistical methodology, and report benchmark results showing linear scaling with cluster size. The framework and all evaluation code are available as open source.
Fonte: arXiv cs.CL
Theory/Optimization • Score 85
Lie Generator Networks for Nonlinear Partial Differential Equations
arXiv:2603.29264v1 Announce Type: new
Abstract: Linear dynamical systems are fully characterized by their eigenspectra, accessible directly from the generator of the dynamics. For nonlinear systems governed by partial differential equations, no equivalent theory exists. We introduce Lie Generator Network--Koopman (LGN-KM), a neural operator that lifts nonlinear dynamics into a linear latent space and learns the continuous-time Koopman generator ($L_k$) through a decomposition $L_k = S - D_k$, where $S$ is skew-symmetric representing conservative inter-modal coupling, and $D_k$ is a positive-definite diagonal encoding modal dissipation. This architectural decomposition enforces stability and enables interpretability through direct spectral access to the learned dynamics. On two-dimensional Navier--Stokes turbulence, the generator recovers the known dissipation scaling and a complete multi-branch dispersion relation from trajectory data alone with no physics supervision. Independently trained models at different flow regimes recover matched gauge-invariant spectral structure, exposing a gauge freedom in the Koopman lifting. Because the generator is provably stable, it enables guaranteed long-horizon stability, continuous-time evaluation at arbitrary time, and physics-informed cross-viscosity model transfer.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Drift Estimation for Diffusion Processes Using Neural Networks Based on Discretely Observed Independent Paths
arXiv:2511.11161v2 Announce Type: replace
Abstract: This paper addresses the nonparametric estimation of the drift function over a compact domain for a time-homogeneous diffusion process, based on high-frequency discrete observations from $N$ independent trajectories. We propose a neural network-based estimator and derive a non-asymptotic convergence rate, decomposed into a training error, an approximation error, and a diffusion-related term scaling as ${\log N}/{N}$. For compositional drift functions, we establish an explicit rate. In the numerical experiments, we consider a drift function with local fluctuations generated by a double-layer compositional structure featuring local oscillations, and show that the empirical convergence rate becomes independent of the input dimension $d$. Compared to the $B$-spline method, the neural network estimator achieves better convergence rates and more effectively captures local features, particularly in higher-dimensional settings.
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
Differentiable Initialization-Accelerated CPU-GPU Hybrid Combinatorial Scheduling
arXiv:2603.28943v1 Announce Type: new
Abstract: This paper presents a hybrid CPU-GPU framework for solving combinatorial scheduling problems formulated as Integer Linear Programming (ILP). While scheduling underpins many optimization tasks in computing systems, solving these problems optimally at scale remains a long-standing challenge due to their NP-hard nature. We introduce a novel approach that combines differentiable optimization with classical ILP solving. Specifically, we utilize differentiable presolving to rapidly generate high-quality partial solutions, which serve as warm-starts for commercial ILP solvers (CPLEX, Gurobi) and rising open-source solver HiGHS. This method enables significantly improved early pruning compared to state-of-the-art standalone solvers. Empirical results across industry-scale benchmarks demonstrate up to a $10\times$ performance gain over baselines, narrowing the optimality gap to $<0.1\%$. This work represents the first demonstration of utilizing differentiable optimization to initialize exact ILP solvers for combinatorial scheduling, opening new opportunities to integrate machine learning infrastructure with classical exact optimization methods across broader domains.
Fonte: arXiv cs.LG
Vision • Score 85
M2H-MX: Multi-Task Dense Visual Perception for Real-Time Monocular Spatial Understanding
arXiv:2603.29236v1 Announce Type: new
Abstract: Monocular cameras are attractive for robotic perception due to their low cost and ease of deployment, yet achieving reliable real-time spatial understanding from a single image stream remains challenging. While recent multi-task dense prediction models have improved per-pixel depth and semantic estimation, translating these advances into stable monocular mapping systems is still non-trivial.
This paper presents M2H-MX, a real-time multi-task perception model for monocular spatial understanding. The model preserves multi-scale feature representations while introducing register-gated global context and controlled cross-task interaction in a lightweight decoder, enabling depth and semantic predictions to reinforce each other under strict latency constraints. Its outputs integrate directly into an unmodified monocular SLAM pipeline through a compact perception-to-mapping interface.
We evaluate both dense prediction accuracy and in-the-loop system performance. On NYUDv2, M2H-MX-L achieves state-of-the-art results, improving semantic mIoU by 6.6% and reducing depth RMSE by 9.4% over representative multi-task baselines. When deployed in a real-time monocular mapping system on ScanNet, M2H-MX reduces average trajectory error by 60.7% compared to a strong monocular SLAM baseline while producing cleaner metric-semantic maps. These results demonstrate that modern multi-task dense prediction can be reliably deployed for real-time monocular spatial perception in robotic systems.
Fonte: arXiv cs.CV
Vision • Score 85
Fisheye3R: Adapting Unified 3D Feed-Forward Foundation Models to Fisheye Lenses
arXiv:2603.28896v1 Announce Type: new
Abstract: Feed-forward foundation models for multi-view 3-dimensional (3D) reconstruction have been trained on large-scale datasets of perspective images; when tested on wide field-of-view images, e.g., from a fisheye camera, their performance degrades. Their error arises from changes in spatial positions of pixels due to a non-linear projection model that maps 3D points onto the 2D image plane. While one may surmise that training on fisheye images would resolve this problem, there are far fewer fisheye images with ground truth than perspective images, which limit generalization. To enable inference on imagery exhibiting high radial distortion, we propose Fisheye3R, a novel adaptation framework that extends these multi-view 3D reconstruction foundation models to natively accommodate fisheye inputs without performance regression on perspective images. To address the scarcity of fisheye images and ground truth, we introduce flexible learning schemes that support self-supervised adaptation using only unlabeled perspective images and supervised adaptation without any fisheye training data. Extensive experiments across three foundation models, including VGGT, $\pi^3$, and MapAnything, demonstrate that our approach consistently improves camera pose, depth, point map, and field-of-view estimation on fisheye images.
Fonte: arXiv cs.CV
Vision • Score 85
Dual-Imbalance Continual Learning for Real-World Food Recognition
arXiv:2603.29133v1 Announce Type: new
Abstract: Visual food recognition in real-world dietary logging scenarios naturally exhibits severe data imbalance, where a small number of food categories appear frequently while many others occur rarely, resulting in long-tailed class distributions. In practice, food recognition systems often operate in a continual learning setting, where new categories are introduced sequentially over time. However, existing studies typically assume that each incremental step introduces a similar number of new food classes, which rarely happens in real world where the number of newly observed categories can vary significantly across steps, leading to highly uneven learning dynamics. As a result, continual food recognition exhibits a dual imbalance: imbalanced samples within each food class and imbalanced numbers of new food classes to learn at each incremental learning step. In this work, we introduce DIME, a Dual-Imbalance-aware Adapter Merging framework for continual food recognition. DIME learns lightweight adapters for each task using parameter-efficient fine-tuning and progressively integrates them through a class-count guided spectral merging strategy. A rank-wise threshold modulation mechanism further stabilizes the merging process by preserving dominant knowledge while allowing adaptive updates. The resulting model maintains a single merged adapter for inference, enabling efficient deployment without accumulating task-specific modules. Experiments on realistic long-tailed food benchmarks under our step-imbalanced setup show that the proposed method consistently improves by more than 3% over the strongest existing continual learning baselines. Code is available at https://github.com/xiaoyanzhang1/DIME.
Fonte: arXiv cs.CV
Theory/Optimization • Score 85
mlr3mbo: Bayesian Optimization in R
arXiv:2603.29730v1 Announce Type: new
Abstract: We present mlr3mbo, a comprehensive and modular toolbox for Bayesian optimization in R. mlr3mbo supports single- and multi-objective optimization, multi-point proposals, batch and asynchronous parallelization, input and output transformations, and robust error handling. While it can be used for many standard Bayesian optimization variants in applied settings, researchers can also construct custom BO algorithms from its flexible building blocks. In addition to an introduction to the software, its design principles, and its building blocks, the paper presents two extensive empirical evaluations of the software on the surrogate-based benchmark suite YAHPO Gym. To identify robust default configurations for both numeric and mixed-hierarchical optimization regimes, and to gain further insights into the respective impacts of individual settings, we run a coordinate descent search over the mlr3mbo configuration space and analyze its results. Furthermore, we demonstrate that mlr3mbo achieves state-of-the-art performance by benchmarking it against a wide range of optimizers, including HEBO, SMAC3, Ax, and Optuna.
Fonte: arXiv stat.ML
MLOps/Systems • Score 85
Causality-inspired Federated Learning for Dynamic Spatio-Temporal Graphs
arXiv:2603.29384v1 Announce Type: new
Abstract: Federated Graph Learning (FGL) has emerged as a powerful paradigm for decentralized training of graph neural networks while preserving data privacy. However, existing FGL methods are predominantly designed for static graphs and rely on parameter averaging or distribution alignment, which implicitly assume that all features are equally transferable across clients, overlooking both the spatial and temporal heterogeneity and the presence of client-specific knowledge in real-world graphs. In this work, we identify that such assumptions create a vicious cycle of spurious representation entanglement, client-specific interference, and negative transfer, degrading generalization performance in Federated Learning over Dynamic Spatio-Temporal Graphs (FSTG). To address this issue, we propose a novel causality-inspired framework named SC-FSGL, which explicitly decouples transferable causal knowledge from client-specific noise through representation-level interventions. Specifically, we introduce a Conditional Separation Module that simulates soft interventions through client conditioned masks, enabling the disentanglement of invariant spatio-temporal causal factors from spurious signals and mitigating representation entanglement caused by client heterogeneity. In addition, we propose a Causal Codebook that clusters causal prototypes and aligns local representations via contrastive learning, promoting cross-client consistency and facilitating knowledge sharing across diverse spatio-temporal patterns. Experiments on five diverse heterogeneity Spatio-Temporal Graph (STG) datasets show that SC-FSGL outperforms state-of-the-art methods.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
MemFactory: Unified Inference & Training Framework for Agent Memory
arXiv:2603.29493v1 Announce Type: new
Abstract: Memory-augmented Large Language Models (LLMs) are essential for developing capable, long-term AI agents. Recently, applying Reinforcement Learning (RL) to optimize memory operations, such as extraction, updating, and retrieval, has emerged as a highly promising research direction. However, existing implementations remain highly fragmented and task-specific, lacking a unified infrastructure to streamline the integration, training, and evaluation of these complex pipelines. To address this gap, we present MemFactory, the first unified, highly modular training and inference framework specifically designed for memory-augmented agents. Inspired by the success of unified fine-tuning frameworks like LLaMA-Factory, MemFactory abstracts the memory lifecycle into atomic, plug-and-play components, enabling researchers to seamlessly construct custom memory agents via a "Lego-like" architecture. Furthermore, the framework natively integrates Group Relative Policy Optimization (GRPO) to fine-tune internal memory management policies driven by multi-dimensional environmental rewards. MemFactory provides out-of-the-box support for recent cutting-edge paradigms, including Memory-R1, RMM, and MemAgent. We empirically validate MemFactory on the open-source MemAgent architecture using its publicly available training and evaluation data. Across both in-domain and out-of-distribution evaluation sets, MemFactory consistently improves performance over the corresponding base models, with relative gains of up to 14.8%. By providing a standardized, extensible, and easy-to-use infrastructure, MemFactory significantly lowers the barrier to entry, paving the way for future innovations in memory-driven AI agents.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
Calibrated Confidence Expression for Radiology Report Generation
arXiv:2603.29492v1 Announce Type: new
Abstract: Safe deployment of Large Vision-Language Models (LVLMs) in radiology report generation requires not only accurate predictions but also clinically interpretable indicators of when outputs should be thoroughly reviewed, enabling selective radiologist verification and reducing the risk of hallucinated findings influencing clinical decisions. One intuitive approach to this is verbalized confidence, where the model explicitly states its certainty. However, current state-of-the-art language models are often overconfident, and research on calibration in multimodal settings such as radiology report generation is limited. To address this gap, we introduce ConRad (Confidence Calibration for Radiology Reports), a reinforcement learning framework for fine-tuning medical LVLMs to produce calibrated verbalized confidence estimates alongside radiology reports. We study two settings: a single report-level confidence score and a sentence-level variant assigning a confidence to each claim. Both are trained using the GRPO algorithm with reward functions based on the logarithmic scoring rule, which incentivizes truthful self-assessment by penalizing miscalibration and guarantees optimal calibration under reward maximization. Experimentally, ConRad substantially improves calibration and outperforms competing methods. In a clinical evaluation we show that ConRad's report level scores are well aligned with clinicians' judgment. By highlighting full reports or low-confidence statements for targeted review, ConRad can support safer clinical integration of AI-assistance for report generation.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
Kwame 2.0: Human-in-the-Loop Generative AI Teaching Assistant for Large Scale Online Coding Education in Africa
arXiv:2603.29159v1 Announce Type: new
Abstract: Providing timely and accurate learning support in large-scale online coding courses is challenging, particularly in resource-constrained contexts. We present Kwame 2.0, a bilingual (English-French) generative AI teaching assistant built using retrieval-augmented generation and deployed in a human-in-the-loop forum within SuaCode, an introductory mobile-based coding course for learners across Africa. Kwame 2.0 retrieves relevant course materials and generates context-aware responses while encouraging human oversight and community participation. We deployed the system in a 15-month longitudinal study spanning 15 cohorts with 3,717 enrollments across 35 African countries. Evaluation using community feedback and expert ratings shows that Kwame 2.0 provided high-quality and timely support, achieving high accuracy on curriculum-related questions, while human facilitators and peers effectively mitigated errors, particularly for administrative queries. Our findings demonstrate that human-in-the-loop generative AI systems can combine the scalability and speed of AI with the reliability of human support, offering an effective approach to learning assistance for underrepresented populations in resource-constrained settings at scale.
Fonte: arXiv cs.CL
RL • Score 85
APEX-EM: Non-Parametric Online Learning for Autonomous Agents via Structured Procedural-Episodic Experience Replay
arXiv:2603.29093v1 Announce Type: new
Abstract: LLM-based autonomous agents lack persistent procedural memory: they re-derive solutions from scratch even when structurally identical tasks have been solved before. We present \textbf{APEX-EM}, a non-parametric online learning framework that accumulates, retrieves, and reuses structured procedural plans without modifying model weights. APEX-EM introduces: (1) a \emph{structured experience representation} encoding the full procedural-episodic trace of each execution -- planning steps, artifacts, iteration history with error analysis, and quality scores; (2) a \emph{Plan-Retrieve-Generate-Iterate-Ingest} (PRGII) workflow with Task Verifiers providing multi-dimensional reward signals; and (3) a \emph{dual-outcome Experience Memory} with hybrid retrieval combining semantic search, structural signature matching, and plan DAG traversal -- enabling cross-domain transfer between tasks sharing no lexical overlap but analogous operational structure. Successful experiences serve as positive in-context examples; failures as negative examples with structured error annotations.
We evaluate on BigCodeBench~\cite{zhuo2025bigcodebench}, KGQAGen-10k~\cite{zhang2025kgqagen}, and Humanity's Last Exam~\cite{phan2025hle} using Claude Sonnet 4.5 and Opus 4.5. On KGQAGen-10k, APEX-EM achieves 89.6\% accuracy versus 41.3\% without memory (+48.3pp), surpassing the oracle-retrieval upper bound (84.9\%). On BigCodeBench, it reaches 83.3\% SR from a 53.9\% baseline (+29.4pp), exceeding MemRL's~\cite{memrl2025} +11.0pp gain under comparable frozen-backbone conditions (noting backbone differences controlled for in our analysis). On HLE, entity graph retrieval reaches 48.0\% from 25.2\% (+22.8pp). Ablations show component value is task-dependent: rich judge feedback is negligible for code generation but critical for structured queries (+10.3pp), while binary-signal iteration partially compensates for weaker feedback.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training
arXiv:2603.28858v1 Announce Type: new
Abstract: Continual pre-training is widely used to adapt LLMs to target languages and domains, yet the mixture ratio of training data remains a sensitive hyperparameter that is expensive to tune: they must be fixed before training begins, and a suboptimal choice can waste weeks of compute. In this work, we propose OptiMer, which decouples ratio selection from training: we train one CPT model per dataset, extract each model's distribution vector, which represents the parameter shift induced by that dataset, and search for optimal composition weights post-hoc via Bayesian optimization. Experiments on Gemma 3 27B across languages (Japanese, Chinese) and domains (Math, Code) show that OptiMer consistently outperforms data mixture and model averaging baselines with 15-35 times lower search cost. Key findings reveal that 1) the optimized weights can be interpreted as data mixture ratios, and retraining with these ratios improves data mixture CPT, and 2) the same vector pool can be re-optimized for a given objective without any retraining, producing target-tailored models on demand. Our work establishes that data mixture ratio selection, traditionally a pre-training decision, can be reformulated as a post-hoc optimization over distribution vectors, offering a more flexible paradigm for continual pre-training.
Fonte: arXiv cs.CL
MLOps/Systems • Score 85
Improving Efficiency of GPU Kernel Optimization Agents using a Domain-Specific Language and Speed-of-Light Guidance
arXiv:2603.29010v1 Announce Type: new
Abstract: Optimizing GPU kernels with LLM agents is an iterative process over a large design space. Every candidate must be generated, compiled, validated, and profiled, so fewer trials will save both runtime and cost. We make two key observations. First, the abstraction level that agents operate at is important. If it is too low, the LLM wastes reasoning on low-impact details. If it is too high, it may miss important optimization choices. Second, agents cannot easily tell when they reach the point of diminishing returns, wasting resources as they continue searching.
These observations motivate two design principles to improve efficiency: (1) a compact domain-specific language (DSL) that can be learned in context and lets the model reason at a higher level while preserving important optimization levers, and (2) Speed-of-Light (SOL) guidance that uses first-principles performance bounds to steer and budget search. We implement these principles in $\mu$CUTLASS, a DSL with a compiler for CUTLASS-backed GPU kernels that covers kernel configuration, epilogue fusion, and multi-stage pipelines. We use SOL guidance to estimate headroom and guide optimization trials, deprioritize problems that are near SOL, and flag kernels that game the benchmark.
On 59 KernelBench problems with the same iteration budgets, switching from generating low-level code to DSL code using GPT-5-mini turns a 0.40x geomean regression into a 1.27x speedup over PyTorch. Adding SOL-guided steering raises this to 1.56x. Across model tiers, $\mu$CUTLASS + SOL-guidance lets weaker models outperform stronger baseline agents at lower token cost. SOL-guided budgeting saves 19-43% of tokens while retaining at least 95% of geomean speedup, with the best policy reaching a 1.68x efficiency gain. Lastly, SOL analysis helps detect benchmark-gaming cases, where kernels may appear fast while failing to perform the intended computation.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
PolarQuant: Optimal Gaussian Weight Quantization via Hadamard Rotation for LLM Compression
arXiv:2603.29078v1 Announce Type: new
Abstract: We present PolarQuant, a post-training weight quantization method for large language models (LLMs) that exploits the distributional structure of neural network weights to achieve near-lossless compression. PolarQuant operates in three stages: (1) block-wise normalization to the unit hypersphere, (2) Walsh-Hadamard rotation to transform coordinates into approximately Gaussian random variables, and (3) quantization with centroids matched to the Gaussian distribution. Our ablation reveals that Hadamard rotation alone accounts for 98% of the quality improvement, reducing Qwen3.5-9B perplexity from 6.90 (absmax Q5) to 6.40 (Delta = +0.03 from FP16), making it practically lossless without any calibration data. Furthermore, PolarQuant functions as an effective preprocessing step for downstream INT4 quantizers: PolarQuant Q5 dequantized and re-quantized by torchao INT4 achieves perplexity 6.56 versus 6.68 for direct absmax INT4, while maintaining 43.1 tok/s throughput at 6.5 GB VRAM. Code and models are publicly available.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Research
arXiv:2603.28986v1 Announce Type: new
Abstract: Current Autonomous Scientific Research (ASR) systems, despite leveraging large language models (LLMs) and agentic architectures, remain constrained by fixed workflows and toolsets that prevent adaptation to evolving tasks and environments. We introduce Mimosa, an evolving multi-agent framework that automatically synthesizes task-specific multi-agent workflows and iteratively refines them through experimental feedback. Mimosa leverages the Model Context Protocol (MCP) for dynamic tool discovery, generates workflow topologies via a meta-orchestrator, executes subtasks through code-generating agents that invoke available tools and scientific software libraries, and scores executions with an LLM-based judge whose feedback drives workflow refinement. On ScienceAgentBench, Mimosa achieves a success rate of 43.1% with DeepSeek-V3.2, surpassing both single-agent baselines and static multi-agent configurations. Our results further reveal that models respond heterogeneously to multi-agent decomposition and iterative learning, indicating that the benefits of workflow evolution depend on the capabilities of the underlying execution model. Beyond these benchmarks, Mimosa modular architecture and tool-agnostic design make it readily extensible, and its fully logged execution traces and archived workflows support auditability by preserving every analytical step for inspection and potential replication. Combined with domain-expert guidance, the framework has the potential to automate a broad range of computationally accessible scientific tasks across disciplines. Released as a fully open-source platform, Mimosa aims to provide an open foundation for community-driven ASR.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
DeepRV: Accelerating Spatiotemporal Inference with Pre-trained Neural Priors
arXiv:2503.21473v3 Announce Type: replace
Abstract: Gaussian Processes (GPs) provide a flexible and statistically principled foundation for modelling spatiotemporal phenomena, but their $O(N^3)$ scaling makes them intractable for large datasets. Approximate methods such as variational inference (VI), inducing-point (sparse) GPs, low-rank kernel approximations (e.g., Nystrom methods and random Fourier features), and approximations such as INLA improve scalability but typically trade off accuracy, calibration, or modelling flexibility. We introduce DeepRV, a neural-network surrogate that replaces GP prior sampling, while closely matching full GP accuracy at inference including hyperparameter estimates, and reducing computational complexity to $O(N^2)$, increasing scalability and inference speed. DeepRV serves as a drop-in replacement for GP prior realisations in e.g. MCMC-based probabilistic programming pipelines, preserving full model flexibility. Across simulated benchmarks, non-separable spatiotemporal GPs, and a real-world application to education deprivation in London (n = 4,994 locations), DeepRV achieves the highest fidelity to exact GPs while substantially accelerating inference. Code is provided in the dl4bi Python package, with all experiments run on a single consumer-grade GPU to ensure accessibility for practitioners.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
Disentangled Graph Prompting for Out-Of-Distribution Detection
arXiv:2603.29644v1 Announce Type: new
Abstract: When testing data and training data come from different distributions, deep neural networks (DNNs) will face significant safety risks in practical applications. Therefore, out-of-distribution (OOD) detection techniques, which can identify OOD samples at test time and alert the system, are urgently needed. Existing graph OOD detection methods usually characterize fine-grained in-distribution (ID) patterns from multiple perspectives, and train end-to-end graph neural networks (GNNs) for prediction. However, due to the unavailability of OOD data during training, the absence of explicit supervision signals could lead to sub-optimal performance of end-to-end encoders. To address this issue, we follow the pre-training+prompting paradigm to utilize pre-trained GNN encoders, and propose Disentangled Graph Prompting (DGP), to capture fine-grained ID patterns with the help of ID graph labels. Specifically, we design two prompt generators that respectively generate class-specific and class-agnostic prompt graphs by modifying the edge weights of an input graph. We also design several effective losses to train the prompt generators and prevent trivial solutions. We conduct extensive experiments on ten datasets to demonstrate the superiority of our proposed DGP, which achieves a relative AUC improvement of 3.63% over the best graph OOD detection baseline. Ablation studies and hyper-parameter experiments further show the effectiveness of DGP. Code is available at https://github.com/BUPT-GAMMA/DGP.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
mtslearn: Machine Learning in Python for Medical Time Series
arXiv:2603.29432v1 Announce Type: new
Abstract: Medical time-series data captures the dynamic progression of patient conditions, playing a vital role in modern clinical decision support systems. However, real-world clinical data is highly heterogeneous and inconsistently formatted. Furthermore, existing machine learning tools often have steep learning curves and fragmented workflows. Consequently, a significant gap remains between cutting-edge AI technologies and clinical application. To address this, we introduce mtslearn, an end-to-end integrated toolkit specifically designed for medical time-series data. First, the framework provides a unified data interface that automates the parsing and alignment of wide, long, and flat data formats. This design significantly reduces data cleaning overhead. Building on this, mtslearn provides a complete pipeline from data reading and feature engineering to model training and result visualization. Furthermore, it offers flexible interfaces for custom algorithms. Through a modular design, mtslearn simplifies complex data engineering tasks into a few lines of code. This significantly lowers the barrier to entry for clinicians with limited programming experience, empowering them to focus more on exploring medical hypotheses and accelerating the translation of advanced algorithms into real-world clinical practice. mtslearn is publicly available at https://github.com/PKUDigitalHealth/mtslearn.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Stochastic Dimension Implicit Functional Projections for Exact Integral Conservation in High-Dimensional PINNs
arXiv:2603.29237v1 Announce Type: new
Abstract: Enforcing exact macroscopic conservation laws, such as mass and energy, in neural partial differential equation (PDE) solvers is computationally challenging in high dimensions. Traditional discrete projections rely on deterministic quadrature that scales poorly and restricts mesh-free formulations like PINNs. Furthermore, high-order operators incur heavy memory overhead, and generic optimization often lacks convergence guarantees for non-convex conservation manifolds. To address this, we propose the Stochastic Dimension Implicit Functional Projection (SDIFP) framework. Instead of projecting discrete vectors, SDIFP applies a global affine transformation to the continuous network output. This yields closed-form solutions for integral constraints via detached Monte Carlo (MC) quadrature, bypassing spatial grid dependencies. For scalable training, we introduce a doubly-stochastic unbiased gradient estimator (DS-UGE). By decoupling spatial sampling from differential operator subsampling, the DS-UGE reduces memory complexity from $\mathcal{O}(M \times N_{\mathcal{L}})$ to $\mathcal{O}(N \times |\mathcal{I}|)$. SDIFP mitigates sampling variance, preserves solution regularity, and maintains $\mathcal{O}(1)$ inference efficiency, providing a scalable, mesh-free approach for solving conservative high-dimensional PDEs.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Quality-Controlled Active Learning via Gaussian Processes for Robust Structure-Property Learning in Autonomous Microscopy
arXiv:2603.29135v1 Announce Type: new
Abstract: Autonomous experimental systems are increasingly used in materials research to accelerate scientific discovery, but their performance is often limited by low-quality, noisy data. This issue is especially problematic in data-intensive structure-property learning tasks such as Image-to-Spectrum (Im2Spec) and Spectrum-to-Image (Spec2Im) translations, where standard active learning strategies can mistakenly prioritize poor-quality measurements. We introduce a gated active learning framework that combines curiosity-driven sampling with a physics-informed quality control filter based on the Simple Harmonic Oscillator model fits, allowing the system to automatically exclude low-fidelity data during acquisition. Evaluations on a pre-acquired dataset of band-excitation piezoresponse spectroscopy (BEPS) data from PbTiO3 thin films with spatially localized noise show that the proposed method outperforms random sampling, standard active learning, and multitask learning strategies. The gated approach enhances both Im2Spec and Spec2Im by handling noise during training and acquisition, leading to more reliable forward and inverse predictions. In contrast, standard active learners often misinterpret noise as uncertainty and end up acquiring bad samples that hurt performance. Given its promising applicability, we further deployed the framework in real-time experiments on BiFeO3 thin films, demonstrating its effectiveness in real autonomous microscopy experiments. Overall, this work supports a shift toward hybrid autonomy in self-driving labs, where physics-informed quality assessment and active decision-making work hand-in-hand for more reliable discovery.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Derived Fields Preserve Fine-Scale Detail in Budgeted Neural Simulators
arXiv:2603.29224v1 Announce Type: new
Abstract: Fine-scale-faithful neural simulation under fixed storage budgets remains challenging. Many existing methods reduce high-frequency error by improving architectures, training objectives, or rollout strategies. However, under budgeted coarsen-quantize-decode pipelines, fine detail can already be lost when the carried state is constructed. In the canonical periodic incompressible Navier-Stokes setting, we show that primitive and derived fields undergo systematically different retained-band distortions under the same operator. Motivated by this observation, we formulate Derived-Field Optimization (DerivOpt), a general state-design framework that chooses which physical fields are carried and how storage budget is allocated across them under a calibrated channel model. Across the full time-dependent forward subset of PDEBench, DerivOpt not only improves pooled mean rollout nRMSE, but also delivers a decisive advantage in fine-scale fidelity over a broad set of strong baselines. More importantly, the gains are already visible at input time, before rollout learning begins. This indicates that the carried state is often the dominant bottleneck under tight storage budgets. These results suggest a broader conclusion: in budgeted neural simulation, carried-state design should be treated as a first-class design axis alongside architecture, loss, and rollout strategy.
Fonte: arXiv cs.LG
RL • Score 85
Realistic Market Impact Modeling for Reinforcement Learning Trading Environments
arXiv:2603.29086v1 Announce Type: new
Abstract: Reinforcement learning (RL) has shown promise for trading, yet most open-source backtesting environments assume negligible or fixed transaction costs, causing agents to learn trading behaviors that fail under realistic execution. We introduce three Gymnasium-compatible trading environments -- MACE (Market-Adjusted Cost Execution) stock trading, margin trading, and portfolio optimization -- that integrate nonlinear market impact models grounded in the Almgren-Chriss framework and the empirically validated square-root impact law. Each environment provides pluggable cost models, permanent impact tracking with exponential decay, and comprehensive trade-level logging. We evaluate five DRL algorithms (A2C, PPO, DDPG, SAC, TD3) on the NASDAQ-100, comparing a fixed 10 bps baseline against the AC model with Optuna-tuned hyperparameters. Our results show that (i) the cost model materially changes both absolute performance and the relative ranking of algorithms across all three environments; (ii) the AC model produces dramatically different trading behavior, e.g., daily costs dropping from $200k to $8k with turnover falling from 19% to 1%; (iii) hyperparameter optimization is essential for constraining pathological trading, with costs dropping up to 82%; and (iv) algorithm-cost model interactions are strongly environment-specific, e.g., DDPG's OOS Sharpe jumps from -2.1 to 0.3 under AC in margin trading while SAC's drops from -0.5 to -1.2. We release the full suite as an open-source extension to FinRL-Meta.
Fonte: arXiv cs.LG
MLOps/Systems • Score 88
ARCS: Autoregressive Circuit Synthesis with Topology-Aware Graph Attention and Spec Conditioning
arXiv:2603.29068v1 Announce Type: new
Abstract: I present ARCS, a system for amortized analog circuit generation that produces complete, SPICE-simulatable designs (topology and component values) in milliseconds rather than the minutes required by search-based methods. A hybrid pipeline combining two learned generators (a graph VAE and a flow-matching model) with SPICE-based ranking achieves 99.9% simulation validity (reward 6.43/8.0) across 32 topologies using only 8 SPICE evaluations, 40x fewer than genetic algorithms. For single-model inference, a topology-aware Graph Transformer with Best-of-3 candidate selection reaches 85% simulation validity in 97ms, over 600x faster than random search. The key technical contribution is Group Relative Policy Optimization (GRPO): I identify a critical failure mode of REINFORCE (cross-topology reward distribution mismatch) and resolve it with per-topology advantage normalization, improving simulation validity by +9.6pp over REINFORCE in only 500 RL steps (10x fewer). Grammar-constrained decoding additionally guarantees 100% structural validity by construction via topology-aware token masking. ARCS does not yet match the per-design quality of search-based optimization (5.48 vs. 7.48 reward), but its >1000x speed advantage enables rapid prototyping, design-space exploration, and warm-starting search methods (recovering 96.6% of GA quality with 49% fewer simulations).
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
From Physics to Surrogate Intelligence: A Unified Electro-Thermo-Optimization Framework for TSV Networks
arXiv:2603.29268v1 Announce Type: new
Abstract: High-density through-substrate vias (TSVs) enable 2.5D/3D heterogeneous integration but introduce significant signal-integrity and thermal-reliability challenges due to electrical coupling, insertion loss, and self-heating. Conventional full-wave finite-element method (FEM) simulations provide high accuracy but become computationally prohibitive for large design-space exploration. This work presents a scalable electro-thermal modeling and optimization framework that combines physics-informed analytical modeling, graph neural network (GNN) surrogates, and full-wave sign-off validation. A multi-conductor analytical model computes broadband S-parameters and effective anisotropic thermal conductivities of TSV arrays, achieving $5\%-10\%$ relative Frobenius error (RFE) across array sizes up to $15x15$. A physics-informed GNN surrogate (TSV-PhGNN), trained on analytical data and fine-tuned with HFSS simulations, generalizes to larger arrays with RFE below $2\%$ and nearly constant variance. The surrogate is integrated into a multi-objective Pareto optimization framework targeting reflection coefficient, insertion loss, worst-case crosstalk (NEXT/FEXT), and effective thermal conductivity. Millions of TSV configurations can be explored within minutes, enabling exhaustive layout and geometric optimization that would be infeasible using FEM alone. Final designs are validated with Ansys HFSS and Mechanical, showing strong agreement. The proposed framework enables rapid electro-thermal co-design of TSV arrays while reducing per-design evaluation time by more than six orders of magnitude.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
CausalPulse: An Industrial-Grade Neurosymbolic Multi-Agent Copilot for Causal Diagnostics in Smart Manufacturing
arXiv:2603.29755v1 Announce Type: new
Abstract: Modern manufacturing environments demand real-time, trustworthy, and interpretable root-cause insights to sustain productivity and quality. Traditional analytics pipelines often treat anomaly detection, causal inference, and root-cause analysis as isolated stages, limiting scalability and explainability. In this work, we present CausalPulse, an industry-grade multi-agent copilot that automates causal diagnostics in smart manufacturing. It unifies anomaly detection, causal discovery, and reasoning through a neurosymbolic architecture built on standardized agentic protocols. CausalPulse is being deployed in a Robert Bosch manufacturing plant, integrating seamlessly with existing monitoring workflows and supporting real-time operation at production scale. Evaluations on both public (Future Factories) and proprietary (Planar Sensor Element) datasets show high reliability, achieving overall success rates of 98.0% and 98.73%. Per-criterion success rates reached 98.75% for planning and tool use, 97.3% for self-reflection, and 99.2% for collaboration. Runtime experiments report end-to-end latency of 50-60s per diagnostic workflow with near-linear scalability (R^2=0.97), confirming real-time readiness. Comparison with existing industrial copilots highlights distinct advantages in modularity, extensibility, and deployment maturity. These results demonstrate how CausalPulse's modular, human-in-the-loop design enables reliable, interpretable, and production-ready automation for next-generation manufacturing.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
Reasoning-Driven Synthetic Data Generation and Evaluation
arXiv:2603.29791v1 Announce Type: new
Abstract: Although many AI applications of interest require specialized multi-modal models, relevant data to train such models is inherently scarce or inaccessible. Filling these gaps with human annotators is prohibitively expensive, error-prone, and time-consuming, leading model builders to increasingly consider synthetic data as a scalable alternative. However, existing synthetic data generation methods often rely on manual prompts, evolutionary algorithms, or extensive seed data from the target distribution - limiting their scalability, explainability, and control. In this paper, we introduce Simula: a novel reasoning-driven framework for data generation and evaluation. It employs a seedless, agentic approach to generate synthetic datasets at scale, allowing users to define desired dataset characteristics through an explainable and controllable process that enables fine-grained resource allocation. We show the efficacy of our approach on a variety of datasets, rigorously testing both intrinsic and downstream properties. Our work (1) offers guidelines for synthetic data mechanism design, (2) provides insights into generating and evaluating synthetic data at scale, and (3) unlocks new opportunities for developing and deploying AI in domains where data scarcity or privacy concerns are paramount.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
OneComp: One-Line Revolution for Generative AI Model Compression
arXiv:2603.28845v1 Announce Type: new
Abstract: Deploying foundation models is increasingly constrained by memory footprint, latency, and hardware costs. Post-training compression can mitigate these bottlenecks by reducing the precision of model parameters without significantly degrading performance; however, its practical implementation remains challenging as practitioners navigate a fragmented landscape of quantization algorithms, precision budgets, data-driven calibration strategies, and hardware-dependent execution regimes. We present OneComp, an open-source compression framework that transforms this expert workflow into a reproducible, resource-adaptive pipeline. Given a model identifier and available hardware, OneComp automatically inspects the model, plans mixed-precision assignments, and executes progressive quantization stages, ranging from layer-wise compression to block-wise refinement and global refinement. A key architectural choice is treating the first quantized checkpoint as a deployable pivot, ensuring that each subsequent stage improves the same model and that quality increases as more compute is invested. By converting state-of-the-art compression research into an extensible, open-source, hardware-aware pipeline, OneComp bridges the gap between algorithmic innovation and production-grade model deployment.
Fonte: arXiv cs.LG
NLP/LLMs • Score 88
AgentFixer: From Failure Detection to Fix Recommendations in LLM Agentic Systems
arXiv:2603.29848v1 Announce Type: new
Abstract: We introduce a comprehensive validation framework for LLM-based agentic systems that provides systematic diagnosis and improvement of reliability failures. The framework includes fifteen failure-detection tools and two root-cause analysis modules that jointly uncover weaknesses across input handling, prompt design, and output generation. It integrates lightweight rule-based checks with LLM-as-a-judge assessments to support structured incident detection, classification, and repair. We applied the framework to IBM CUGA, evaluating its performance on the AppWorld and WebArena benchmarks. The analysis revealed recurrent planner misalignments, schema violations, brittle prompt dependencies, and more. Based on these insights, we refined both prompting and coding strategies, maintaining CUGA's benchmark results while enabling mid-sized models such as Llama 4 and Mistral Medium to achieve notable accuracy gains, substantially narrowing the gap with frontier models. Beyond quantitative validation, we conducted an exploratory study that fed the framework's diagnostic outputs and agent description into an LLM for self-reflection and prioritization. This interactive analysis produced actionable insights on recurring failure patterns and focus areas for improvement, demonstrating how validation itself can evolve into an agentic, dialogue-driven process. These results show a path toward scalable, quality assurance, and adaptive validation in production agentic systems, offering a foundation for more robust, interpretable, and self-improving agentic architectures.
Fonte: arXiv cs.AI
Applications • Score 85
Owl-AuraID 1.0: An Intelligent System for Autonomous Scientific Instrumentation and Scientific Data Analysis
arXiv:2603.29828v1 Announce Type: new
Abstract: Scientific discovery increasingly depends on high-throughput characterization, yet automation is hindered by proprietary GUIs and the limited generalizability of existing API-based systems. We present Owl-AuraID, a software-hardware collaborative embodied agent system that adopts a GUI-native paradigm to operate instruments through the same interfaces as human experts. Its skill-centric framework integrates Type-1 (GUI operation) and Type-2 (data analysis) skills into end-to-end workflows, connecting physical sample handling with scientific interpretation. Owl-AuraID demonstrates broad coverage across ten categories of precision instruments and diverse workflows, including multimodal spectral analysis, microscopic imaging, and crystallographic analysis, supporting modalities such as FTIR, NMR, AFM, and TGA. Overall, Owl-AuraID provides a practical, extensible foundation for autonomous laboratories and illustrates a path toward evolving laboratory intelligence through reusable operational and analytical skills. The code are available at https://github.com/OpenOwlab/AuraID.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
View-oriented Conversation Compiler for Agent Trace Analysis
arXiv:2603.29678v1 Announce Type: new
Abstract: Agent traces carry increasing analytical value in the era of context learning and harness-driven agentic cognition, yet most prior work treats conversation format as a trivial engineering detail. Modern agent conversations contain deeply structured content, including nested tool calls and results, chain-of-thought reasoning blocks, sub-agent invocations, context-window compaction boundaries, and harness-injected system directives, whose complexity far exceeds that of simple user-assistant exchanges. Feeding such traces to a reflector or other analytical mechanism in plain text, JSON, YAML, or via grep can materially degrade analysis quality. This paper presents VCC (View-oriented Conversation Compiler), a compiler (lex, parse, IR, lower, emit) that transforms raw agent JSONL logs into a family of structured views: a full view (lossless transcript serving as the canonical line-number coordinate system), a user-interface view (reconstructing the interaction as the user actually perceived it), and an adaptive view (a structure-preserving projection governed by a relevance predicate). In a context-learning experiment on AppWorld, replacing only the reflector's input format, from raw JSONL to VCC-compiled views, leads to higher pass rates across all three model configurations tested, while cutting reflector token consumption by half to two-thirds and producing more concise learned memory. These results suggest that message format functions as infrastructure for context learning, not as an incidental implementation choice.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
ELT-Bench-Verified: Benchmark Quality Issues Underestimate AI Agent Capabilities
arXiv:2603.29399v1 Announce Type: new
Abstract: Constructing Extract-Load-Transform (ELT) pipelines is a labor-intensive data engineering task and a high-impact target for AI automation. On ELT-Bench, the first benchmark for end-to-end ELT pipeline construction, AI agents initially showed low success rates, suggesting they lacked practical utility.
We revisit these results and identify two factors causing a substantial underestimation of agent capabilities. First, re-evaluating ELT-Bench with upgraded large language models reveals that the extraction and loading stage is largely solved, while transformation performance improves significantly. Second, we develop an Auditor-Corrector methodology that combines scalable LLM-driven root-cause analysis with rigorous human validation (inter-annotator agreement Fleiss' kappa = 0.85) to audit benchmark quality. Applying this to ELT-Bench uncovers that most failed transformation tasks contain benchmark-attributable errors -- including rigid evaluation scripts, ambiguous specifications, and incorrect ground truth -- that penalize correct agent outputs.
Based on these findings, we construct ELT-Bench-Verified, a revised benchmark with refined evaluation logic and corrected ground truth. Re-evaluating on this version yields significant improvement attributable entirely to benchmark correction. Our results show that both rapid model improvement and benchmark quality issues contributed to underestimating agent capabilities. More broadly, our findings echo observations of pervasive annotation errors in text-to-SQL benchmarks, suggesting quality issues are systemic in data engineering evaluation. Systematic quality auditing should be standard practice for complex agentic tasks. We release ELT-Bench-Verified to provide a more reliable foundation for progress in AI-driven data engineering automation.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
LLM Readiness Harness: Evaluation, Observability, and CI Gates for LLM/RAG Applications
arXiv:2603.27355v1 Announce Type: new
Abstract: We present a readiness harness for LLM and RAG applications that turns evaluation into a deployment decision workflow. The system combines automated benchmarks, OpenTelemetry observability, and CI quality gates under a minimal API contract, then aggregates workflow success, policy compliance, groundedness, retrieval hit rate, cost, and p95 latency into scenario-weighted readiness scores with Pareto frontiers. We evaluate the harness on ticket-routing workflows and BEIR grounding tasks (SciFact and FiQA) with full Azure matrix coverage (162/162 valid cells across datasets, scenarios, retrieval depths, seeds, and models). Results show that readiness is not a single metric: on FiQA under sla-first at k=5, gpt-4.1-mini leads in readiness and faithfulness, while gpt-5.2 pays a substantial latency cost; on SciFact, models are closer in quality but still separable operationally. Ticket-routing regression gates consistently reject unsafe prompt variants, demonstrating that the harness can block risky releases instead of merely reporting offline scores. The result is a reproducible, operationally grounded framework for deciding whether an LLM or RAG system is ready to ship.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
ScoutAttention: Efficient KV Cache Offloading via Layer-Ahead CPU Pre-computation for LLM Inference
arXiv:2603.27138v1 Announce Type: new
Abstract: Large language models encounter critical GPU memory capacity constraints during long-context inference, where KV cache memory consumption severely limits decode batch sizes. While existing research has explored offloading KV cache to DRAM, these approaches either demand frequent GPU-CPU data transfers or impose extensive CPU computation requirements, resulting in poor GPU utilization as the system waits for I/O operations or CPU processing to complete.
We propose ScoutAttention, a novel KV cache offloading framework that accelerates LLM inference through collaborative GPU-CPU attention computation. To prevent CPU computation from bottlenecking the system, ScoutAttention introduces GPU-CPU collaborative block-wise sparse attention that significantly reduces CPU load. Unlike conventional parallel computing approaches, our framework features a novel layer-ahead CPU pre-computation algorithm, enabling the CPU to initiate attention computation one layer in advance, complemented by asynchronous periodic recall mechanisms to maintain minimal CPU compute load. Experimental results demonstrate that ScoutAttention maintains accuracy within 2.4% of baseline while achieving 2.1x speedup compared to existing offloading methods.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
GSR-GNN: Training Acceleration and Memory-Saving Framework of Deep GNNs on Circuit Graph
arXiv:2603.27156v1 Announce Type: new
Abstract: Graph Neural Networks (GNNs) show strong promise for circuit analysis, but scaling to modern large-scale circuit graphs is limited by GPU memory and training cost, especially for deep models. We revisit deep GNNs for circuit graphs and show that, when trainable, they significantly outperform shallow architectures, motivating an efficient, domain-specific training framework. We propose Grouped-Sparse-Reversible GNN (GSR-GNN), which enables training GNNs with up to hundreds of layers while reducing both compute and memory overhead. GSR-GNN integrates reversible residual modules with a group-wise sparse nonlinear operator that compresses node embeddings without sacrificing task-relevant information, and employs an optimized execution pipeline to eliminate fragmented activation storage and reduce data movement. On sampled circuit graphs, GSR-GNN achieves up to 87.2\% peak memory reduction and over 30$\times$ training speedup with negligible degradation in correlation-based quality metrics, making deep GNNs practical for large-scale EDA workloads.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
CARGO: Carbon-Aware Gossip Orchestration in Smart Shipping
arXiv:2603.27857v1 Announce Type: new
Abstract: Smart shipping operations increasingly depend on collaborative AI, yet the underlying data are generated across vessels with uneven connectivity, limited backhaul, and clear commercial sensitivity. In such settings, server-coordinated FL remains a weak systems assumption, depending on a reachable aggregation point and repeated wide-area synchronization, both of which are difficult to guarantee in maritime networks. A serverless gossip approach therefore represents a more natural approach, but existing methods still treat communication mainly as an optimization bottleneck, rather than as a resource that must be managed jointly with carbon cost, reliability, and long-term participation balance. In this context, this paper presents CARGO, a carbon-aware gossip orchestration framework for smart-shipping. CARGO separates learning into a control and a data plane. The data plane performs local optimization with compressed gossip exchange, while the control plane decides, at each round, which vessels should participate, which communication edges should be activated, how aggressively updates should be compressed, and when recovery actions should be triggered. We evaluate CARGO under a predictive-maintenance scenario using operational bulk-carrier engine data and a trace-driven maritime communication protocol that captures client dropout, partial participation, packet loss, and multiple connectivity regimes, derived from mobility-aware vessel interactions. Across the tested stress settings, CARGO consistently remains in the high-accuracy regime while reducing carbon footprint and communication overheads, compared to accuracy-competitive decentralized baselines. Overall, the conducted performance evaluation demonstrates that CARGO is a feasible and practical solution for reliable and resource-conscious maritime AI deployment.
Fonte: arXiv cs.AI
RecSys • Score 85
Let the Agent Steer: Closed-Loop Ranking Optimization via Influence Exchange
arXiv:2603.27765v1 Announce Type: new
Abstract: Recommendation ranking is fundamentally an influence allocation problem: a sorting formula distributes ranking influence among competing factors, and the business outcome depends on finding the optimal "exchange rates" among them. However, offline proxy metrics systematically misjudge how influence reallocation translates to online impact, with asymmetric bias across metrics that a single calibration factor cannot correct.
We present Sortify, the first fully autonomous LLM-driven ranking optimization agent deployed in a large-scale production recommendation system. The agent reframes ranking optimization as continuous influence exchange, closing the full loop from diagnosis to parameter deployment without human intervention. It addresses structural problems through three mechanisms: (1) a dual-channel framework grounded in Savage's Subjective Expected Utility (SEU) that decouples offline-online transfer correction (Belief channel) from constraint penalty adjustment (Preference channel); (2) an LLM meta-controller operating on framework-level parameters rather than low-level search variables; (3) a persistent Memory DB with 7 relational tables for cross-round learning. Its core metric, Influence Share, provides a decomposable measure where all factor contributions sum to exactly 100%.
Sortify has been deployed across two Southeast Asian markets. In Country A, the agent pushed GMV from -3.6% to +9.2% within 7 rounds with peak orders reaching +12.5%. In Country B, a cold-start deployment achieved +4.15% GMV/UU and +3.58% Ads Revenue in a 7-day A/B test, leading to full production rollout.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
DSevolve: Enabling Real-Time Adaptive Scheduling on Dynamic Shop Floor with LLM-Evolved Heuristic Portfolios
arXiv:2603.27628v1 Announce Type: new
Abstract: In dynamic manufacturing environments, disruptions such as machine breakdowns and new order arrivals continuously shift the optimal dispatching strategy, making adaptive rule selection essential. Existing LLM-powered Automatic Heuristic Design (AHD) frameworks evolve toward a single elite rule that cannot meet this adaptability demand. To address this, we present DSevolve, an industrial scheduling framework that evolves a quality-diverse portfolio of dispatching rules offline and adaptively deploys them online with second-level response time. Multi-persona seeding and topology-aware evolutionary operators produce a behaviorally diverse rule archive indexed by a MAP-Elites feature space. Upon each disruption event, a probe-based fingerprinting mechanism characterizes the current shop floor state, retrieves high-quality candidate rules from an offline knowledge base, and selects the best one via rapid look-ahead simulation. Evaluated on 500 dynamic flexible job shop instances derived from real industrial data, DSevolve outperforms state-of-the-art AHD frameworks, classical dispatching rules, genetic programming, and deep reinforcement learning, offering a practical and deployable solution for intelligent shop floor scheduling.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Liquid Networks with Mixture Density Heads for Efficient Imitation Learning
arXiv:2603.27058v1 Announce Type: new
Abstract: We compare liquid neural networks with mixture density heads against diffusion policies on Push-T, RoboMimic Can, and PointMaze under a shared-backbone comparison protocol that isolates policy-head effects under matched inputs, training budgets, and evaluation settings. Across tasks, liquid policies use roughly half the parameters (4.3M vs. 8.6M), achieve 2.4x lower offline prediction error, and run 1.8 faster at inference. In sample-efficiency experiments spanning 1% to 46.42% of training data, liquid models remain consistently more robust, with especially large gains in low-data and medium-data regimes. Closed-loop results on Push-T and PointMaze are directionally consistent with offline rankings but noisier, indicating that strong offline density modeling helps deployment while not fully determining closed-loop success. Overall, liquid recurrent multimodal policies provide a compact and practical alternative to iterative denoising for imitation learning.
Fonte: arXiv cs.LG
Applications • Score 85
An Intelligent Framework for Real-Time Yoga Pose Detection and Posture Correction
arXiv:2603.26760v1 Announce Type: new
Abstract: Yoga is widely recognized for improving physical fitness, flexibility, and mental well being. However, these benefits depend strongly on correct posture execution. Improper alignment during yoga practice can reduce effectiveness and increase the risk of musculoskeletal injuries, especially in self guided or online training environments. This paper presents a hybrid Edge AI based framework for real time yoga pose detection and posture correction. The proposed system integrates lightweight human pose estimation models with biomechanical feature extraction and a CNN LSTM based temporal learning architecture to recognize yoga poses and analyze motion dynamics. Joint angles and skeletal features are computed from detected keypoints and compared with reference pose configurations to evaluate posture correctness. A quantitative scoring mechanism is introduced to measure alignment deviations and generate real time corrective feedback through visual, text based, and voice based guidance. In addition, Edge AI optimization techniques such as model quantization and pruning are applied to enable low latency performance on resource constrained devices. The proposed framework provides an intelligent and scalable digital yoga assistant that can improve user safety and training effectiveness in modern fitness applications.
Fonte: arXiv cs.CV
RL • Score 85
Bitboard version of Tetris AI
arXiv:2603.26765v1 Announce Type: new
Abstract: The efficiency of game engines and policy optimization algorithms is crucial for training reinforcement learning (RL) agents in complex sequential decision-making tasks, such as Tetris. Existing Tetris implementations suffer from low simulation speeds, suboptimal state evaluation, and inefficient training paradigms, limiting their utility for large-scale RL research. To address these limitations, this paper proposes a high-performance Tetris AI framework based on bitboard optimization and improved RL algorithms. First, we redesign the Tetris game board and tetrominoes using bitboard representations, leveraging bitwise operations to accelerate core processes (e.g., collision detection, line clearing, and Dellacherie-Thiery Features extraction) and achieve a 53-fold speedup compared to OpenAI Gym-Tetris. Second, we introduce an afterstate-evaluating actor network that simplifies state value estimation by leveraging Tetris afterstate property, outperforming traditional action-value networks with fewer parameters. Third, we propose a buffer-optimized Proximal Policy Optimization (PPO) algorithm that balances sampling and update efficiency, achieving an average score of 3,829 on 10x10 grids within 3 minutes. Additionally, we develop a Python-Java interface compliant with the OpenAI Gym standard, enabling seamless integration with modern RL frameworks. Experimental results demonstrate that our framework enhances Tetris's utility as an RL benchmark by bridging low-level bitboard optimizations with high-level AI strategies, providing a sample-efficient and computationally lightweight solution for scalable sequential decision-making research.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
Parameter Estimation in Stochastic Differential Equations via Wiener Chaos Expansion and Stochastic Gradient Descent
arXiv:2603.27019v1 Announce Type: new
Abstract: This study addresses the inverse problem of parameter estimation for Stochastic Differential Equations (SDEs) by minimizing a regularized discrepancy functional via Stochastic Gradient Descent (SGD). To achieve computational efficiency, we leverage the Wiener Chaos Expansion (WCE), a spectral decomposition technique that projects the stochastic solution onto an orthogonal basis of Hermite polynomials. This transformation effectively maps the stochastic dynamics into a hierarchical system of deterministic functions, termed the \textit{propagator}. By reducing the stochastic inference task to a deterministic optimization problem, our framework circumvents the heavy computational burden and sampling requirements of traditional simulation-based methods like MCMC or MLE. The robustness and scalability of the proposed approach are demonstrated through numerical experiments on various non-linear SDEs, including models for individual biological growth. Results show that the WCE-SGD framework provides accurate parameter recovery even from discrete, noisy observations, offering a significant paradigm shift in the efficient modeling of complex stochastic systems.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
KAT-Coder-V2 Technical Report
arXiv:2603.27703v1 Announce Type: new
Abstract: We present KAT-Coder-V2, an agentic coding model developed by the KwaiKAT team at Kuaishou. KAT-Coder-V2 adopts a "Specialize-then-Unify" paradigm that decomposes agentic coding into five expert domains - SWE, WebCoding, Terminal, WebSearch, and General - each undergoing independent supervised fine-tuning and reinforcement learning, before being consolidated into a single model via on-policy distillation. We develop KwaiEnv, a modular infrastructure sustaining tens of thousands of concurrent sandbox instances, and scale RL training along task complexity, intent alignment, and scaffold generalization. We further propose MCLA for stabilizing MoE RL training and Tree Training for eliminating redundant computation over tree-structured trajectories with up to 6.2x speedup. KAT-Coder-V2 achieves 79.6% on SWE-bench Verified (vs. Claude Opus 4.6 at 80.8%), 88.7 on PinchBench (surpassing GLM-5 and MiniMax M2.7), ranks first across all three frontend aesthetics scenarios, and maintains strong generalist scores on Terminal-Bench Hard (46.8) and tau^2-Bench (93.9). Our model is publicly available at https://streamlake.com/product/kat-coder.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
SCOPE: Tree-based Self-Correcting Online Log Parsing via Syntactic-Semantic Collaboration
arXiv:2603.27247v1 Announce Type: new
Abstract: Log parsing is a critical step for automated log analysis in complex systems. Traditional heuristic-based methods offer high efficiency but are limited in accuracy due to overlooking semantic context. In contrast, recent LLM-based parsers improve accuracy via se mantic understanding but incur high latency from frequent model calls. To address this, we propose SCOPE, the first self-correcting online log parsing method that integrates the strengths of both heuristic and LLM-based paradigms. SCOPE introduces a novel bi-directional tree structure that enables efficient template match ing from both forward and reverse directions, resulting in a higher overall matching rate. Additionally, it adopts a two-stage syntactic semantic collaboration framework: a lightweight NLP model first utilizes part-of-speech (POS) information for syntax-based match ing, while the LLM is selectively invoked as a fallback to handle semantically complex cases when uncertainty remains. This design significantly reduces LLM API usage while maintaining high ac curacy, achieving a balance between efficiency and effectiveness. Extensive evaluations on diverse benchmark datasets show that SCOPE outperforms state-of-the-art methods in both accuracy and efficiency. The implementation and datasets are publicly released to facilitate further research.
Fonte: arXiv cs.CL
MLOps/Systems • Score 85
Calorimeter Shower Superresolution with Conditional Normalizing Flows: Implementation and Statistical Evaluation
arXiv:2603.26813v1 Announce Type: cross
Abstract: In High Energy Physics, detailed calorimeter simulations and reconstructions are essential for accurate energy measurements and particle identification, but their high granularity makes them computationally expensive. Developing data-driven techniques capable of recovering fine-grained information from coarser readouts, a task known as calorimeter superresolution, offers a promising way to reduce both computational and hardware costs while preserving detector performance. This thesis investigates whether a generative model originally designed for fast simulation can be effectively applied to calorimeter superresolution. Specifically, the model proposed in arXiv:2308.11700 is re-implemented independently and trained on the CaloChallenge 2022 dataset based on the Geant4 Par04 calorimeter geometry. Finally, the model's performance is assessed through a rigorous statistical evaluation framework, following the methodology introduced in arXiv:2409.16336, to quantitatively test its ability to reproduce the reference distributions.
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
High dimensional theory of two-phase optimizers
arXiv:2603.26954v1 Announce Type: new
Abstract: The trend towards larger training setups has brought a renewed interest in partially asynchronous two-phase optimizers which optimize locally and then synchronize across workers. Additionally, recent work suggests that the one-worker version of one of these algorithms, DiLoCo, shows promising results as a (synchronous) optimizer. Motivated by these studies we present an analysis of LA-DiLoCo, a simple member of the DiLoCo family, on a high-dimensional linear regression problem. We show that the one-worker variant, LA, provides a different tradeoff between signal and noise than SGD, which is beneficial in many scenarios. We also show that the multi-worker version generates more noise than the single worker version, but that this additional noise generation can be ameliorated by appropriate choice of hyperparameters. We conclude with an analysis of SLA -- LA with momentum -- and show that stacking two momentum operators gives an opportunity for acceleration via a non-linear transformation of the "effective'' Hessian spectrum, which is maximized for Nesterov momentum. Altogether our results show that two-phase optimizers represent a fruitful new paradigm for understanding and improving training algorithms.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
MuonEq: Balancing Before Orthogonalization with Lightweight Equilibration
arXiv:2603.28254v1 Announce Type: cross
Abstract: Orthogonalized-update optimizers such as Muon improve training of matrix-valued parameters, but existing extensions mostly act either after orthogonalization by rescaling updates or before it with heavier whitening-based preconditioners. We introduce {\method}, a lightweight family of pre-orthogonalization equilibration schemes for Muon in three forms: two-sided row/column normalization (RC), row normalization (R), and column normalization (C). These variants rebalance the momentum matrix before finite-step Newton--Schulz using row/column squared-norm statistics and only $\mathcal{O}(m+n)$ auxiliary state. We show that finite-step orthogonalization is governed by input spectral properties, especially stable rank and condition number, and that row/column normalization is a zeroth-order whitening surrogate that removes marginal scale mismatch. For the hidden matrix weights targeted by {\method}, the row-normalized variant R is the natural default and preserves the $\widetilde{\mathcal{O}}(T^{-1/4})$ stationarity guarantee of Muon-type methods. In LLaMA2 pretraining on C4, the default R variant consistently outperforms Muon on 130M and 350M models, yielding faster convergence and lower validation perplexity.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
A Step Toward Federated Pretraining of Multimodal Large Language Models
arXiv:2603.26786v1 Announce Type: new
Abstract: The rapid evolution of Multimodal Large Language Models (MLLMs) is bottlenecked by the saturation of high-quality public data, while vast amounts of diverse multimodal data remain inaccessible in privacy-sensitive silos. Federated Learning (FL) offers a promising solution to unlock these distributed resources, but existing research focuses predominantly on fine-tuning, leaving the foundational pre-training phase largely unexplored. In this paper, we formally introduce the Federated MLLM Alignment (Fed-MA) task, a lightweight pre-training paradigm that freezes the vision encoder and LLM while collaboratively training the cross-modal projector. We identify two critical challenges in this setting: (i) parameter interference in aggregating local projectors; and (ii) gradient oscillations in one-pass collaborative SGD. To address these challenges, we propose Fed-CMP, a pioneering framework for federated MLLM pre-training. Fed-CMP employs Canonical Reliability-Aware Aggregation, which constructs a canonical space to decompose client projectors into a shared alignment basis and client-specific coefficients, then performs reliability-weighted fusion to suppress parameter interference. Furthermore, Fed-CMP introduces Orthogonality-Preserved Momentum, which applies momentum to the shared alignment basis via orthogonal projection, accumulating historical optimization directions while preserving geometric structure. We construct four federated pre-training scenarios based on public datasets, and extensive experiments validate that Fed-CMP significantly outperforms existing baselines.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
Throughput Optimization as a Strategic Lever in Large-Scale AI Systems: Evidence from Dataloader and Memory Profiling Innovations
arXiv:2603.26823v1 Announce Type: new
Abstract: The development of large-scale foundation models, particularly Large Language Models (LLMs), is constrained by significant computational and memory bottlenecks. These challenges elevate throughput optimization from a mere engineering task to a critical strategic lever, directly influencing training time, operational cost, and the feasible scale of next-generation models. This paper synthesizes evidence from recent academic and industry innovations to analyze key advancements in training efficiency. We examine architectural solutions to dataloader bottlenecks, such as the OVERLORD framework, which has demonstrated a 4.5% improvement in end-to-end training throughput. We investigate memory optimization techniques designed to overcome the GPU memory wall, including CPU offloading strategies like DeepSpeed's ZeRO-Offload, which enable the training of models far exceeding single-accelerator capacity. Furthermore, we explore the growing importance of compiler-centric optimizations, exemplified by Triton-distributed, which enables the joint optimization of computation, memory, and communication for substantial performance gains. The analysis is contextualized by advanced profiling tools and hardware characterization studies that identify and mitigate previously overlooked overheads like Dynamic Voltage and Frequency Scaling (DVFS). Findings indicate that a holistic, system-level approach, integrating innovations across data pipelines, memory management, network fabrics, and compiler technologies, is essential for accelerating AI development, managing costs, and pushing the boundaries of model scale.
Fonte: arXiv cs.LG
NLP/LLMs • Score 90
daVinci-LLM:Towards the Science of Pretraining
arXiv:2603.27164v1 Announce Type: new
Abstract: The foundational pretraining phase determines a model's capability ceiling, as post-training struggles to overcome capability foundations established during pretraining, yet it remains critically under-explored. This stems from a structural paradox: organizations with computational resources operate under commercial pressures that inhibit transparent disclosure, while academic institutions possess research freedom but lack pretraining-scale computational resources. daVinci-LLM occupies this unexplored intersection, combining industrial-scale resources with full research freedom to advance the science of pretraining. We adopt a fully-open paradigm that treats openness as scientific methodology, releasing complete data processing pipelines, full training processes, and systematic exploration results. Recognizing that the field lacks systematic methodology for data processing, we employ the Data Darwinism framework, a principled L0-L9 taxonomy from filtering to synthesis. We train a 3B-parameter model from random initialization across 8T tokens using a two-stage adaptive curriculum that progressively shifts from foundational capabilities to reasoning-intensive enhancement. Through 200+ controlled ablations, we establish that: processing depth systematically enhances capabilities, establishing it as a critical dimension alongside volume scaling; different domains exhibit distinct saturation dynamics, necessitating adaptive strategies from proportion adjustments to format shifts; compositional balance enables targeted intensification while preventing performance collapse; how evaluation protocol choices shape our understanding of pretraining progress. By releasing the complete exploration process, we enable the community to build upon our findings and systematic methodologies to form accumulative scientific knowledge in pretraining.
Fonte: arXiv cs.AI
NLP/LLMs • Score 88
Robust Batch-Level Query Routing for Large Language Models under Cost and Capacity Constraints
arXiv:2603.26796v1 Announce Type: new
Abstract: We study the problem of routing queries to large language models (LLMs) under cost, GPU resources, and concurrency constraints. Prior per-query routing methods often fail to control batch-level cost, especially under non-uniform or adversarial batching. To address this, we propose a batch-level, resource-aware routing framework that jointly optimizes model assignment for each batch while respecting cost and model capacity limits. We further introduce a robust variant that accounts for uncertainty in predicted LLM performance, along with an offline instance allocation procedure that balances quality and throughput across multiple models. Experiments on two multi-task LLM benchmarks show that robustness improves accuracy by 1-14% over non-robust counterparts (depending on the performance estimator), batch-level routing outperforms per-query methods by up to 24% under adversarial batching, and optimized instance allocation yields additional gains of up to 3% compared to a non-optimized allocation, all while strictly controlling cost and GPU resource constraints.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
EpochX: Building the Infrastructure for an Emergent Agent Civilization
arXiv:2603.27304v1 Announce Type: new
Abstract: General-purpose technologies reshape economies less by improving individual tools than by enabling new ways to organize production and coordination. We believe AI agents are approaching a similar inflection point: as foundation models make broad task execution and tool use increasingly accessible, the binding constraint shifts from raw capability to how work is delegated, verified, and rewarded at scale. We introduce EpochX, a credits-native marketplace infrastructure for human-agent production networks. EpochX treats humans and agents as peer participants who can post tasks or claim them. Claimed tasks can be decomposed into subtasks and executed through an explicit delivery workflow with verification and acceptance. Crucially, EpochX is designed so that each completed transaction can produce reusable ecosystem assets, including skills, workflows, execution traces, and distilled experience. These assets are stored with explicit dependency structure, enabling retrieval, composition, and cumulative improvement over time. EpochX also introduces a native credit mechanism to make participation economically viable under real compute costs. Credits lock task bounties, budget delegation, settle rewards upon acceptance, and compensate creators when verified assets are reused. By formalizing the end-to-end transaction model together with its asset and incentive layers, EpochX reframes agentic AI as an organizational design problem: building infrastructures where verifiable work leaves persistent, reusable artifacts, and where value flows support durable human-agent collaboration.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
Koopman Operator Identification of Model Parameter Trajectories for Temporal Domain Generalization (KOMET)
arXiv:2603.26923v1 Announce Type: new
Abstract: Parametric models deployed in non-stationary environments degrade as the underlying data distribution evolves over time (a phenomenon known as temporal domain drift). In the current work, we present KOMET (Koopman Operator identification of Model parameter Evolution under Temporal drift), a model-agnostic, data-driven framework that treats the sequence of trained parameter vectors as the trajectory of a nonlinear dynamical system and identifies its governing linear operator via Extended Dynamic Mode Decomposition (EDMD). A warm-start sequential training protocol enforces parameter-trajectory smoothness, and a Fourier-augmented observable dictionary exploits the periodic structure inherent in many real-world distribution drifts. Once identified, KOMET's Koopman operator predicts future parameter trajectories autonomously, without access to future labeled data, enabling zero-retraining adaptation at deployment. Evaluated on six datasets spanning rotating, oscillating, and expanding distribution geometries, KOMET achieves mean autonomous-rollout accuracies between 0.981 and 1.000 over 100 held-out time steps. Spectral and coupling analyses further reveal interpretable dynamical structure consistent with the geometry of the drifting decision boundary.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
MediHive: A Decentralized Agent Collective for Medical Reasoning
arXiv:2603.27150v1 Announce Type: new
Abstract: Large language models (LLMs) have revolutionized medical reasoning tasks, yet single-agent systems often falter on complex, interdisciplinary problems requiring robust handling of uncertainty and conflicting evidence. Multi-agent systems (MAS) leveraging LLMs enable collaborative intelligence, but prevailing centralized architectures suffer from scalability bottlenecks, single points of failure, and role confusion in resource-constrained environments. Decentralized MAS (D-MAS) promise enhanced autonomy and resilience via peer-to-peer interactions, but their application to high-stakes healthcare domains remains underexplored. We introduce MediHive, a novel decentralized multi-agent framework for medical question answering that integrates a shared memory pool with iterative fusion mechanisms. MediHive deploys LLM-based agents that autonomously self-assign specialized roles, conduct initial analyses, detect divergences through conditional evidence-based debates, and locally fuse peer insights over multiple rounds to achieve consensus. Empirically, MediHive outperforms single-LLM and centralized baselines on MedQA and PubMedQA datasets, attaining accuracies of 84.3% and 78.4%, respectively. Our work advances scalable, fault-tolerant D-MAS for medical AI, addressing key limitations of centralized designs while demonstrating superior performance in reasoning-intensive tasks.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
PhyDCM: A Reproducible Open-Source Framework for AI-Assisted Brain Tumor Classification from Multi-Sequence MRI
arXiv:2603.26794v1 Announce Type: new
Abstract: MRI-based medical imaging has become indispensable in modern clinical diagnosis, particularly for brain tumor detection. However, the rapid growth in data volume poses challenges for conventional diagnostic approaches. Although deep learning has shown strong performance in automated classification, many existing solutions are confined to closed technical architectures, limiting reproducibility and further academic development. PhyDCM is introduced as an open-source software framework that integrates a hybrid classification architecture based on MedViT with standardized DICOM processing and an interactive desktop visualization interface. The system is designed as a modular digital library that separates computational logic from the graphical interface, allowing independent modification and extension of components. Standardized preprocessing, including intensity rescaling and limited data augmentation, ensures consistency across varying MRI acquisition settings. Experimental evaluation on MRI datasets from BRISC2025 and curated Kaggle collections (FigShare, SARTAJ, and Br35H) demonstrates stable diagnostic performance, achieving over 93% classification accuracy across categories. The framework supports structured, exportable outputs and multi-planar reconstruction of volumetric data. By emphasizing transparency, modularity, and accessibility, PhyDCM provides a practical foundation for reproducible AI-driven medical image analysis, with flexibility for future integration of additional imaging modalities.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Self-evolving AI agents for protein discovery and directed evolution
arXiv:2603.27303v1 Announce Type: new
Abstract: Protein scientific discovery is bottlenecked by the manual orchestration of information and algorithms, while general agents are insufficient in complex domain projects. VenusFactory2 provides an autonomous framework that shifts from static tool usage to dynamic workflow synthesis via a self-evolving multi-agent infrastructure to address protein-related demands. It outperforms a set of well-known agents on the VenusAgentEval benchmark, and autonomously organizes the discovery and optimization of proteins from a single natural language prompt.
Fonte: arXiv cs.AI
RL • Score 85
RG-TTA: Regime-Guided Meta-Control for Test-Time Adaptation in Streaming Time Series
arXiv:2603.27814v1 Announce Type: cross
Abstract: Test-time adaptation (TTA) enables neural forecasters to adapt to distribution shifts in streaming time series, but existing methods apply the same adaptation intensity regardless of the nature of the shift. We propose Regime-Guided Test-Time Adaptation (RG-TTA), a meta-controller that continuously modulates adaptation intensity based on distributional similarity to previously-seen regimes. Using an ensemble of Kolmogorov-Smirnov, Wasserstein-1, feature-distance, and variance-ratio metrics, RG-TTA computes a similarity score for each incoming batch and uses it to (i) smoothly scale the learning rate -- more aggressive for novel distributions, conservative for familiar ones -- and (ii) control gradient effort via loss-driven early stopping rather than fixed budgets, allowing the system to allocate exactly the effort each batch requires. As a supplementary mechanism, RG-TTA gates checkpoint reuse from a regime memory, loading stored specialist models only when they demonstrably outperform the current model (loss improvement >= 30%). RG-TTA is model-agnostic and strategy-composable: it wraps any forecaster exposing train/predict/save/load interfaces and enhances any gradient-based TTA method. We demonstrate three compositions -- RG-TTA, RG-EWC, and RG-DynaTTA -- and evaluate 6 update policies (3 baselines + 3 regime-guided variants) across 4 compact architectures (GRU, iTransformer, PatchTST, DLinear), 14 datasets (6 real-world multivariate benchmarks + 8 synthetic regime scenarios), and 4 forecast horizons (96, 192, 336, 720) under a streaming evaluation protocol with 3 random seeds (672 experiments total). Regime-guided policies achieve the lowest MSE in 156 of 224 seed-averaged experiments (69.6%), with RG-EWC winning 30.4% and RG-TTA winning 29.0%. Overall, RG-TTA reduces MSE by 5.7% vs TTA while running 5.5% faster; RG-EWC reduces MSE by 14.1% vs standalone EWC.
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
Machine Learning-Assisted High-Dimensional Matrix Estimation
arXiv:2603.28346v1 Announce Type: cross
Abstract: Efficient estimation of high-dimensional matrices-including covariance and precision matrices-is a cornerstone of modern multivariate statistics. Most existing studies have focused primarily on the theoretical properties of the estimators (e.g., consistency and sparsity), while largely overlooking the computational challenges inherent in high-dimensional settings. Motivated by recent advances in learning-based optimization method-which integrate data-driven structures with classical optimization algorithms-we explore high-dimensional matrix estimation assisted by machine learning. Specifically, for the optimization problem of high-dimensional matrix estimation, we first present a solution procedure based on the Linearized Alternating Direction Method of Multipliers (LADMM). We then introduce learnable parameters and model the proximal operators in the iterative scheme with neural networks, thereby improving estimation accuracy and accelerating convergence. Theoretically, we first prove the convergence of LADMM, and then establish the convergence, convergence rate, and monotonicity of its reparameterized counterpart; importantly, we show that the reparameterized LADMM enjoys a faster convergence rate. Notably, the proposed reparameterization theory and methodology are applicable to the estimation of both high-dimensional covariance and precision matrices. We validate the effectiveness of our method by comparing it with several classical optimization algorithms across different structures and dimensions of high-dimensional matrices.
Fonte: arXiv stat.ML
Vision • Score 85
Embedding Provenance in Computer Vision Datasets with JSON-LD
arXiv:2603.27348v1 Announce Type: new
Abstract: With the ubiquity of computer vision in industry, the importance of image provenance is becoming more apparent. Provenance provides information about the origin and derivation of some resource, e.g., an image dataset, enabling users to trace data changes to better understand the expected behaviors of downstream models trained on such data. Provenance may also help with data maintenance by ensuring compliance, supporting audits and improving reusability. Typically, if provided, provenance is stored separately, e.g., within a text file, leading to a loss of descriptive information for key details like image capture settings, data preprocessing steps, and model architecture or iteration. Images often lack the information detailing the parameters of their creation or compilation. This paper proposes a novel schema designed to structure image provenance in a manageable and coherent format. The approach utilizes JavaScript Object Notation for Linked Data (JSON-LD), embedding this provenance directly within the image file. This offers two significant benefits: (1) it aligns image descriptions with a robust schema inspired by and linked to established standards, and (2) it ensures that provenance remains intrinsically tied to images, preventing loss of information and enhancing system qualities, e.g., maintainability and adaptability. This approach emphasizes maintaining the direct connection between vision resources and their provenance.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Meta-Harness: End-to-End Optimization of Model Harnesses
arXiv:2603.28052v1 Announce Type: new
Abstract: The performance of large language model (LLM) systems depends not only on model weights, but also on their harness: the code that determines what information to store, retrieve, and present to the model. Yet harnesses are still designed largely by hand, and existing text optimizers are poorly matched to this setting because they compress feedback too aggressively. We introduce Meta-Harness, an outer-loop system that searches over harness code for LLM applications. It uses an agentic proposer that accesses the source code, scores, and execution traces of all prior candidates through a filesystem. On online text classification, Meta-Harness improves over a state-of-the-art context management system by 7.7 points while using 4x fewer context tokens. On retrieval-augmented math reasoning, a single discovered harness improves accuracy on 200 IMO-level problems by 4.7 points on average across five held-out models. On agentic coding, discovered harnesses surpass the best hand-engineered baselines on TerminalBench-2. Together, these results show that richer access to prior experience can enable automated harness engineering.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
From Inference Routing to Agent Orchestration: Declarative Policy Compilation with Cross-Layer Verification
arXiv:2603.27299v1 Announce Type: new
Abstract: The Semantic Router DSL is a non-Turing-complete policy language deployed in production for per-request LLM inference routing: content signals (embedding similarity, PII detection, jailbreak scoring) feed into weighted projections and priority-ordered decision trees that select a model, enforce privacy policies, and produce structured audit traces -- all from a single declarative source file. Prior work established conflict-free compilation for probabilistic predicates and positioned the DSL within the Workload-Router-Pool inference architecture.
This paper extends the same language from stateless, per-request routing to multi-step agent workflows -- the full path from inference gateway to agent orchestration to infrastructure deployment. The DSL compiler emits verified decision nodes for orchestration frameworks (LangGraph, OpenClaw), Kubernetes artifacts (NetworkPolicy, Sandbox CRD, ConfigMap), YANG/NETCONF payloads, and protocol-boundary gates (MCP, A2A) -- all from the same source.
Because the language is non-Turing-complete, the compiler guarantees exhaustive routing, conflict-free branching, referential integrity, and audit traces structurally coupled to the decision logic. Because signal definitions are shared across targets, a threshold change propagates from inference gateway to agent gate to infrastructure artifact in one compilation step -- eliminating cross-team coordination as the primary source of policy drift. We ground the approach in four pillars -- auditability, cost efficiency, verifiability, and tunability -- and identify the verification boundary at each layer.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
FeDMRA: Federated Incremental Learning with Dynamic Memory Replay Allocation
arXiv:2603.28455v1 Announce Type: cross
Abstract: In federated healthcare systems, Federated Class-Incremental Learning (FCIL) has emerged as a key paradigm, enabling continuous adaptive model learning among distributed clients while safeguarding data privacy. However, in practical applications, data across agent nodes within the distributed framework often exhibits non-independent and identically distributed (non-IID) characteristics, rendering traditional continual learning methods inapplicable. To address these challenges, this paper covers more comprehensive incremental task scenarios and proposes a dynamic memory allocation strategy for exemplar storage based on the data replay mechanism. This strategy fully taps into the inherent potential of data heterogeneity, while taking into account the performance fairness of all participating clients, thereby establishing a balanced and adaptive solution to mitigate catastrophic forgetting. Unlike the fixed allocation of client exemplar memory, the proposed scheme emphasizes the rational allocation of limited storage resources among clients to improve model performance. Furthermore, extensive experiments are conducted on three medical image datasets, and the results demonstrate significant performance improvements compared to existing baseline models.
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
Overcoming the Incentive Collapse Paradox
arXiv:2603.27049v1 Announce Type: new
Abstract: AI-assisted task delegation is increasingly common, yet human effort in such systems is costly and typically unobserved. Recent work by Bastani and Cachon (2025); Sambasivan et al. (2021) shows that accuracy-based payment schemes suffer from incentive collapse: as AI accuracy improves, sustaining positive human effort requires unbounded payments. We study this problem in a budget-constrained principal-agent framework with strategic human agents whose output accuracy depends on unobserved effort. We propose a sentinel-auditing payment mechanism that enforces a strictly positive and controllable level of human effort at finite cost, independent of AI accuracy. Building on this incentive-robust foundation, we develop an incentive-aware active statistical inference framework that jointly optimizes (i) the auditing rate and (ii) active sampling and budget allocation across tasks of varying difficulty to minimize the final statistical loss under a single budget. Experiments demonstrate improved cost-error tradeoffs relative to standard active learning and auditing-only baselines.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
Text Data Integration
arXiv:2603.27055v1 Announce Type: new
Abstract: Data comes in many forms. From a shallow perspective, they can be viewed as being either in structured (e.g., as a relation, as key-value pairs) or unstructured (e.g., text, image) formats. So far, machines have been fairly good at processing and reasoning over structured data that follows a precise schema. However, the heterogeneity of data poses a significant challenge on how well diverse categories of data can be meaningfully stored and processed. Data Integration, a crucial part of the data engineering pipeline, addresses this by combining disparate data sources and providing unified data access to end-users. Until now, most data integration systems have leaned on only combining structured data sources. Nevertheless, unstructured data (a.k.a. free text) also contains a plethora of knowledge waiting to be utilized. Thus, in this chapter, we firstly make the case for the integration of textual data, to later present its challenges, state of the art and open problems.
Fonte: arXiv cs.CL
Vision • Score 85
Steering Sparse Autoencoder Latents to Control Dynamic Head Pruning in Vision Transformers (Student Abstract)
arXiv:2603.26743v1 Announce Type: new
Abstract: Dynamic head pruning in Vision Transformers (ViTs) improves efficiency by removing redundant attention heads, but existing pruning policies are often difficult to interpret and control. In this work, we propose a novel framework by integrating Sparse Autoencoders (SAEs) with dynamic pruning, leveraging their ability to disentangle dense embeddings into interpretable and controllable sparse latents. Specifically, we train an SAE on the final-layer residual embedding of the ViT and amplify the sparse latents with different strategies to alter pruning decisions. Among them, per-class steering reveals compact, class-specific head subsets that preserve accuracy. For example, bowl improves accuracy (76% to 82%) while reducing head usage (0.72 to 0.33) via heads h2 and h5. These results show that sparse latent features enable class-specific control of dynamic pruning, effectively bridging pruning efficiency and mechanistic interpretability in ViTs.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
AutoMS: Multi-Agent Evolutionary Search for Cross-Physics Inverse Microstructure Design
arXiv:2603.27195v1 Announce Type: new
Abstract: Designing microstructures that satisfy coupled cross-physics objectives is a fundamental challenge in material science. This inverse design problem involves a vast, discontinuous search space where traditional topology optimization is computationally prohibitive, and deep generative models often suffer from "physical hallucinations," lacking the capability to ensure rigorous validity. To address this limitation, we introduce AutoMS, a multi-agent neuro-symbolic framework that reformulates inverse design as an LLM-driven evolutionary search. Unlike methods that treat LLMs merely as interfaces, AutoMS integrates them as "semantic navigators" to initialize search spaces and break local optima, while our novel Simulation-Aware Evolutionary Search (SAES) addresses the "blindness" of traditional evolutionary strategies. Specifically, SAES utilizes simulation feedback to perform local gradient approximation and directed parameter updates, effectively guiding the search toward physically valid Pareto frontiers. Orchestrating specialized agents (Manager, Parser, Generator, and Simulator), AutoMS achieves a state-of-the-art 83.8\% success rate on 17 diverse cross-physics tasks, nearly doubling the performance of traditional NSGA-II (43.7\%) and significantly outperforming ReAct-based LLM baselines (53.3\%). Furthermore, our hierarchical architecture reduces total execution time by 23.3\%. AutoMS demonstrates that autonomous agent systems can effectively navigate complex physical landscapes, bridging the gap between semantic design intent and rigorous physical validity.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
AstraAI: LLMs, Retrieval, and AST-Guided Assistance for HPC Codebases
arXiv:2603.27423v1 Announce Type: new
Abstract: We present AstraAI, a command-line interface (CLI) coding framework for high-performance computing (HPC) software development. AstraAI operates directly within a Linux terminal and integrates large language models (LLMs) with Retrieval-Augmented Generation (RAG) and Abstract Syntax Tree (AST)-based structural analysis to enable context-aware code generation for complex scientific codebases. The central idea is to construct a high-fidelity prompt that is passed to the LLM for inference. This prompt augments the user request with relevant code snippets retrieved from the underlying framework codebase via RAG and structural context extracted from AST analysis, providing the model with precise information about relevant functions, data structures, and overall code organization. The framework is designed to perform scoped modifications to source code while preserving structural consistency with the surrounding code. AstraAI supports both locally hosted models from Hugging Face and API-based frontier models accessible via the American Science Cloud, enabling flexible deployment across HPC environments. The system generates code that aligns with existing project structures and programming patterns. We demonstrate AstraAI on representative HPC code generation tasks within AMReX, a DOE-supported HPC software infrastructure for exascale applications.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
HeteroHub: An Applicable Data Management Framework for Heterogeneous Multi-Embodied Agent System
arXiv:2603.28010v1 Announce Type: new
Abstract: Heterogeneous Multi-Embodied Agent Systems involve coordinating multiple embodied agents with diverse capabilities to accomplish tasks in dynamic environments. This process requires the collection, generation, and consumption of massive, heterogeneous data, which primarily falls into three categories: static knowledge regarding the agents, tasks, and environments; multimodal training datasets tailored for various AI models; and high-frequency sensor streams. However, existing frameworks lack a unified data management infrastructure to support the real-world deployment of such systems. To address this gap, we present \textbf{HeteroHub}, a data-centric framework that integrates static metadata, task-aligned training corpora, and real-time data streams. The framework supports task-aware model training, context-sensitive execution, and closed-loop control driven by real-world feedback. In our demonstration, HeteroHub successfully coordinates multiple embodied AI agents to execute complex tasks, illustrating how a robust data management framework can enable scalable, maintainable, and evolvable embodied AI systems.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Unlabeled Cross-Center Automatic Analysis for TAAD: An Integrated Framework from Segmentation to Clinical Features
arXiv:2603.26019v1 Announce Type: cross
Abstract: Type A Aortic Dissection (TAAD) is a life-threatening cardiovascular emergency that demands rapid and precise preoperative evaluation. While key anatomical and pathological features are decisive for surgical planning, current research focuses predominantly on improving segmentation accuracy, leaving the reliable, quantitative extraction of clinically actionable features largely under-explored. Furthermore, constructing comprehensive TAAD datasets requires labor-intensive, expert level pixel-wise annotations, which is impractical for most clinical institutions. Due to significant domain shift, models trained on a single center dataset also suffer from severe performance degradation during cross-institutional deployment. This study addresses a clinically critical challenge: the accurate extraction of key TAAD clinical features during cross-institutional deployment in the total absence of target-domain annotations. To this end, we propose an unsupervised domain adaptation (UDA)-driven framework for the automated extraction of TAAD clinical features. The framework leverages limited source-domain labels while effectively adapting to unlabeled data from target domains. Tailored for real-world emergency workflows, our framework aims to achieve stable cross-institutional multi-class segmentation, reliable and quantifiable clinical feature extraction, and practical deployability independent of high-cost annotations. Extensive experiments demonstrate that our method significantly improves cross-domain segmentation performance compared to existing state-of-the-art approaches. More importantly, a reader study involving multiple cardiovascular surgeons confirms that the automatically extracted clinical features provide meaningful assistance for preoperative assessment, highlighting the practical utility of the proposed end-to-end segmentation-to-feature pipeline.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Methods for Knowledge Graph Construction from Text Collections: Development and Applications
arXiv:2603.25862v1 Announce Type: cross
Abstract: Virtually every sector of society is experiencing a dramatic growth in the volume of unstructured textual data that is generated and published, from news and social media online interactions, through open access scholarly communications and observational data in the form of digital health records and online drug reviews. The volume and variety of data across all this range of domains has created both unprecedented opportunities and pressing challenges for extracting actionable knowledge for several application scenarios. However, the extraction of rich semantic knowledge demands the deployment of scalable and flexible automatic methods adaptable across text genres and schema specifications. Moreover, the full potential of these data can only be unlocked by coupling information extraction methods with Semantic Web techniques for the construction of full-fledged Knowledge Graphs, that are semantically transparent, explainable by design and interoperable. In this thesis, we experiment with the application of Natural Language Processing, Machine Learning and Generative AI methods, powered by Semantic Web best practices, to the automatic construction of Knowledge Graphs from large text corpora, in three use case applications: the analysis of the Digital Transformation discourse in the global news and social media platforms; the mapping and trend analysis of recent research in the Architecture, Engineering, Construction and Operations domain from a large corpus of publications; the generation of causal relation graphs of biomedical entities from electronic health records and patient-authored drug reviews. The contributions of this thesis to the research community are in terms of benchmark evaluation results, the design of customized algorithms and the creation of data resources in the form of Knowledge Graphs, together with data analysis results built on top of them.
Fonte: arXiv cs.AI
NLP/LLMs • Score 90
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models
arXiv:2603.26164v1 Announce Type: new
Abstract: Data-centric training has emerged as a promising direction for improving large language models (LLMs) by optimizing not only model parameters but also the selection, composition, and weighting of training data during optimization. However, existing approaches to data selection, data mixture optimization, and data reweighting are often developed in isolated codebases with inconsistent interfaces, hindering reproducibility, fair comparison, and practical integration. In this paper, we present DataFlex, a unified data-centric dynamic training framework built upon LLaMA-Factory. DataFlex supports three major paradigms of dynamic data optimization: sample selection, domain mixture adjustment, and sample reweighting, while remaining fully compatible with the original training workflow. It provides extensible trainer abstractions and modular components, enabling a drop-in replacement for standard LLM training, and unifies key model-dependent operations such as embedding extraction, inference, and gradient computation, with support for large-scale settings including DeepSpeed ZeRO-3. We conduct comprehensive experiments across multiple data-centric methods. Dynamic data selection consistently outperforms static full-data training on MMLU across both Mistral-7B and Llama-3.2-3B. For data mixture, DoReMi and ODM improve both MMLU accuracy and corpus-level perplexity over default proportions when pretraining Qwen2.5-1.5B on SlimPajama at 6B and 30B token scales. DataFlex also achieves consistent runtime improvements over original implementations. These results demonstrate that DataFlex provides an effective, efficient, and reproducible infrastructure for data-centric dynamic training of LLMs.
Fonte: arXiv cs.LG
Applications • Score 85
A Lightweight, Transferable, and Self-Adaptive Framework for Intelligent DC Arc-Fault Detection in Photovoltaic Systems
arXiv:2603.25749v1 Announce Type: cross
Abstract: Arc-fault circuit interrupters (AFCIs) are essential for mitigating fire hazards in residential photovoltaic (PV) systems, yet achieving reliable DC arc-fault detection under real-world conditions remains challenging. Spectral interference from inverter switching, hardware heterogeneity, operating-condition drift, and environmental noise collectively compromise conventional AFCI solutions. This paper proposes a lightweight, transferable, and self-adaptive learning-driven framework (LD-framework) for intelligent DC arc-fault detection. At the device level, LD-Spec learns compact spectral representations enabling efficient on-device inference and near-perfect arc discrimination. Across heterogeneous inverter platforms, LD-Align performs cross-hardware representation alignment to ensure robust detection despite hardware-induced distribution shifts. To address long-term evolution, LD-Adapt introduces a cloud-edge collaborative self-adaptive updating mechanism that detects unseen operating regimes and performs controlled model evolution. Extensive experiments involving over 53,000 labeled samples demonstrate near-perfect detection, achieving 0.9999 accuracy and 0.9996 F1-score. Across diverse nuisance-trip-prone conditions, including inverter start-up, grid transitions, load switching, and harmonic disturbances, the method achieves a 0% false-trip rate. Cross-hardware transfer shows reliable adaptation using only 0.5%-1% labeled target data while preserving source performance. Field adaptation experiments demonstrate recovery of detection precision from 21% to 95% under previously unseen conditions. These results indicate that the LD-framework enables a scalable, deployment-oriented AFCI solution maintaining highly reliable detection across heterogeneous devices and long-term operation.
Fonte: arXiv cs.AI
Applications • Score 85
Challenges and opportunities for AI to help deliver fusion energy
arXiv:2603.25777v1 Announce Type: cross
Abstract: There is great potential for the application of AI tools in fusion research, and substantial worldwide benefit if fusion power is realised. However, using AI comes with its own challenges, many of which can be mitigated if responsible and robust methodologies are built into existing approaches. To do that requires close, long-term collaborations between fusion domain experts and AI developers and awareness of the fact that not all problems in fusion research are best tackled with AI tools. In April 2025, experts from academia, industry, UKAEA and STFC discussed how AI can be used to advance R&D in fusion energy at the first edition of The Economist FusionFest event. This Perspective is an expanded and updated summary of the round table discussion, providing more context and examples.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
MAGNET: Autonomous Expert Model Generation via Decentralized Autoresearch and BitNet Training
arXiv:2603.25813v1 Announce Type: cross
Abstract: We present MAGNET (Model Autonomously Growing Network), a decentralized system for autonomous generation, training, and serving of domain-expert language models across commodity hardware. MAGNET integrates four components: (1) autoresearch, an autonomous ML research pipeline that automates dataset generation, hyperparameter exploration, evaluation, and error-driven iteration; (2) BitNet b1.58 ternary training, enabling CPU-native inference via bitnet.cpp without GPU hardware; (3) DiLoCo-based distributed merging for communication-efficient aggregation of domain specialists; and (4) on-chain contribution tracking on the HOOTi EVM chain. We validate autoresearch through three case studies: video safety classification (balanced accuracy 0.9287 to 0.9851), cryptocurrency directional prediction (41% to 54.9% hit rate), and BitNet hyperparameter optimization (10-phase sweep, -16.7% validation loss).
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
DRiffusion: Draft-and-Refine Process Parallelizes Diffusion Models with Ease
arXiv:2603.25872v1 Announce Type: new
Abstract: Diffusion models have achieved remarkable success in generating high-fidelity content but suffer from slow, iterative sampling, resulting in high latency that limits their use in interactive applications. We introduce DRiffusion, a parallel sampling framework that parallelizes diffusion inference through a draft-and-refine process. DRiffusion employs skip transitions to generate multiple draft states for future timesteps and computes their corresponding noises in parallel, which are then used in the standard denoising process to produce refined results. Theoretically, our method achieves an acceleration rate of $\tfrac{1}{n}$ or $\tfrac{2}{n+1}$, depending on whether the conservative or aggressive mode is used, where $n$ denotes the number of devices. Empirically, DRiffusion attains 1.4$\times$-3.7$\times$ speedup across multiple diffusion models while incur minimal degradation in generation quality: on MS-COCO dataset, both FID and CLIP remain largely on par with those of the original model, while PickScore and HPSv2.1 show only minor average drops of 0.17 and 0.43, respectively. These results verify that DRiffusion delivers substantial acceleration and preserves perceptual quality.
Fonte: arXiv cs.LG
Applications • Score 85
Data-Driven Plasticity Modeling via Acoustic Profiling
arXiv:2603.25894v1 Announce Type: new
Abstract: This paper presents a data-driven framework for modeling plastic deformation in crystalline metals through acoustic emission (AE) analysis. Building on experimental data from compressive loading of nickel micropillars, the study introduces a wavelet-based method using Morlet transforms to detect AE events across distinct frequency bands, enabling identification of both large and previously overlooked small-scale events. The detected events are validated against stress-drop dynamics, demonstrating strong physical consistency and revealing a relationship between AE energy release and strain evolution, including the onset of increased strain rate following major events. Leveraging labeled datasets of events and non-events, the work applies machine learning techniques, showing that engineered time and frequency domain features significantly outperform raw signal classifiers, and identifies key discriminative features such as RMS amplitude, zero crossing rate, and spectral centroid. Finally, clustering analysis uncovers four distinct AE event archetypes corresponding to different deformation mechanisms, highlighting the potential for transitioning from retrospective analysis to predictive modeling of material behavior using acoustic signals.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Policy-Guided World Model Planning for Language-Conditioned Visual Navigation
arXiv:2603.25981v1 Announce Type: cross
Abstract: Navigating to a visually specified goal given natural language instructions remains a fundamental challenge in embodied AI. Existing approaches either rely on reactive policies that struggle with long-horizon planning, or employ world models that suffer from poor action initialization in high-dimensional spaces. We present PiJEPA, a two-stage framework that combines the strengths of learned navigation policies with latent world model planning for instruction-conditioned visual navigation. In the first stage, we finetune an Octo-based generalist policy, augmented with a frozen pretrained vision encoder (DINOv2 or V-JEPA-2), on the CAST navigation dataset to produce an informed action distribution conditioned on the current observation and language instruction. In the second stage, we use this policy-derived distribution to warm-start Model Predictive Path Integral (MPPI) planning over a separately trained JEPA world model, which predicts future latent states in the embedding space of the same frozen encoder. By initializing the MPPI sampling distribution from the policy prior rather than from an uninformed Gaussian, our planner converges faster to high-quality action sequences that reach the goal. We systematically study the effect of the vision encoder backbone, comparing DINOv2 and V-JEPA-2, across both the policy and world model components. Experiments on real-world navigation tasks demonstrate that PiJEPA significantly outperforms both standalone policy execution and uninformed world model planning, achieving improved goal-reaching accuracy and instruction-following fidelity.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
On Integrating Resilience and Human Oversight into LLM-Assisted Modeling Workflows for Digital Twins
arXiv:2603.25898v1 Announce Type: cross
Abstract: LLM-assisted modeling holds the potential to rapidly build executable Digital Twins of complex systems from only coarse descriptions and sensor data. However, resilience to LLM hallucination, human oversight, and real-time model adaptability remain challenging and often mutually conflicting requirements. We present three critical design principles for integrating resilience and oversight into such workflows, derived from insights gained through our work on FactoryFlow - an open-source LLM-assisted framework for building simulation-based Digital Twins of manufacturing systems. First, orthogonalize structural modeling and parameter fitting. Structural descriptions (components, interconnections) are LLM-translated from coarse natural language to an intermediate representation with human visualization and validation, which is algorithmically converted to the final model. Parameter inference, in contrast, operates continuously on sensor data streams with expert-tunable controls. Second, restrict the model IR to interconnections of parameterized, pre-validated library components rather than monolithic simulation code, enabling interpretability and error-resilience. Third, and most important, is to use a density-preserving IR. When IR descriptions expand dramatically from compact inputs hallucination errors accumulate proportionally. We present the case for Python as a density-preserving IR : loops express regularity compactly, classes capture hierarchy and composition, and the result remains highly readable while exploiting LLMs strong code generation capabilities. A key contribution is detailed characterization of LLM-induced errors across model descriptions of varying detail and complexity, revealing how IR choice critically impacts error rates. These insights provide actionable guidance for building resilient and transparent LLM-assisted simulation automation workflows.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
Second-Order, First-Class: A Composable Stack for Curvature-Aware Training
arXiv:2603.25976v1 Announce Type: new
Abstract: Second-order methods promise improved stability and faster convergence, yet they remain underused due to implementation overhead, tuning brittleness, and the lack of composable APIs. We introduce Somax, a composable Optax-native stack that treats curvature-aware training as a single JIT-compiled step governed by a static plan. Somax exposes first-class modules -- curvature operators, estimators, linear solvers, preconditioners, and damping policies -- behind a single step interface and composes with Optax by applying standard gradient transformations (e.g., momentum, weight decay, schedules) to the computed direction. This design makes typically hidden choices explicit and swappable. Somax separates planning from execution: it derives a static plan (including cadences) from module requirements, then runs the step through a specialized execution path that reuses intermediate results across modules. We report system-oriented ablations showing that (i) composition choices materially affect scaling behavior and time-to-accuracy, and (ii) planning reduces per-step overhead relative to unplanned composition with redundant recomputation.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
SocialX: A Modular Platform for Multi-Source Big Data Research in Indonesia
arXiv:2603.26253v1 Announce Type: new
Abstract: Big data research in Indonesia is constrained by a fundamental fragmentation: relevant data is scattered across social media, news portals, e-commerce platforms, review sites, and academic databases, each with different formats, access methods, and noise characteristics. Researchers must independently build collection pipelines, clean heterogeneous data, and assemble separate analysis tools, a process that often overshadows the research itself. We present SocialX, a modular platform for multi-source big data research that integrates heterogeneous data collection, language-aware preprocessing, and pluggable analysis into a unified, source-agnostic pipeline. The platform separates concerns into three independent layers (collection, preprocessing, and analysis) connected by a lightweight job-coordination mechanism. This modularity allows each layer to grow independently: new data sources, preprocessing methods, or analysis tools can be added without modifying the existing pipeline. We describe the design principles that enable this extensibility, detail the preprocessing methodology that addresses challenges specific to Indonesian text across registers, and demonstrate the platform's utility through a walkthrough of a typical research workflow. SocialX is publicly accessible as a web-based platform at https://www.socialx.id.
Fonte: arXiv cs.CL
Privacy/Security/Fairness • Score 85
CANGuard: A Spatio-Temporal CNN-GRU-Attention Hybrid Architecture for Intrusion Detection in In-Vehicle CAN Networks
arXiv:2603.25763v1 Announce Type: cross
Abstract: The Internet of Vehicles (IoV) has become an essential component of smart transportation systems, enabling seamless interaction among vehicles and infrastructure. In recent years, it has played a progressively significant role in enhancing mobility, safety, and transportation efficiency. However, this connectivity introduces severe security vulnerabilities, particularly Denial-of-Service (DoS) and spoofing attacks targeting the Controller Area Network (CAN) bus, which could severely inhibit communication between the critical components of a vehicle, leading to system malfunctions, loss of control, or even endangering passengers' safety. To address this problem, this paper presents CANGuard, a novel spatio-temporal deep learning architecture that combines Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), and an attention mechanism to effectively identify such attacks. The model is trained and evaluated on the CICIoV2024 dataset, achieving competitive performance across accuracy, precision, recall, and F1-score and outperforming existing state-of-the-art methods. A comprehensive ablation study confirms the individual and combined contributions of the CNN, GRU, and attention components. Additionally, a SHAP analysis is conducted to interpret the decision-making process of the model and determine which features have the most significant impact on intrusion detection. The proposed approach demonstrates strong potential for practical and scalable security enhancements in modern IoV environments, thereby ensuring safer and more secure CAN bus communications.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Semi-Automated Knowledge Engineering and Process Mapping for Total Airport Management
arXiv:2603.26076v1 Announce Type: new
Abstract: Documentation of airport operations is inherently complex due to extensive technical terminology, rigorous regulations, proprietary regional information, and fragmented communication across multiple stakeholders. The resulting data silos and semantic inconsistencies present a significant impediment to the Total Airport Management (TAM) initiative. This paper presents a methodological framework for constructing a domain-grounded, machine-readable Knowledge Graph (KG) through a dual-stage fusion of symbolic Knowledge Engineering (KE) and generative Large Language Models (LLMs).
The framework employs a scaffolded fusion strategy in which expert-curated KE structures guide LLM prompts to facilitate the discovery of semantically aligned knowledge triples. We evaluate this methodology on the Google LangExtract library and investigate the impact of context window utilization by comparing localized segment-based inference with document-level processing. Contrary to prior empirical observations of long-context degradation in LLMs, document-level processing improves the recovery of non-linear procedural dependencies.
To ensure the high-fidelity provenance required in airport operations, the proposed framework fuses a probabilistic model for discovery and a deterministic algorithm for anchoring every extraction to its ground source. This ensures absolute traceability and verifiability, bridging the gap between "black-box" generative outputs and the transparency required for operational tooling. Finally, we introduce an automated framework that operationalizes this pipeline to synthesize complex operational workflows from unstructured textual corpora.
Fonte: arXiv cs.AI
Vision • Score 85
GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation
arXiv:2603.26266v1 Announce Type: new
Abstract: Large vision-language models have endowed GUI agents with strong general capabilities for interface understanding and interaction. However, due to insufficient exposure to domain-specific software operation data during training, these agents exhibit significant domain bias - they lack familiarity with the specific operation workflows (planning) and UI element layouts (grounding) of particular applications, limiting their real-world task performance. In this paper, we present GUIDE (GUI Unbiasing via Instructional-Video Driven Expertise), a training-free, plug-and-play framework that resolves GUI agent domain bias by autonomously acquiring domain-specific expertise from web tutorial videos through a retrieval-augmented automated annotation pipeline. GUIDE introduces two key innovations. First, a subtitle-driven Video-RAG pipeline unlocks video semantics through subtitle analysis, performing progressive three-stage retrieval - domain classification, topic extraction, and relevance matching - to identify task-relevant tutorial videos. Second, a fully automated annotation pipeline built on an inverse dynamics paradigm feeds consecutive keyframes enhanced with UI element detection into VLMs, inferring the required planning and grounding knowledge that are injected into the agent's corresponding modules to address both manifestations of domain bias. Extensive experiments on OSWorld demonstrate GUIDE's generality as a plug-and-play component for both multi-agent systems and single-model agents. It consistently yields over 5% improvements and reduces execution steps - without modifying any model parameters or architecture - validating GUIDE as an architecture-agnostic enhancement to bridge GUI agent domain bias.
Fonte: arXiv cs.AI
Vision • Score 85
ETA-VLA: Efficient Token Adaptation via Temporal Fusion and Intra-LLM Sparsification for Vision-Language-Action Models
arXiv:2603.25766v1 Announce Type: cross
Abstract: The integration of Vision-Language-Action (VLA) models into autonomous driving systems offers a unified framework for interpreting complex scenes and executing control commands. However, the necessity to incorporate historical multi-view frames for accurate temporal reasoning imposes a severe computational burden, primarily driven by the quadratic complexity of self-attention mechanisms in Large Language Models (LLMs). To alleviate this bottleneck, we propose ETA-VLA, an Efficient Token Adaptation framework for VLA models. ETA-VLA processes the past $n$ frames of multi-view images and introduces a novel Intra-LLM Sparse Aggregator (ILSA). Drawing inspiration from human driver attention allocation, ILSA dynamically identifies and prunes redundant visual tokens guided by textual queries and temporal consistency. Specifically, we utilize a text-guided scoring mechanism alongside a diversity-preserving sparsification strategy to select a sparse subset of critical tokens, ensuring comprehensive awareness of the driving scene. Extensive experiments on the NAVSIM v2 demonstrate that ETA-VLA achieves driving performance comparable to state-of-the-art baselines while reducing computational FLOPs by approximately 32\%. Notably, our method prunes 85% of visual tokens and reduces inference FLOPs by 61\%, but still retaining 94% of the original accuracy on the NAVSIM v2 benchmark.
Fonte: arXiv cs.AI
NLP/LLMs • Score 95
CADSmith: Multi-Agent CAD Generation with Programmatic Geometric Validation
arXiv:2603.26512v1 Announce Type: new
Abstract: Existing methods for text-to-CAD generation either operate in a single pass with no geometric verification or rely on lossy visual feedback that cannot resolve dimensional errors. We present CADSmith, a multi-agent pipeline that generates CadQuery code from natural language. It then undergoes an iterative refinement process through two nested correction loops: an inner loop that resolves execution errors and an outer loop grounded in programmatic geometric validation. The outer loop combines exact measurements from the OpenCASCADE kernel (bounding box dimensions, volume, solid validity) with holistic visual assessment from an independent vision-language model Judge. This provides both the numerical precision and the high-level shape awareness needed to converge on the correct geometry. The system uses retrieval-augmented generation over API documentation rather than fine-tuning, maintaining a current database as the underlying CAD library evolves. We evaluate on a custom benchmark of 100 prompts in three difficulty tiers (T1 through T3) with three ablation configurations. Against a zero-shot baseline, CADSmith achieves a 100% execution rate (up from 95%), improves the median F1 score from 0.9707 to 0.9846, the median IoU from 0.8085 to 0.9629, and reduces the mean Chamfer Distance from 28.37 to 0.74, demonstrating that closed-loop refinement with programmatic geometric feedback substantially improves the quality and reliability of LLM-generated CAD models.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
Bayesian Optimization on Networks
arXiv:2510.27643v2 Announce Type: replace
Abstract: This paper studies optimization on networks modeled as metric graphs. Motivated by applications where the objective function is expensive to evaluate or only available as a black box, we develop Bayesian optimization algorithms that sequentially update a Gaussian process surrogate model of the objective to guide the acquisition of query points. To ensure that the surrogates are tailored to the network's geometry, we adopt Whittle-Mat\'ern Gaussian process prior models defined via stochastic partial differential equations on metric graphs. In addition to establishing regret bounds for optimizing sufficiently smooth objective functions, we analyze the practical case in which the smoothness of the objective is unknown and the Whittle-Mat\'ern prior is represented using finite elements. Numerical results demonstrate the effectiveness of our algorithms for optimizing benchmark objective functions on a synthetic metric graph and for Bayesian inversion via maximum a posteriori estimation on a telecommunication network.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
MemBoost: A Memory-Boosted Framework for Cost-Aware LLM Inference
arXiv:2603.26557v1 Announce Type: new
Abstract: Large Language Models (LLMs) deliver strong performance but incur high inference cost in real-world services, especially under workloads with repeated or near-duplicate queries across users and sessions. In this work, we propose MemBoost, a memory-boosted LLM serving framework that enables a lightweight model to reuse previously generated answers and retrieve relevant supporting information for cheap inference, while selectively escalating difficult or uncertain queries to a stronger model. Unlike standard retrieval-augmented generation, which primarily grounds a single response, MemBoost is designed for interactive settings by supporting answer reuse, continual memory growth, and cost-aware routing. Experiments across multiple models under simulated workloads show that MemBoost substantially reduces expensive large-model invocations and overall inference cost, while maintaining high answer quality comparable to the strong model baseline.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
AutoB2G: A Large Language Model-Driven Agentic Framework For Automated Building-Grid Co-Simulation
arXiv:2603.26005v1 Announce Type: new
Abstract: The growing availability of building operational data motivates the use of reinforcement learning (RL), which can learn control policies directly from data and cope with the complexity and uncertainty of large-scale building clusters. However, most existing simulation environments prioritize building-side performance metrics and lack systematic evaluation of grid-level impacts, while their experimental workflows still rely heavily on manual configuration and substantial programming expertise. Therefore, this paper proposes AutoB2G, an automated building-grid co-simulation framework that completes the entire simulation workflow solely based on natural-language task descriptions. The framework extends CityLearn V2 to support Building-to-Grid (B2G) interaction and adopts the large language model (LLM)-based SOCIA (Simulation Orchestration for Computational Intelligence with Agents) framework to automatically generate, execute, and iteratively refine the simulator. As LLMs lack prior knowledge of the implementation context of simulation functions, a codebase covering simulation configurations and functional modules is constructed and organized as a directed acyclic graph (DAG) to explicitly represent module dependencies and execution order, guiding the LLM to retrieve a complete executable path. Experimental results demonstrate that AutoB2G can effectively enable automated simulator implementations, coordinating B2G interactions to improve grid-side performance metrics.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
AIRA_2: Overcoming Bottlenecks in AI Research Agents
arXiv:2603.26499v1 Announce Type: new
Abstract: Existing research has identified three structural performance bottlenecks in AI research agents: (1) synchronous single-GPU execution constrains sample throughput, limiting the benefit of search; (2) a generalization gap where validation-based selection causes performance to degrade over extended search horizons; and (3) the limited capability of fixed, single-turn LLM operators imposes a ceiling on search performance. We introduce AIRA$_2$, which addresses these bottlenecks through three architectural choices: an asynchronous multi-GPU worker pool that increases experiment throughput linearly; a Hidden Consistent Evaluation protocol that delivers a reliable evaluation signal; and ReAct agents that dynamically scope their actions and debug interactively. On MLE-bench-30, AIRA$_2$ achieves a mean Percentile Rank of 71.8% at 24 hours - surpassing the previous best of 69.9% - and steadily improves to 76.0% at 72 hours. Ablation studies reveal that each component is necessary and that the "overfitting" reported in prior work was driven by evaluation noise rather than true data memorization.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
TinyML for Acoustic Anomaly Detection in IoT Sensor Networks
arXiv:2603.26135v1 Announce Type: new
Abstract: Tiny Machine Learning enables real-time, energy-efficient data processing directly on microcontrollers, making it ideal for Internet of Things sensor networks. This paper presents a compact TinyML pipeline for detecting anomalies in environmental sound within IoT sensor networks. Acoustic monitoring in IoT systems can enhance safety and context awareness, yet cloud-based processing introduces challenges related to latency, power usage, and privacy. Our pipeline addresses these issues by extracting Mel Frequency Cepstral Coefficients from sound signals and training a lightweight neural network classifier optimized for deployment on edge devices. The model was trained and evaluated using the UrbanSound8K dataset, achieving a test accuracy of 91% and balanced F1-scores of 0.91 across both normal and anomalous sound classes. These results demonstrate the feasibility and reliability of embedded acoustic anomaly detection for scalable and responsive IoT deployments.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
AgentCollab: A Self-Evaluation-Driven Collaboration Paradigm for Efficient LLM Agents
arXiv:2603.26034v1 Announce Type: new
Abstract: Autonomous agents powered by large language models (LLMs) perform complex tasks through long-horizon reasoning and tool interaction, where a fundamental trade-off arises between execution efficiency and reasoning robustness. Models at different capability-cost levels offer complementary advantages: lower-cost models enable fast execution but may struggle on difficult reasoning segments, while stronger models provide more robust reasoning at higher computational cost. We present AgentCollab, a self-driven collaborative inference framework that dynamically coordinates models with different reasoning capacities during agent execution. Instead of relying on external routing modules, the framework uses the agent's own self-reflection signal to determine whether the current reasoning trajectory is making meaningful progress, and escalates control to a stronger reasoning tier only when necessary. To further stabilize long-horizon execution, we introduce a difficulty-aware cumulative escalation strategy that allocates additional reasoning budget based on recent failure signals. In our experiments, we instantiate this framework using a two-level small-large model setting. Experiments on diverse multi-step agent benchmarks show that AgentCollab consistently improves the accuracy-efficiency Pareto frontier of LLM agents.
Fonte: arXiv cs.CL
Theory/Optimization • Score 85
Vecchia-Inducing-Points Full-Scale Approximations for Gaussian Processes
arXiv:2507.05064v3 Announce Type: replace
Abstract: Gaussian processes are flexible, probabilistic, non-parametric models widely used in machine learning and statistics. However, their scalability to large data sets is limited by computational constraints. To overcome these challenges, we propose Vecchia-inducing-points full-scale (VIF) approximations combining the strengths of global inducing points and local Vecchia approximations. Vecchia approximations excel in settings with low-dimensional inputs and moderately smooth covariance functions, while inducing point methods are better suited to high-dimensional inputs and smoother covariance functions. Our VIF approach bridges these two regimes by using an efficient correlation-based neighbor-finding strategy for the Vecchia approximation of the residual process, implemented via a modified cover tree algorithm. We further extend our framework to non-Gaussian likelihoods by introducing iterative methods that substantially reduce computational costs for training and prediction by several orders of magnitudes compared to Cholesky-based computations when using a Laplace approximation. In particular, we propose and compare novel preconditioners and provide theoretical convergence results. Extensive numerical experiments on simulated and real-world data sets show that VIF approximations are both computationally efficient as well as more accurate and numerically stable than state-of-the-art alternatives. All methods are implemented in the open source C++ library GPBoost with high-level Python and R interfaces.
Fonte: arXiv stat.ML
MLOps/Systems • Score 85
PruneFuse: Efficient Data Selection via Weight Pruning and Network Fusion
arXiv:2603.26138v1 Announce Type: new
Abstract: Efficient data selection is crucial for enhancing the training efficiency of deep neural networks and minimizing annotation requirements. Traditional methods often face high computational costs, limiting their scalability and practical use. We introduce PruneFuse, a novel strategy that leverages pruned networks for data selection and later fuses them with the original network to optimize training. PruneFuse operates in two stages: First, it applies structured pruning to create a smaller pruned network that, due to its structural coherence with the original network, is well-suited for the data selection task. This small network is then trained and selects the most informative samples from the dataset. Second, the trained pruned network is seamlessly fused with the original network. This integration leverages the insights gained during the training of the pruned network to facilitate the learning process of the fused network while leaving room for the network to discover more robust solutions. Extensive experimentation on various datasets demonstrates that PruneFuse significantly reduces computational costs for data selection, achieves better performance than baselines, and accelerates the overall training process.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Constitutive parameterized deep energy method for solid mechanics problems with random material parameters
arXiv:2603.26030v1 Announce Type: new
Abstract: In practical structural design and solid mechanics simulations, material properties inherently exhibit random variations within bounded intervals. However, evaluating mechanical responses under continuous material uncertainty remains a persistent challenge. Traditional numerical approaches, such as the Finite Element Method (FEM), incur prohibitive computational costs as they require repeated mesh discretization and equation solving for every parametric realization. Similarly, data-driven surrogate models depend heavily on massive, high-fidelity datasets, while standard physics-informed frameworks (e.g., the Deep Energy Method) strictly demand complete retraining from scratch whenever material parameters change. To bridge this critical gap, we propose the Constitutive Parameterized Deep Energy Method (CPDEM). In this purely physics-driven framework, the strain energy density functional is reformulated by encoding a latent representation of stochastic constitutive parameters. By embedding material parameters directly into the neural network alongside spatial coordinates, CPDEM transforms conventional spatial collocation points into parameter-aware material points. Trained in an unsupervised manner via expected energy minimization over the parameter domain, the pre-trained model continuously learns the solution manifold. Consequently, it enables zero-shot, real-time inference of displacement fields for unknown material parameters without requiring any dataset generation or model retraining. The proposed method is rigorously validated across diverse benchmarks, including linear elasticity, finite-strain hyperelasticity, and complex highly nonlinear contact mechanics. To the best of our knowledge, CPDEM represents the first purely physics-driven deep learning paradigm capable of simultaneously and efficiently handling continuous multi-parameter variations in solid mechanics.
Fonte: arXiv cs.LG
NLP/LLMs • Score 75
Online Learning for Dynamic Constellation Topologies
arXiv:2603.25954v1 Announce Type: new
Abstract: The use of satellite networks has increased significantly in recent years due to their advantages over purely terrestrial systems, such as higher availability and coverage. However, to effectively provide these services, satellite networks must cope with the continuous orbital movement and maneuvering of their nodes and the impact on the network's topology. In this work, we address the problem of (dynamic) network topology configuration under the online learning framework. As a byproduct, our approach does not assume structure about the network, such as known orbital planes (that could be violated by maneuvering satellites). We empirically demonstrate that our problem formulation matches the performance of state-of-the-art offline methods. Importantly, we demonstrate that our approach is amenable to constrained online learning, exhibiting a trade-off between computational complexity per iteration and convergence to a final strategy.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Preventing Data Leakage in EEG-Based Survival Prediction: A Two-Stage Embedding and Transformer Framework
arXiv:2603.25923v1 Announce Type: new
Abstract: Deep learning models have shown promise in EEG-based outcome prediction for comatose patients after cardiac arrest, but their reliability is often compromised by subtle forms of data leakage. In particular, when long EEG recordings are segmented into short windows and reused across multiple training stages, models may implicitly encode and propagate label information, leading to overly optimistic validation performance and poor generalization.
In this study, we identify a previously overlooked form of data leakage in multi-stage EEG modeling pipelines. We demonstrate that violating strict patient-level separation can significantly inflate validation metrics while causing substantial degradation on independent test data.
To address this issue, we propose a leakage-aware two-stage framework. In the first stage, short EEG segments are transformed into embedding representations using a convolutional neural network with an ArcFace objective. In the second stage, a Transformer-based model aggregates these embeddings to produce patient-level predictions, with strict isolation between training cohorts to eliminate leakage pathways.
Experiments on a large-scale EEG dataset of post-cardiac-arrest patients show that the proposed framework achieves stable and generalizable performance under clinically relevant constraints, particularly in maintaining high sensitivity at stringent specificity thresholds. These results highlight the importance of rigorous data partitioning and provide a practical solution for reliable EEG-based outcome prediction.
Fonte: arXiv cs.LG
RL • Score 85
Neuro-Cognitive Reward Modeling for Human-Centered Autonomous Vehicle Control
arXiv:2603.25968v1 Announce Type: new
Abstract: Recent advancements in computer vision have accelerated the development of autonomous driving. Despite these advancements, training machines to drive in a way that aligns with human expectations remains a significant challenge. Human factors are still essential, as humans possess a sophisticated cognitive system capable of rapidly interpreting scene information and making accurate decisions. Aligning machine with human intent has been explored with Reinforcement Learning with Human Feedback (RLHF). Conventional RLHF methods rely on collecting human preference data by manually ranking generated outputs, which is time-consuming and indirect. In this work, we propose an electroencephalography (EEG)-guided decision-making framework to incorporate human cognitive insights without behaviour response interruption into reinforcement learning (RL) for autonomous driving. We collected EEG signals from 20 participants in a realistic driving simulator and analyzed event-related potentials (ERP) in response to sudden environmental changes. Our proposed framework employs a neural network to predict the strength of ERP based on the cognitive information from visual scene information. Moreover, we explore the integration of such cognitive information into the reward signal of the RL algorithm. Experimental results show that our framework can improve the collision avoidance ability of the RL algorithm, highlighting the potential of neuro-cognitive feedback in enhancing autonomous driving systems. Our project page is: https://alex95gogo.github.io/Cognitive-Reward/.
Fonte: arXiv cs.CV
Applications • Score 85
Personalizing Mathematical Game-based Learning for Children: A Preliminary Study
arXiv:2603.25925v1 Announce Type: new
Abstract: Game-based learning (GBL) is widely adopted in mathematics education. It enhances learners' engagement and critical thinking throughout the mathematics learning process. However, enabling players to learn intrinsically through mathematical games still presents challenges. In particular, effective GBL systems require dozens of high-quality game levels and mechanisms to deliver them to appropriate players in a way that matches their learning abilities. To address this challenge, we propose a framework, guided by adaptive learning theory, that uses artificial intelligence (AI) techniques to build a classifier for player-generated levels. We collect 206 distinct game levels created by both experts and advanced players in Creative Mode, a new tool in a math game-based learning app, and develop a classifier to extract game features and predict valid game levels. The preliminary results show that the Random Forest model is the optimal classifier among the four machine learning classification models (k-nearest neighbors, decision trees, support vector machines, and random forests). This study provides insights into the development of GBL systems, highlighting the potential of integrating AI into the game-level design process to provide more personalized game levels for players.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
Optimization Trade-offs in Asynchronous Federated Learning: A Stochastic Networks Approach
arXiv:2603.26231v1 Announce Type: new
Abstract: Synchronous federated learning scales poorly due to the straggler effect. Asynchronous algorithms increase the update throughput by processing updates upon arrival, but they introduce two fundamental challenges: gradient staleness, which degrades convergence, and bias toward faster clients under heterogeneous data distributions. Although algorithms such as AsyncSGD and Generalized AsyncSGD mitigate this bias via client-side task queues, most existing analyses neglect the underlying queueing dynamics and lack closed-form characterizations of the update throughput and gradient staleness. To close this gap, we develop a stochastic queueing-network framework for Generalized AsyncSGD that jointly models random computation times at the clients and the central server, as well as random uplink and downlink communication delays. Leveraging product-form network theory, we derive a closed-form expression for the update throughput, alongside closed-form upper bounds for both the communication round complexity and the expected wall-clock time required to reach an $\epsilon$-stationary point. These results formally characterize the trade-off between gradient staleness and wall-clock convergence speed. We further extend the framework to quantify energy consumption under stochastic timing, revealing an additional trade-off between convergence speed and energy efficiency. Building on these analytical results, we propose gradient-based optimization strategies to jointly optimize routing and concurrency. Experiments on EMNIST demonstrate reductions of 29%--46% in convergence time and 36%--49% in energy consumption compared to AsyncSGD.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
UCAgent: An End-to-End Agent for Block-Level Functional Verification
arXiv:2603.25768v1 Announce Type: cross
Abstract: Functional verification remains a critical bottleneck in modern IC development cycles, accounting for approximately 70% of total development time in many projects. However, traditional methods, including constrained-random and formal verification, struggle to keep pace with the growing complexity of modern semiconductor designs.
While recent advances in Large Language Models (LLMs) have shown promise in code generation and task automation, significant challenges hinder the realization of end-to-end functional verification automation. These challenges include (i) limited accuracy in generating Verilog/SystemVerilog verification code, (ii) the fragility of LLMs when executing complex, multi-step verification workflows, and (iii) the difficulty of maintaining verification consistency across specifications, coverage models, and test cases throughout the workflow.
To address these challenges, we propose UCAgent, an end-to-end agent that automates hardware block-level functional verification based on three core mechanisms. First, we establish a pure Python verification environment using Picker and Toffee to avoid relying on LLM-generated SystemVerilog verification code. Second, we introduce a configurable 31-stage fine-grained verification workflow to guide the LLM, where each stage is verified by an automated checker. Furthermore, we propose a Verification Consistency Labeling Mechanism (VCLM) that assigns hierarchical labels to LLM-generated artifacts, improving the reliability and traceability of verification.
Experimental results show that UCAgent can complete end-to-end automated verification on multiple modules, including the UART, FPU, and integer divider modules, achieving up to 98.5% code coverage and up to 100% functional coverage. UCAgent also discovers previously unidentified design defects in realistic designs, demonstrating its practical potential.
Fonte: arXiv cs.AI
Multimodal • Score 85
MUST: Modality-Specific Representation-Aware Transformer for Diffusion-Enhanced Survival Prediction with Missing Modality
arXiv:2603.26071v1 Announce Type: new
Abstract: Accurate survival prediction from multimodal medical data is essential for precision oncology, yet clinical deployment faces a persistent challenge: modalities are frequently incomplete due to cost constraints, technical limitations, or retrospective data availability. While recent methods attempt to address missing modalities through feature alignment or joint distribution learning, they fundamentally lack explicit modeling of the unique contributions of each modality as opposed to the information derivable from other modalities. We propose MUST (Modality-Specific representation-aware Transformer), a novel framework that explicitly decomposes each modality's representation into modality-specific and cross-modal contextualized components through algebraic constraints in a learned low-rank shared subspace. This decomposition enables precise identification of what information is lost when a modality is absent. For the truly modality-specific information that cannot be inferred from available modalities, we employ conditional latent diffusion models to generate high-quality representations conditioned on recovered shared information and learned structural priors. Extensive experiments on five TCGA cancer datasets demonstrate that MUST achieves state-of-the-art performance with complete data while maintaining robust predictions in both missing pathology and missing genomics conditions, with clinically acceptable inference latency.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Knowledge Distillation for Efficient Transformer-Based Reinforcement Learning in Hardware-Constrained Energy Management Systems
arXiv:2603.26249v1 Announce Type: new
Abstract: Transformer-based reinforcement learning has emerged as a strong candidate for sequential control in residential energy management. In particular, the Decision Transformer can learn effective battery dispatch policies from historical data, thereby increasing photovoltaic self-consumption and reducing electricity costs. However, transformer models are typically too computationally demanding for deployment on resource-constrained residential controllers, where memory and latency constraints are critical. This paper investigates knowledge distillation to transfer the decision-making behaviour of high-capacity Decision Transformer policies to compact models that are more suitable for embedded deployment. Using the Ausgrid dataset, we train teacher models in an offline sequence-based Decision Transformer framework on heterogeneous multi-building data. We then distil smaller student models by matching the teachers' actions, thereby preserving control quality while reducing model size. Across a broad set of teacher-student configurations, distillation largely preserves control performance and even yields small improvements of up to 1%, while reducing the parameter count by up to 96%, the inference memory by up to 90%, and the inference time by up to 63%. Beyond these compression effects, comparable cost improvements are also observed when distilling into a student model of identical architectural capacity. Overall, our results show that knowledge distillation makes Decision Transformer control more applicable for residential energy management on resource-limited hardware.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Reinforcing Structured Chain-of-Thought for Video Understanding
arXiv:2603.25942v1 Announce Type: cross
Abstract: Multi-modal Large Language Models (MLLMs) show promise in video understanding. However, their reasoning often suffers from thinking drift and weak temporal comprehension, even when enhanced by Reinforcement Learning (RL) techniques like Group Relative Policy Optimization (GRPO). Moreover, existing RL methods usually depend on Supervised Fine-Tuning (SFT), which requires costly Chain-of-Thought (CoT) annotation and multi-stage training, and enforces fixed reasoning paths, limiting MLLMs' ability to generalize and potentially inducing bias. To overcome these limitations, we introduce Summary-Driven Reinforcement Learning (SDRL), a novel single-stage RL framework that obviates the need for SFT by utilizing a Structured CoT format: Summarize -> Think -> Answer. SDRL introduces two self-supervised mechanisms integrated into the GRPO objective: 1) Consistency of Vision Knowledge (CVK) enforces factual grounding by reducing KL divergence among generated summaries; and 2) Dynamic Variety of Reasoning (DVR) promotes exploration by dynamically modulating thinking diversity based on group accuracy. This novel integration effectively balances alignment and exploration, supervising both the final answer and the reasoning process. Our method achieves state-of-the-art performance on seven public VideoQA datasets.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
IncreRTL: Traceability-Guided Incremental RTL Generation under Requirement Evolution
arXiv:2603.25769v1 Announce Type: cross
Abstract: Large language models (LLMs) have shown promise in generating RTL code from natural-language descriptions, but existing methods remain static and struggle to adapt to evolving design requirements, potentially causing structural drift and costly full regeneration. We propose IncreRTL, a LLM-driven framework for incremental RTL generation under requirement evolution. By constructing requirement-code traceability links to locate and regenerate affected code segments, IncreRTL achieves accurate and consistent updates. Evaluated on our newly constructed EvoRTL-Bench, IncreRTL demonstrates notable improvements in regeneration consistency and efficiency, advancing LLM-based RTL generation toward practical engineering deployment.
Fonte: arXiv cs.AI
RL • Score 85
Prune as You Generate: Online Rollout Pruning for Faster and Better RLVR
arXiv:2603.24840v1 Announce Type: new
Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced the reasoning capabilities of Large Language Models (LLMs). However, methods such as GRPO and DAPO suffer from substantial computational cost, since they rely on sampling many rollouts for each prompt. Moreover, in RLVR the relative advantage is often sparse: many samples become nearly all-correct or all-incorrect, yielding low within-group reward variance and thus weak learning signals. In this paper, we introduce arrol (Accelerating RLVR via online Rollout Pruning), an online rollout pruning method that prunes rollouts during generation while explicitly steering the surviving ones more correctness-balanced to enhance learning signals. Specifically, arrol trains a lightweight quality head on-the-fly to predict the success probability of partial rollouts and uses it to make early pruning decisions. The learned quality head can further weigh candidates to improve inference accuracy during test-time scaling. To improve efficiency, we present a system design that prunes rollouts inside the inference engine and re-batches the remaining ones for log-probability computation and policy updates. Across GRPO and DAPO on Qwen-3 and LLaMA-3.2 models (1B-8B), arrol improves average accuracy by +2.30 to +2.99 while achieving up to 1.7x training speedup, and yielding up to +8.33 additional gains in average accuracy in test-time scaling. The code is available at https://github.com/Hsu1023/ARRoL.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
Self-Improvement of Large Language Models: A Technical Overview and Future Outlook
arXiv:2603.25681v1 Announce Type: new
Abstract: As large language models (LLMs) continue to advance, improving them solely through human supervision is becoming increasingly costly and limited in scalability. As models approach human-level capabilities in certain domains, human feedback may no longer provide sufficiently informative signals for further improvement. At the same time, the growing ability of models to make autonomous decisions and execute complex actions naturally enables abstractions in which components of the model development process can be progressively automated. Together, these challenges and opportunities have driven increasing interest in self-improvement, where models autonomously generate data, evaluate outputs, and iteratively refine their own capabilities. In this paper, we present a system-level perspective on self-improving language models and introduce a unified framework that organizes existing techniques. We conceptualize the self-improvement system as a closed-loop lifecycle, consisting of four tightly coupled processes: data acquisition, data selection, model optimization, and inference refinement, along with an autonomous evaluation layer. Within this framework, the model itself plays a central role in driving each stage: collecting or generating data, selecting informative signals, updating its parameters, and refining outputs, while the autonomous evaluation layer continuously monitors progress and guides the improvement cycle across stages. Following this lifecycle perspective, we systematically review and analyze representative methods for each component from a technical standpoint. We further discuss current limitations and outline our vision for future research toward fully self-improving LLMs.
Fonte: arXiv cs.CL
RL • Score 85
Distributed Real-Time Vehicle Control for Emergency Vehicle Transit: A Scalable Cooperative Method
arXiv:2603.25000v1 Announce Type: new
Abstract: Rapid transit of emergency vehicles is critical for saving lives and reducing property loss but often relies on surrounding ordinary vehicles to cooperatively adjust their driving behaviors. It is important to ensure rapid transit of emergency vehicles while minimizing the impact on ordinary vehicles. Centralized mathematical solver and reinforcement learning are the state-of-the-art methods. The former obtains optimal solutions but is only practical for small-scale scenarios. The latter implicitly learns through extensive centralized training but the trained model exhibits limited scalability to different traffic conditions. Hence, existing methods suffer from two fundamental limitations: high computational cost and lack of scalability. To overcome above limitations, this work proposes a scalable distributed vehicle control method, where vehicles adjust their driving behaviors in a distributed manner online using only local instead of global information. We proved that the proposed distributed method using only local information is approximately equivalent to the one using global information, which enables vehicles to evaluate their candidate states and make approximately optimal decisions in real time without pre-training and with natural adaptability to varying traffic conditions. Then, a distributed conflict resolution mechanism is further proposed to guarantee vehicles' safety by avoiding their decision conflicts, which eliminates the single-point-of-failure risk of centralized methods and provides deterministic safety guarantees that learned methods cannot offer. Compared with existing methods, simulation experiments based on real-world traffic datasets demonstrate that the proposed method achieves faster decision-making, less impact on ordinary vehicles, and maintains much stronger scalability across different traffic densities and road configurations.
Fonte: arXiv cs.CV
Vision • Score 85
KitchenTwin: Semantically and Geometrically Grounded 3D Kitchen Digital Twins
arXiv:2603.24684v1 Announce Type: new
Abstract: Embodied AI training and evaluation require object-centric digital twin environments with accurate metric geometry and semantic grounding. Recent transformer-based feedforward reconstruction methods can efficiently predict global point clouds from sparse monocular videos, yet these geometries suffer from inherent scale ambiguity and inconsistent coordinate conventions. This mismatch prevents the reliable fusion of these dimensionless point cloud predictions with locally reconstructed object meshes. We propose a novel scale-aware 3D fusion framework that registers visually grounded object meshes with transformer-predicted global point clouds to construct metrically consistent digital twins. Our method introduces a Vision-Language Model (VLM)-guided geometric anchor mechanism that resolves this fundamental coordinate mismatch by recovering an accurate real-world metric scale. To fuse these networks, we propose a geometry-aware registration pipeline that explicitly enforces physical plausibility through gravity-aligned vertical estimation, Manhattan-world structural constraints, and collision-free local refinement. Experiments on real indoor kitchen environments demonstrate improved cross-network object alignment and geometric consistency for downstream tasks, including multi-primitive fitting and metric measurement. We additionally introduce an open-source indoor digital twin dataset with metrically scaled scenes and semantically grounded and registered object-centric mesh annotations.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Natural-Language Agent Harnesses
arXiv:2603.25723v1 Announce Type: new
Abstract: Agent performance increasingly depends on \emph{harness engineering}, yet harness design is usually buried in controller code and runtime-specific conventions, making it hard to transfer, compare, and study as a scientific object. We ask whether the high-level control logic of an agent harness can instead be externalized as a portable executable artifact. We introduce \textbf{Natural-Language Agent Harnesses} (NLAHs), which express harness behavior in editable natural language, and \textbf{Intelligent Harness Runtime} (IHR), a shared runtime that executes these harnesses through explicit contracts, durable artifacts, and lightweight adapters. Across coding and computer-use benchmarks, we conduct controlled evaluations of operational viability, module ablation, and code-to-text harness migration.
Fonte: arXiv cs.CL
Multimodal • Score 85
ReDiPrune: Relevance-Diversity Pre-Projection Token Pruning for Efficient Multimodal LLMs
arXiv:2603.24680v1 Announce Type: new
Abstract: Recent multimodal large language models are computationally expensive because Transformers must process a large number of visual tokens. We present \textbf{ReDiPrune}, a training-free token pruning method applied before the vision-language projector, where visual features remain rich and discriminative. Unlike post-projection pruning methods that operate on compressed representations, ReDiPrune selects informative tokens directly from vision encoder outputs, preserving fine-grained spatial and semantic cues. Each token is scored by a lightweight rule that jointly consider text-conditioned relevance and max-min diversity, ensuring the selected tokens are both query-relevant and non-redundant. ReDiPrune is fully plug-and-play, requiring no retraining or architectural modifications, and can be seamlessly inserted between the encoder and projector. Across four video and five image benchmarks, it consistently improves the accuracy-efficiency trade-off. For example, on EgoSchema with LLaVA-NeXT-Video-7B, retaining only 15\% of visual tokens yields a +2.0\% absolute accuracy gain while reducing computation by more than $6\times$ in TFLOPs. Code is available at https://github.com/UA-CVML/ReDiPrune.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation
arXiv:2603.25702v1 Announce Type: new
Abstract: Block-diffusion language models offer a promising path toward faster-than-autoregressive generation by combining block-wise autoregressive decoding with within-block parallel denoising. However, in the few-step regime needed for practical acceleration, standard confidence-thresholded decoding is often brittle: aggressive thresholds hurt quality, while conservative thresholds require unnecessary denoising steps. Existing approaches that address this issue either require additional training or incur extra test-time compute. We present S2D2, a training-free self-speculative decoding framework for block-diffusion language models. Our key observation is that a block-diffusion model becomes autoregressive when the block size is reduced to one, allowing the same pretrained model to act as both drafter and verifier. S2D2 inserts a speculative verification step into standard block-diffusion decoding and uses lightweight routing policies to decide when verification is worth its cost. This yields a hybrid decoding trajectory in which diffusion proposes tokens in parallel, while the autoregressive mode acts as a local sequence-level critic. Across three mainstream block-diffusion families, S2D2 consistently improves the accuracy-speed tradeoff over strong confidence-thresholding baselines. On SDAR, we observe up to $4.7\times$ speedup over autoregressive decoding, and up to $1.57\times$ over a tuned dynamic decoding baseline while improving accuracy by up to $4.5$ points. On LLaDA2.1-Mini, S2D2 remains complementary to built-in self-correction, including a conservative setting where it is $4.4\times$ faster than the static baseline with slightly higher accuracy.
Fonte: arXiv cs.CL
Multimodal • Score 85
AVControl: Efficient Framework for Training Audio-Visual Controls
arXiv:2603.24793v1 Announce Type: new
Abstract: Controlling video and audio generation requires diverse modalities, from depth and pose to camera trajectories and audio transformations, yet existing approaches either train a single monolithic model for a fixed set of controls or introduce costly architectural changes for each new modality. We introduce AVControl, a lightweight, extendable framework built on LTX-2, a joint audio-visual foundation model, where each control modality is trained as a separate LoRA on a parallel canvas that provides the reference signal as additional tokens in the attention layers, requiring no architectural changes beyond the LoRA adapters themselves. We show that simply extending image-based in-context methods to video fails for structural control, and that our parallel canvas approach resolves this. On the VACE Benchmark, we outperform all evaluated baselines on depth- and pose-guided generation, inpainting, and outpainting, and show competitive results on camera control and audio-visual benchmarks. Our framework supports a diverse set of independently trained modalities: spatially-aligned controls such as depth, pose, and edges, camera trajectory with intrinsics, sparse motion control, video editing, and, to our knowledge, the first modular audio-visual controls for a joint generation model. Our method is both compute- and data-efficient: each modality requires only a small dataset and converges within a few hundred to a few thousand training steps, a fraction of the budget of monolithic alternatives. We publicly release our code and trained LoRA checkpoints.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
Once-for-All Channel Mixers (HYPERTINYPW): Generative Compression for TinyML
arXiv:2603.24916v1 Announce Type: cross
Abstract: Deploying neural networks on microcontrollers is constrained by kilobytes of flash and SRAM, where 1x1 pointwise (PW) mixers often dominate memory even after INT8 quantization across vision, audio, and wearable sensing. We present HYPER-TINYPW, a compression-as-generation approach that replaces most stored PW weights with generated weights: a shared micro-MLP synthesizes PW kernels once at load time from tiny per-layer codes, caches them, and executes them with standard integer operators. This preserves commodity MCU runtimes and adds only a one-off synthesis cost; steady-state latency and energy match INT8 separable CNN baselines. Enforcing a shared latent basis across layers removes cross-layer redundancy, while keeping PW1 in INT8 stabilizes early, morphology-sensitive mixing. We contribute (i) TinyML-faithful packed-byte accounting covering generator, heads/factorization, codes, kept PW1, and backbone; (ii) a unified evaluation with validation-tuned t* and bootstrap confidence intervals; and (iii) a deployability analysis covering integer-only inference and boot versus lazy synthesis. On three ECG benchmarks (Apnea-ECG, PTB-XL, MIT-BIH), HYPER-TINYPW shifts the macro-F1 versus flash Pareto frontier: at about 225 kB it matches a roughly 1.4 MB CNN while being 6.31x smaller (84.15% fewer bytes), retaining at least 95% of large-model macro-F1. Under 32-64 kB budgets it sustains balanced detection where compact baselines degrade. The mechanism applies broadly to other 1D biosignals, on-device speech, and embedded sensing tasks where per-layer redundancy dominates, indicating a wider role for compression-as-generation in resource-constrained ML systems. Beyond ECG, HYPER-TINYPW transfers to TinyML audio: on Speech Commands it reaches 96.2% test accuracy (98.2% best validation), supporting broader applicability to embedded sensing workloads where repeated linear mixers dominate memory.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
Prompt Attack Detection with LLM-as-a-Judge and Mixture-of-Models
arXiv:2603.25176v1 Announce Type: new
Abstract: Prompt attacks, including jailbreaks and prompt injections, pose a critical security risk to Large Language Model (LLM) systems. In production, guardrails must mitigate these attacks under strict low-latency constraints, resulting in a deployment gap in which lightweight classifiers and rule-based systems struggle to generalize under distribution shift, while high-capacity LLM-based judges remain too slow or costly for live enforcement. In this work, we examine whether lightweight, general-purpose LLMs can reliably serve as security judges under real-world production constraints. Through careful prompt and output design, lightweight LLMs are guided through a structured reasoning process involving explicit intent decomposition, safety-signal verification, harm assessment, and self-reflection. We evaluate our method on a curated dataset combining benign queries from real-world chatbots with adversarial prompts generated via automated red teaming (ART), covering diverse and evolving patterns. Our results show that general-purpose LLMs, such as gemini-2.0-flash-lite-001, can serve as effective low-latency judges for live guardrails. This configuration is currently deployed in production as a centralized guardrail service for public service chatbots in Singapore. We additionally evaluate a Mixture-of-Models (MoM) setting to assess whether aggregating multiple LLM judges improves prompt-attack detection performance relative to single-model judges, with only modest gains observed.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
SurgPhase: Time efficient pituitary tumor surgery phase recognition via an interactive web platform
arXiv:2603.24897v1 Announce Type: new
Abstract: Accurate surgical phase recognition is essential for analyzing procedural workflows, supporting intraoperative decision-making, and enabling data-driven improvements in surgical education and performance evaluation. In this work, we present a comprehensive framework for phase recognition in pituitary tumor surgery (PTS) videos, combining self-supervised representation learning, robust temporal modeling, and scalable data annotation strategies. Our method achieves 90\% accuracy on a held-out test set, outperforming current state-of-the-art approaches and demonstrating strong generalization across variable surgical cases.
A central contribution of this work is the integration of a collaborative online platform designed for surgeons to upload surgical videos, receive automated phase analysis, and contribute to a growing dataset. This platform not only facilitates large-scale data collection but also fosters knowledge sharing and continuous model improvement. To address the challenge of limited labeled data, we pretrain a ResNet-50 model using the self-supervised framework on 251 unlabeled PTS videos, enabling the extraction of high-quality feature representations. Fine-tuning is performed on a labeled dataset of 81 procedures using a modified training regime that incorporates focal loss, gradual layer unfreezing, and dynamic sampling to address class imbalance and procedural variability.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
VideoTIR: Accurate Understanding for Long Videos with Efficient Tool-Integrated Reasoning
arXiv:2603.25021v1 Announce Type: new
Abstract: Existing Multimodal Large Language Models (MLLMs) often suffer from hallucinations in long video understanding (LVU), primarily due to the imbalance between textual and visual tokens. Observing that MLLMs handle short visual inputs well, recent LVU works alleviate hallucinations by automatically parsing the vast visual data into manageable segments that can be effectively processed by MLLMs. SFT-based tool-calling methods can serve this purpose, but they typically require vast amounts of fine-grained, high-quality data and suffer from constrained tool-calling trajectories. We propose a novel VideoTIR that leverages Reinforcement Learning (RL) to encourage proper usage of comprehensive multi-level toolkits for efficient long video understanding. VideoTIR explores both Zero-RL and SFT cold-starting to enable MLLMs to retrieve and focus on meaningful video segments/images/regions, enhancing long video understanding both accurately and efficiently. To reduce redundant tool-calling, we propose Toolkit Action Grouped Policy Optimization (TAGPO), which enhances the efficiency of the calling process through stepwise reward assignment and reuse of failed rollouts. Additionally, we develop a sandbox-based trajectory synthesis framework to generate high-quality trajectories data. Extensive experiments on three long-video QA benchmarks demonstrate the effectiveness and efficiency of our method.
Fonte: arXiv cs.CV
Privacy/Security/Fairness • Score 85
AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective
arXiv:2603.24857v1 Announce Type: cross
Abstract: As machine learning (ML) systems expand in both scale and functionality, the security landscape has become increasingly complex, with a proliferation of attacks and defenses. However, existing studies largely treat these threats in isolation, lacking a coherent framework to expose their shared principles and interdependencies. This fragmented view hinders systematic understanding and limits the design of comprehensive defenses. Crucially, the two foundational assets of ML -- \textbf{data} and \textbf{models} -- are no longer independent; vulnerabilities in one directly compromise the other. The absence of a holistic framework leaves open questions about how these bidirectional risks propagate across the ML pipeline. To address this critical gap, we propose a \emph{unified closed-loop threat taxonomy} that explicitly frames model-data interactions along four directional axes. Our framework offers a principled lens for analyzing and defending foundation models. The resulting four classes of security threats represent distinct but interrelated categories of attacks: (1) Data$\rightarrow$Data (D$\rightarrow$D): including \emph{data decryption attacks and watermark removal attacks}; (2) Data$\rightarrow$Model (D$\rightarrow$M): including \emph{poisoning, harmful fine-tuning attacks, and jailbreak attacks}; (3) Model$\rightarrow$Data (M$\rightarrow$D): including \emph{model inversion, membership inference attacks, and training data extraction attacks}; (4) Model$\rightarrow$Model (M$\rightarrow$M): including \emph{model extraction attacks}. Our unified framework elucidates the underlying connections among these security threats and establishes a foundation for developing scalable, transferable, and cross-modal security strategies, particularly within the landscape of foundation models.
Fonte: arXiv cs.CL
Theory/Optimization • Score 85
When Models Don't Collapse: On the Consistency of Iterative MLE
arXiv:2505.19046v3 Announce Type: replace
Abstract: The widespread use of generative models has created a feedback loop, in which each generation of models is trained on data partially produced by its predecessors. This process has raised concerns about model collapse: A critical degradation in performance caused by repeated training on synthetic data. However, different analyses in the literature have reached different conclusions as to the severity of model collapse. As such, it remains unclear how concerning this phenomenon is, and under which assumptions it can be avoided. To address this, we theoretically study model collapse for maximum likelihood estimation (MLE), in a natural setting where synthetic data is gradually added to the original data set. Under standard assumptions (similar to those long used for proving asymptotic consistency and normality of MLE), we establish non-asymptotic bounds showing that collapse can be avoided even as the fraction of real data vanishes. On the other hand, we prove that some assumptions (beyond MLE consistency) are indeed necessary: Without them, model collapse can occur arbitrarily quickly, even when the original data is still present in the training set. To the best of our knowledge, these are the first rigorous examples of iterative generative modeling with accumulating data that rapidly leads to model collapse.
Fonte: arXiv stat.ML
Vision • Score 85
HyDRA: Hybrid Domain-Aware Robust Architecture for Heterogeneous Collaborative Perception
arXiv:2603.23975v1 Announce Type: new
Abstract: In collaborative perception, an agent's performance can be degraded by heterogeneity arising from differences in model architecture or training data distributions. To address this challenge, we propose HyDRA (Hybrid Domain-Aware Robust Architecture), a unified pipeline that integrates intermediate and late fusion within a domain-aware framework. We introduce a lightweight domain classifier that dynamically identifies heterogeneous agents and assigns them to the late-fusion branch. Furthermore, we propose anchor-guided pose graph optimization to mitigate localization errors inherent in late fusion, leveraging reliable detections from intermediate fusion as fixed spatial anchors. Extensive experiments demonstrate that, despite requiring no additional training, HyDRA achieves performance comparable to state-of-the-art heterogeneity-aware CP methods. Importantly, this performance is maintained as the number of collaborating agents increases, enabling zero-cost scaling without retraining.
Fonte: arXiv cs.CV
Theory/Optimization • Score 85
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
arXiv:2603.24582v1 Announce Type: new
Abstract: Agentic artificial intelligence (AI) in organizations is a sequential decision problem constrained by reliability and oversight cost. When deterministic workflows are replaced by stochastic policies over actions and tool calls, the key question is not whether a next step appears plausible, but whether the resulting trajectory remains statistically supported, locally unambiguous, and economically governable. We develop a measure-theoretic Markov framework for this setting. The core quantities are state blind-spot mass B_n(tau), state-action blind mass B^SA_{pi,n}(tau), an entropy-based human-in-the-loop escalation gate, and an expected oversight-cost identity over the workflow visitation measure.
We instantiate the framework on the Business Process Intelligence Challenge 2019 purchase-to-pay log (251,734 cases, 1,595,923 events, 42 distinct workflow actions) and construct a log-driven simulated agent from a chronological 80/20 split of the same process. The main empirical finding is that a large workflow can appear well supported at the state level while retaining substantial blind mass over next-step decisions: refining the operational state to include case context, economic magnitude, and actor class expands the state space from 42 to 668 and raises state-action blind mass from 0.0165 at tau=50 to 0.1253 at tau=1000. On the held-out split, m(s) = max_a pi-hat(a|s) tracks realized autonomous step accuracy within 3.4 percentage points on average.
The same quantities that delimit statistically credible autonomy also determine expected oversight burden. The framework is demonstrated on a large-scale enterprise procurement workflow and is designed for direct application to engineering processes for which operational event logs are available.
Fonte: arXiv cs.AI
NLP/LLMs • Score 90
MetaKube: An Experience-Aware LLM Framework for Kubernetes Failure Diagnosis
arXiv:2603.23580v1 Announce Type: new
Abstract: Existing LLM-based Kubernetes diagnostic systems cannot learn from operational experience, operating on static knowledge bases without improving from past resolutions. We present MetaKube, an experience-aware LLM framework through three synergistic innovations: (1) an Episodic Pattern Memory Network (EPMN) that abstracts diagnostic patterns from historical resolutions and provides confidence-calibrated retrieval for both rapid pattern matching and guided causal exploration, (2) a meta-cognitive controller that dynamically routes between intuitive and analytical pathways based on problem familiarity, optimizing the trade-off between speed and depth, and (3) KubeLLM, a locally-deployable 8B model enhanced through domain-specific post-training on our 7,000-sample Kubernetes Fault Resolution Dataset. Evaluation on 1,873 real-world scenarios demonstrates MetaKube transforms Qwen3-8B from 50.9 to 90.5 points, approaching GPT-4.1 performance while ensuring complete data privacy. EPMN contributes 15.3% improvement through experiential learning, with continuous learning experiments showing progressive gains as the system accumulates operational knowledge. The source code and related resources are available at https://github.com/MetaKube-LLM-for-Kubernetes-Diagnosis/MetaKube.
Fonte: arXiv cs.LG
Applications • Score 85
Wireless communication empowers online scheduling of partially-observable transportation multi-robot systems in a smart factory
arXiv:2603.23967v1 Announce Type: new
Abstract: Achieving agile and reconfigurable production flows in smart factories depends on online multi-robot task assignment (MRTA), which requires online collision-free and congestion-free route scheduling of transportation multi-robot systems (T-MRS), e.g., collaborative automatic guided vehicles (AGVs). Due to the real-time operational requirements and dynamic interactions between T-MRS and production MRS, online scheduling under partial observability in dynamic factory environments remains a significant and under-explored challenge. This paper proposes a novel communication-enabled online scheduling framework that explicitly couples wireless machine-to-machine (M2M) networking with route scheduling, enabling AGVs to exchange intention information, e.g., planned routes, to overcome partial observations and assist complex computation of online scheduling. Specifically, we determine intelligent AGVs' intention and sensor data as new M2M traffic and tailor the retransmission-free multi-link transmission networking to meet real-time operation demands. This scheduling-oriented networking is then integrated with a simulated annealing-based MRTA scheme and a congestion-aware A*-based route scheduling method. The integrated communication and scheduling scheme allows AGVs to dynamically adjust collision-free and congestion-free routes with reduced computational overhead. Numerical experiments shows the impacts from wireless communication on the performance of T-MRS and suggest that the proposed integrated scheme significantly enhances scheduling efficiency compared to other baselines, even under high AGV load conditions and limited channel resources. Moreover, the results reveal that the scheduling-oriented wireless M2M communication design fundamentally differs from human-to-human communications, implying new technological opportunities in a wireless networked smart factory.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Stochastic Dimension-Free Zeroth-Order Estimator for High-Dimensional and High-Order PINNs
arXiv:2603.24002v1 Announce Type: new
Abstract: Physics-Informed Neural Networks (PINNs) for high-dimensional and high-order partial differential equations (PDEs) are primarily constrained by the $\mathcal{O}(d^k)$ spatial derivative complexity and the $\mathcal{O}(P)$ memory overhead of backpropagation (BP). While randomized spatial estimators successfully reduce the spatial complexity to $\mathcal{O}(1)$, their reliance on first-order optimization still leads to prohibitive memory consumption at scale. Zeroth-order (ZO) optimization offers a BP-free alternative; however, naively combining randomized spatial operators with ZO perturbations triggers a variance explosion of $\mathcal{O}(1/\varepsilon^2)$, leading to numerical divergence. To address these challenges, we propose the \textbf{S}tochastic \textbf{D}imension-free \textbf{Z}eroth-order \textbf{E}stimator (\textbf{SDZE}), a unified framework that achieves dimension-independent complexity in both space and memory. Specifically, SDZE leverages \emph{Common Random Numbers Synchronization (CRNS)} to algebraically cancel the $\mathcal{O}(1/\varepsilon^2)$ variance by locking spatial random seeds across perturbations. Furthermore, an \emph{implicit matrix-free subspace projection} is introduced to reduce parameter exploration variance from $\mathcal{O}(P)$ to $\mathcal{O}(r)$ while maintaining an $\mathcal{O}(1)$ optimizer memory footprint. Empirical results demonstrate that SDZE enables the training of 10-million-dimensional PINNs on a single NVIDIA A100 GPU, delivering significant improvements in speed and memory efficiency over state-of-the-art baselines.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
APreQEL: Adaptive Mixed Precision Quantization For Edge LLMs
arXiv:2603.23575v1 Announce Type: new
Abstract: Today, large language models have demonstrated their strengths in various tasks ranging from reasoning, code generation, and complex problem solving. However, this advancement comes with a high computational cost and memory requirements, making it challenging to deploy these models on edge devices to ensure real-time responses and data privacy. Quantization is one common approach to reducing memory use, but most methods apply it uniformly across all layers. This does not account for the fact that different layers may respond differently to reduced precision. Importantly, memory consumption and computational throughput are not necessarily aligned, further complicating deployment decisions. This paper proposes an adaptive mixed precision quantization mechanism that balances memory, latency, and accuracy in edge deployment under user-defined priorities. This is achieved by analyzing the layer-wise contribution and by inferring how different quantization types behave across the target hardware platform in order to assign the most suitable quantization type to each layer. This integration ensures that layer importance and the overall performance trade-offs are jointly respected in this design. Our work unlocks new configuration designs that uniform quantization cannot achieve, expanding the solution space to efficiently deploy the LLMs on resource-constrained devices.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Self-Distillation for Multi-Token Prediction
arXiv:2603.23911v1 Announce Type: new
Abstract: As Large Language Models (LLMs) scale up, inference efficiency becomes a critical bottleneck. Multi-Token Prediction (MTP) could accelerate LLM inference by predicting multiple future tokens in parallel. However, existing MTP approaches still face two challenges: limited acceptance rates of MTP heads, and difficulties in jointly training multiple MTP heads. Therefore, we propose MTP-D, a simple yet effective self-distillation method with minimal additional training cost, which boosts MTP head acceptance rates (+7.5\%) while maximumly preserving main-head performance. We also introduce a looped extension strategy for MTP-D, enabling effective and economical MTP head extension and further significant inference speedup to 1-head MTP (+220.4\%). Moreover, we systematically explore and validate key insights on the distillation strategies and the potential scalability of MTP through extensive experiments on seven benchmarks. These results demonstrate that our MTP-D and looped extension strategy effectively enhance MTP-head performance and inference efficiency, facilitating the practical usage of MTP in LLMs.
Fonte: arXiv cs.CL
NLP/LLMs • Score 90
MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens
arXiv:2603.23516v1 Announce Type: cross
Abstract: Long-term memory is a cornerstone of human intelligence. Enabling AI to process lifetime-scale information remains a long-standing pursuit in
the field. Due to the constraints of full-attention architectures, the effective context length of large language models (LLMs) is typically
limited to 1M tokens. Existing approaches, such as hybrid linear attention, fixed-size memory states (e.g., RNNs), and external storage
methods like RAG or agent systems, attempt to extend this limit. However, they often suffer from severe precision degradation and rapidly
increasing latency as context length grows, an inability to dynamically modify memory content, or a lack of end-to-end optimization. These
bottlenecks impede complex scenarios like large-corpus summarization, Digital Twins, and long-history agent reasoning, while limiting memory
capacity and slowing inference. We present Memory Sparse Attention (MSA), an end-to-end trainable, efficient, and massively scalable memory
model framework. Through core innovations including scalable sparse attention and document-wise RoPE, MSA achieves linear complexity in both
training and inference while maintaining exceptional stability, exhibiting less than 9% degradation when scaling from 16K to 100M tokens.
Furthermore, KV cache compression, combined with Memory Parallel, enables 100M-token inference on 2xA800 GPUs. We also propose Memory
Interleaving to facilitate complex multi-hop reasoning across scattered memory segments. MSA significantly surpasses frontier LLMs,
state-of-the-art RAG systems, and leading memory agents in long-context benchmarks. These results demonstrate that by decoupling memory
capacity from reasoning, MSA provides a scalable foundation to endow general-purpose models with intrinsic, lifetime-scale memory.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
Lagrangian Relaxation Score-based Generation for Mixed Integer linear Programming
arXiv:2603.24033v1 Announce Type: new
Abstract: Predict-and-search (PaS) methods have shown promise for accelerating mixed-integer linear programming (MILP) solving. However, existing approaches typically assume variable independence and rely on deterministic single-point predictions, which limits solution diversityand often necessitates extensive downstream search for high-quality solutions. In this paper, we propose \textbf{SRG}, a generative framework based on Lagrangian relaxation-guided stochastic differential equations (SDEs), with theoretical guarantees on solution quality. SRG leverages convolutional kernels to capture inter-variable dependencies while integrating Lagrangian relaxation to guide the sampling process toward feasible and near-optimal regions. Rather than producing a single estimate, SRG generates diverse, high-quality solution candidates that collectively define compact and effective trust-region subproblems for standard MILP solvers. Across multiple public benchmarks, SRG consistently outperforms existing machine learning baselines in solution quality. Moreover, SRG demonstrates strong zero-shot transferability: on unseen cross-scale/problem instances, it achieves competitive optimality with state-of-the-art exact solvers while significantly reducing computational overhead through faster search and superior solution quality.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Why Machine Learning Models Systematically Underestimate Extreme Values II: How to Fix It with LatentNN
arXiv:2512.23138v2 Announce Type: replace-cross
Abstract: Attenuation bias -- the systematic underestimation of regression coefficients due to measurement errors in input variables -- affects astronomical data-driven models. For linear regression, this problem was solved by treating the true input values as latent variables to be estimated alongside model parameters. In this paper, we show that neural networks suffer from the same attenuation bias and that the latent variable solution generalizes directly to neural networks. We introduce LatentNN, a method that jointly optimizes network parameters and latent input values by maximizing the joint likelihood of observing both inputs and outputs. We demonstrate the correction on one-dimensional regression, multivariate inputs with correlated features, and stellar spectroscopy applications. LatentNN reduces attenuation bias across a range of signal-to-noise ratios where standard neural networks show large bias. This provides a framework for improved neural network inference in the low signal-to-noise regime characteristic of astronomical data. This bias correction is most effective when measurement errors are less than roughly half the intrinsic data range; in the regime of very low signal-to-noise and few informative features. Code is available at https://github.com/tingyuansen/LatentNN.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
AnalogAgent: Self-Improving Analog Circuit Design Automation with LLM Agents
arXiv:2603.23910v1 Announce Type: new
Abstract: Recent advances in large language models (LLMs) suggest strong potential for automating analog circuit design. Yet most LLM-based approaches rely on a single-model loop of generation, diagnosis, and correction, which favors succinct summaries over domain-specific insight and suffers from context attrition that erases critical technical details. To address these limitations, we propose AnalogAgent, a training-free agentic framework that integrates an LLM-based multi-agent system (MAS) with self-evolving memory (SEM) for analog circuit design automation. AnalogAgent coordinates a Code Generator, Design Optimizer, and Knowledge Curator to distill execution feedback into an adaptive playbook in SEM and retrieve targeted guidance for subsequent generation, enabling cross-task transfer without additional expert feedback, databases, or libraries. Across established benchmarks, AnalogAgent achieves 92% Pass@1 with Gemini and 97.4% Pass@1 with GPT-5. Moreover, with compact models (e.g., Qwen-8B), it yields a +48.8% average Pass@1 gain across tasks and reaches 72.1% Pass@1 overall, indicating that AnalogAgent substantially strengthens open-weight models for high-quality analog circuit design automation.
Fonte: arXiv cs.AI
Vision • Score 85
Attention-aware Inference Optimizations for Large Vision-Language Models with Memory-efficient Decoding
arXiv:2603.23914v1 Announce Type: new
Abstract: Large Vision-Language Models (VLMs) have achieved remarkable success in multi-modal reasoning, but their inference time efficiency remains a significant challenge due to the memory overhead during decoding, especially when the query and answer of VLMs consist of long sequences of visual and text tokens. This paper presents AttentionPack, an adaptive and attention-aware optimization framework tailored for large vision-language models with improving memory-efficiency during decoding, focusing on addressing the challenges due to the increased high number of visual inputs and interactions, particularly in long-context tasks with multiple high-resolution images or videos. AttentionPack is novel in two aspects: (i) We introduce a multi-head attention compaction method for economically storing key and value matrices by exploiting the implicit low-rank structure, and (ii) we develop a token-specific attention-aware decompression mechanism to reduce latency overhead. Experimental results on multiple benchmarks demonstrate that AttentionPack improves memory efficiency by up to 8x, enabling higher batch sizes and faster batch inference while preserving the model output quality or longer context lengths for superior retrieval performance. We also report the effectiveness of AttentionPack combined with eviction, quantization and kernel fusion, showing further efficiency gains for resource-limited environments.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training
arXiv:2603.23885v1 Announce Type: new
Abstract: Document parsing has recently advanced with multimodal large language models (MLLMs) that directly map document images to structured outputs. Traditional cascaded pipelines depend on precise layout analysis and often fail under casually captured or non-standard conditions. Although end-to-end approaches mitigate this dependency, they still exhibit repetitive, hallucinated, and structurally inconsistent predictions - primarily due to the scarcity of large-scale, high-quality full-page (document-level) end-to-end parsing data and the lack of structure-aware training strategies. To address these challenges, we propose a data-training co-design framework for robust end-to-end document parsing. A Realistic Scene Synthesis strategy constructs large-scale, structurally diverse full-page end-to-end supervision by composing layout templates with rich document elements, while a Document-Aware Training Recipe introduces progressive learning and structure-token optimization to enhance structural fidelity and decoding stability. We further build Wild-OmniDocBench, a benchmark derived from real-world captured documents for robustness evaluation. Integrated into a 1B-parameter MLLM, our method achieves superior accuracy and robustness across both scanned/digital and real-world captured scenarios. All models, data synthesis pipelines, and benchmarks will be publicly released to advance future research in document understanding.
Fonte: arXiv cs.CV
Vision • Score 85
Mind the Hitch: Dynamic Calibration and Articulated Perception for Autonomous Trucks
arXiv:2603.23711v1 Announce Type: new
Abstract: Autonomous trucking poses unique challenges due to articulated tractor-trailer geometry, and time-varying sensor poses caused by the fifth-wheel joint and trailer flex. Existing perception and calibration methods assume static baselines or rely on high-parallax and texture-rich scenes, limiting their reliability under real-world settings. We propose dCAP (dynamic Calibration and Articulated Perception), a vision-based framework that continuously estimates the 6-DoF (degree of freedom) relative pose between tractor and trailer cameras. dCAP employs a transformer with cross-view and temporal attention to robustly aggregate spatial cues while maintaining temporal consistency, enabling accurate perception under rapid articulation and occlusion. Integrated with BEVFormer, dCAP improves 3D object detection by replacing static calibration with dynamically predicted extrinsics. To facilitate evaluation, we introduce STT4AT, a CARLA-based benchmark simulating semi-trailer trucks with synchronized multi-sensor suites and time-varying inter-rig geometry across diverse environments. Experiments demonstrate that dCAP achieves stable, accurate perception while addressing the limitations of static calibration in autonomous trucking. The dataset, development kit, and source code will be publicly released.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
The Compression Paradox in LLM Inference: Provider-Dependent Energy Effects of Prompt Compression
arXiv:2603.23528v1 Announce Type: new
Abstract: The rapid proliferation of Large Language Models has created an environmental paradox: the very technology that could help solve climate challenges is itself becoming a significant contributor to global carbon emissions. We test whether prompt compression improves inference energy efficiency in 28,421 successful API trials (28,428 planned) across three providers (OpenAI GPT-4o-mini, Anthropic Claude-3.5-Sonnet, and DeepSeek-Chat), five benchmarks (HumanEval, MBPP, GSM8K, MATH, MMLU), and four compression ratios (r in {1.0, 0.7, 0.5, 0.3}). Energy is estimated with a token-based proxy calibrated against local direct measurements, and quality is tracked with benchmark pass rates. Compression produced substantial quality loss (overall pass rate 26.0% at baseline vs. 1.5% at r=0.7) and strongly provider-dependent energy behavior. DeepSeek exhibited output expansion under compression (21 to 798 tokens at r=0.3), corresponding to energy increases up to +2,140%, while GPT-4o-mini showed mixed effects including a reduction at r=0.5. These results indicate that input-token reduction alone is not a reliable energy optimization strategy in production inference. For the evaluated settings, model selection and output-length control provided more consistent energy-quality tradeoffs than prompt compression.
Fonte: arXiv cs.CL
MLOps/Systems • Score 85
Accelerated Parallel Tempering via Neural Transports
arXiv:2502.10328v4 Announce Type: replace
Abstract: Markov Chain Monte Carlo (MCMC) algorithms are essential tools in computational statistics for sampling from unnormalised probability distributions, but can be fragile when targeting high-dimensional, multimodal, or complex target distributions. Parallel Tempering (PT) enhances MCMC's sample efficiency through annealing and parallel computation, propagating samples from tractable reference distributions to intractable targets via state swapping across interpolating distributions. The effectiveness of PT is limited by the often minimal overlap between adjacent distributions in challenging problems, which requires increasing the computational resources to compensate. We introduce a framework that accelerates PT by leveraging neural samplers -- including normalising flows, diffusion models, and controlled diffusions -- to reduce the required overlap. Our approach utilises neural samplers in parallel, circumventing the computational burden of neural samplers while preserving the asymptotic consistency of classical PT. We demonstrate theoretically and empirically on a variety of multimodal sampling problems that our method improves sample quality, reduces the computational cost compared to classical PT, and enables efficient free energy/normalising constant estimation.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
The DeepXube Software Package for Solving Pathfinding Problems with Learned Heuristic Functions and Search
arXiv:2603.23873v1 Announce Type: new
Abstract: DeepXube is a free and open-source Python package and command-line tool that seeks to automate the solution of pathfinding problems by using machine learning to learn heuristic functions that guide heuristic search algorithms tailored to deep neural networks (DNNs). DeepXube is comprised of the latest advances in deep reinforcement learning, heuristic search, and formal logic for solving pathfinding problems. This includes limited-horizon Bellman-based learning, hindsight experience replay, batched heuristic search, and specifying goals with answer-set programming. A robust multiple-inheritance structure simplifies the definition of pathfinding domains and the generation of training data. Training heuristic functions is made efficient through the automatic parallelization of the generation of training data across central processing units (CPUs) and reinforcement learning updates across graphics processing units (GPUs). Pathfinding algorithms that take advantage of the parallelism of GPUs and DNN architectures, such as batch weighted A* and Q* search and beam search are easily employed to solve pathfinding problems through command-line arguments. Finally, several convenient features for visualization, code profiling, and progress monitoring during training and solving are available. The GitHub repository is publicly available at https://github.com/forestagostinelli/deepxube.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Can we generate portable representations for clinical time series data using LLMs?
arXiv:2603.23987v1 Announce Type: new
Abstract: Deploying clinical ML is slow and brittle: models that work at one hospital often degrade under distribution shifts at the next. In this work, we study a simple question -- can large language models (LLMs) create portable patient embeddings i.e. representations of patients enable a downstream predictor built on one hospital to be used elsewhere with minimal-to-no retraining and fine-tuning. To do so, we map from irregular ICU time series onto concise natural language summaries using a frozen LLM, then embed each summary with a frozen text embedding model to obtain a fixed length vector capable of serving as input to a variety of downstream predictors. Across three cohorts (MIMIC-IV, HIRID, PPICU), on multiple clinically grounded forecasting and classification tasks, we find that our approach is simple, easy to use and competitive with in-distribution with grid imputation, self-supervised representation learning, and time series foundation models, while exhibiting smaller relative performance drops when transferring to new hospitals. We study the variation in performance across prompt design, with structured prompts being crucial to reducing the variance of the predictive models without altering mean accuracy. We find that using these portable representations improves few-shot learning and does not increase demographic recoverability of age or sex relative to baselines, suggesting little additional privacy risk. Our work points to the potential that LLMs hold as tools to enable the scalable deployment of production grade predictive models by reducing the engineering overhead.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
VehicleMemBench: An Executable Benchmark for Multi-User Long-Term Memory in In-Vehicle Agents
arXiv:2603.23840v1 Announce Type: new
Abstract: With the growing demand for intelligent in-vehicle experiences, vehicle-based agents are evolving from simple assistants to long-term companions. This evolution requires agents to continuously model multi-user preferences and make reliable decisions in the face of inter-user preference conflicts and changing habits over time. However, existing benchmarks are largely limited to single-user, static question-answer settings, failing to capture the temporal evolution of preferences and the multi-user, tool-interactive nature of real vehicle environments. To address this gap, we introduce VehicleMemBench, a multi-user long-context memory benchmark built on an executable in-vehicle simulation environment. The benchmark evaluates tool use and memory by comparing the post-action environment state with a predefined target state, enabling objective and reproducible evaluation without LLM-based or human scoring. VehicleMemBench includes 23 tool modules, and each sample contains over 80 historical memory events. Experiments show that powerful models perform well on direct instruction tasks but struggle in scenarios involving memory evolution, particularly when user preferences change dynamically. Even advanced memory systems struggle to handle domain-specific memory requirements in this environment. These findings highlight the need for more robust and specialized memory management mechanisms to support long-term adaptive decision-making in real-world in-vehicle systems. To facilitate future research, we release the data and code.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
CDMT-EHR: A Continuous-Time Diffusion Framework for Generating Mixed-Type Time-Series Electronic Health Records
arXiv:2603.23719v1 Announce Type: new
Abstract: Electronic health records (EHRs) are invaluable for clinical research, yet privacy concerns severely restrict data sharing. Synthetic data generation offers a promising solution, but EHRs present unique challenges: they contain both numerical and categorical features that evolve over time. While diffusion models have demonstrated strong performance in EHR synthesis, existing approaches predominantly rely on discrete-time formulations, which suffer from finite-step approximation errors and coupled training-sampling step counts. We propose a continuous-time diffusion framework for generating mixed-type time-series EHRs with three contributions: (1) continuous-time diffusion with a bidirectional gated recurrent unit backbone for capturing temporal dependencies, (2) unified Gaussian diffusion via learnable continuous embeddings for categorical variables, enabling joint cross-feature modeling, and (3) a factorized learnable noise schedule that adapts to per-feature-per-timestep learning difficulties. Experiments on two large-scale intensive care unit datasets demonstrate that our method outperforms existing approaches in downstream task performance, distribution fidelity, and discriminability, while requiring only 50 sampling steps compared to 1,000 for baseline methods. Classifier-free guidance further enables effective conditional generation for class-imbalanced clinical scenarios.
Fonte: arXiv cs.LG
RecSys • Score 85
Lightweight Fairness for LLM-Based Recommendations via Kernelized Projection and Gated Adapters
arXiv:2603.23780v1 Announce Type: new
Abstract: Large Language Models (LLMs) have introduced new capabilities to recommender systems, enabling dynamic, context-aware, and conversational recommendations. However, LLM-based recommender systems inherit and may amplify social biases embedded in their pre-training data, especially when demographic cues are present. Existing fairness solutions either require extra parameters fine-tuning, or suffer from optimization instability. We propose a lightweight and scalable bias mitigation method that combines a kernelized Iterative Null-space Projection (INLP) with a gated Mixture-of-Experts (MoE) adapter. Our approach estimates a closed-form projection that removes single or multiple sensitive attributes from LLM representations with no additional trainable parameters. To preserve task utility, we introduce a two-level MoE adapter that selectively restores useful signals without reintroducing bias. Experiments on two public datasets show that our method reduces attribute leakage across multiple protected variables while maintaining competitive recommendation accuracy.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
LineMVGNN: Anti-Money Laundering with Line-Graph-Assisted Multi-View Graph Neural Networks
arXiv:2603.23584v1 Announce Type: new
Abstract: Anti-money laundering (AML) systems are important for protecting the global economy. However, conventional rule-based methods rely on domain knowledge, leading to suboptimal accuracy and a lack of scalability. Graph neural networks (GNNs) for digraphs (directed graphs) can be applied to transaction graphs and capture suspicious transactions or accounts. However, most spectral GNNs do not naturally support multi-dimensional edge features, lack interpretability due to edge modifications, and have limited scalability owing to their spectral nature. Conversely, most spatial methods may not capture the money flow well. Therefore, in this work, we propose LineMVGNN (Line-Graph-Assisted Multi-View Graph Neural Network), a novel spatial method that considers payment and receipt transactions. Specifically, the LineMVGNN model extends a lightweight MVGNN module, which performs two-way message passing between nodes in a transaction graph. Additionally, LineMVGNN incorporates a line graph view of the original transaction graph to enhance the propagation of transaction information. We conduct experiments on two real-world account-based transaction datasets: the Ethereum phishing transaction network dataset and a financial payment transaction dataset from one of our industry partners. The results show that our proposed method outperforms state-of-the-art methods, reflecting the effectiveness of money laundering detection with line-graph-assisted multi-view graph learning. We also discuss scalability, adversarial robustness, and regulatory considerations of our proposed method.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Compression Method Matters: Benchmark-Dependent Output Dynamics in LLM Prompt Compression
arXiv:2603.23527v1 Announce Type: new
Abstract: Prompt compression is often evaluated by input-token reduction, but its real deployment impact depends on how compression changes output length and total inference cost. We present a controlled replication and extension study of benchmark-dependent output dynamics under aggressive compression, covering 5,400 API calls across three benchmarks and multiple providers. To explain conflicting prior observations, we formalize instruction survival probability (Psi), a structural metric that captures whether task-critical prompt segments remain after truncation. Results show a strong benchmark effect: under r=0.3, DeepSeek exhibits severe output expansion on MBPP (56x, Psi approx 0.15) but substantially lower expansion on HumanEval (5x, Psi approx 0.72), while GPT-4o-mini is comparatively stable across benchmarks. This reconciles the apparent discrepancy between previously reported extreme explosion and lower replication effects by identifying prompt structure, not provider identity alone, as the primary moderator. We introduce the Compression Robustness Index (CRI) for cross-benchmark evaluation and show that single-benchmark assessments can produce misleading conclusions about compression safety and efficiency. To contextualize energy claims, we incorporate companion direct NVML measurements from rented RunPod GPUs and show that token savings can overstate joule savings. These findings motivate benchmark-diverse testing and structure-aware compression policies for reliable, energy-conscious LLM deployment.
Fonte: arXiv cs.CL
Privacy/Security/Fairness • Score 85
DP^2-VL: Private Photo Dataset Protection by Data Poisoning for Vision-Language Models
arXiv:2603.23925v1 Announce Type: new
Abstract: Recent advances in visual-language alignment have endowed vision-language models (VLMs) with fine-grained image understanding capabilities. However, this progress also introduces new privacy risks. This paper first proposes a novel privacy threat model named identity-affiliation learning: an attacker fine-tunes a VLM using only a few private photos of a target individual, thereby embedding associations between the target facial identity and their private property and social relationships into the model's internal representations. Once deployed via public APIs, this model enables unauthorized exposure of the target user's private information upon input of their photos. To benchmark VLMs' susceptibility to such identity-affiliation leakage, we introduce the first identity-affiliation dataset comprising seven typical scenarios appearing in private photos. Each scenario is instantiated with multiple identity-centered photo-description pairs. Experimental results demonstrate that mainstream VLMs like LLaVA, Qwen-VL, and MiniGPT-v2, can recognize facial identities and infer identity-affiliation relationships by fine-tuning on small-scale private photographic dataset, and even on synthetically generated datasets. To mitigate this privacy risk, we propose DP2-VL, the first Dataset Protection framework for private photos that leverages Data Poisoning. Though optimizing imperceptible perturbations by pushing the original representations toward an antithetical region, DP2-VL induces a dataset-level shift in the embedding space of VLMs'encoders. This shift separates protected images from clean inference images, causing fine-tuning on the protected set to overfit. Extensive experiments demonstrate that DP2-VL achieves strong generalization across models, robustness to diverse post-processing operations, and consistent effectiveness across varying protection ratios.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Prompt Compression in Production Task Orchestration: A Pre-Registered Randomized Trial
arXiv:2603.23525v1 Announce Type: new
Abstract: The economics of prompt compression depend not only on reducing input tokens but on how compression changes output length, which is typically priced several times higher. We evaluate this in a pre-registered six-arm randomized controlled trial of prompt compression on production multi-agent task-orchestration, analyzing 358 successful Claude Sonnet 4.5 runs (59-61 per arm) drawn from a randomized corpus of 1,199 real orchestration instructions. We compare an uncompressed control with three uniform retention rates (r=0.8, 0.5, 0.2) and two structure-aware strategies (entropy-adaptive and recency-weighted), measuring total inference cost (input+output) and embedding-based response similarity. Moderate compression (r=0.5) reduced mean total cost by 27.9%, while aggressive compression (r=0.2) increased mean cost by 1.8% despite substantial input reduction, consistent with small mean output expansion (1.03x vs. control) and heavy-tailed uncertainty. Recency-weighted compression achieved 23.5% savings and, together with moderate compression, occupied the empirical cost-similarity Pareto frontier, whereas aggressive compression was dominated on both cost and similarity. These results show that "compress more" is not a reliable production heuristic and that output tokens must be treated as a first-class outcome when designing compression policies.
Fonte: arXiv cs.CL
NLP/LLMs • Score 90
Berta: an open-source, modular tool for AI-enabled clinical documentation
arXiv:2603.23513v1 Announce Type: cross
Abstract: Commercial AI scribes cost \$99-600 per physician per month, operate as opaque systems, and do not return data to institutional infrastructure, limiting organizational control over data governance, quality improvement, and clinical workflows. We developed Berta, an open-source modular scribe platform for AI-enabled clinical documentation, and deployed a customized implementation within Alberta Health Services (AHS) integrated with their existing Snowflake AI Data Cloud infrastructure. The system combines automatic speech recognition with large language models while retaining all clinical data within the secure AHS environment. During eight months (November 2024 to July 2025), 198 emergency physicians used the system in 105 urban and rural facilities, generating 22148 clinical sessions and more than 2800 hours of audio. The use grew from 680 to 5530 monthly sessions. Operating costs averaged less than \$30 per physician per month, a 70-95% reduction compared to commercial alternatives. AHS has since approved expansion to 850 physicians. This is the first provincial-scale deployment of an AI scribe integrated with existing health system infrastructure. By releasing Berta as open source, we provide a reproducible, cost-effective alternative that health systems can adapt to their own secure environments, supporting data sovereignty and informed evaluation of AI documentation technology.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Fast and Faithful: Real-Time Verification for Long-Document Retrieval-Augmented Generation Systems
arXiv:2603.23508v1 Announce Type: new
Abstract: Retrieval-augmented generation (RAG) is increasingly deployed in enterprise search and document-centric assistants, where responses must be grounded in long and complex source materials. In practice, verifying that generated answers faithfully reflect retrieved documents is difficult: large language models can check long contexts but are too slow and costly for interactive services, while lightweight classifiers operate within strict context limits and frequently miss evidence outside truncated passages. We present the design of a real-time verification component integrated into a production RAG pipeline that enables full-document grounding under latency constraints. The system processes documents up to 32K tokens and employs adaptive inference strategies to balance response time and verification coverage across workloads. We describe the architectural decisions, operational trade-offs, and evaluation methodology used to deploy the verifier, and show that full-context verification substantially improves detection of unsupported responses compared with truncated validation. Our experience highlights when long-context verification is necessary, why chunk-based checking often fails in real documents, and how latency budgets shape model design. These findings provide practical guidance for practitioners building reliable large-scale retrieval-augmented applications. (Model, benchmark, and code: https://huggingface.co/llm-semantic-router)
Fonte: arXiv cs.CL
MLOps/Systems • Score 85
Diet Your LLM: Dimension-wise Global Pruning of LLMs via Merging Task-specific Importance Score
arXiv:2603.23985v1 Announce Type: new
Abstract: Large language models (LLMs) have demonstrated remarkable capabilities, but their massive scale poses significant challenges for practical deployment. Structured pruning offers a promising solution by removing entire dimensions or layers, yet existing methods face critical trade-offs: task-agnostic approaches cannot adapt to task-specific requirements, while task-aware methods require costly training to learn task adaptability. We propose DIET (Dimension-wise global pruning of LLMs via merging Task-wise importance scores), a training-free structured pruning method that combines dimension-level granularity with task-aware selection. DIET profiles activation magnitudes across tasks using only 100 samples per task, then applies majority voting to construct a single global mask. DIET does not require large costs from pre-computation or training. Experiments on seven zero-shot benchmarks using Gemma-2 2B and 9B models demonstrate the effectiveness of DIET; for example, at 20% sparsity on Gemma-2 2B, DIET achieves near 10% average accuracy improvement, compared to previous state-of-the-art structured pruning methods. This advantage persists across various sparsity levels and model scales, positioning DIET as a practical and robust choice for structured LLM pruning.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
AI-Supervisor: Autonomous AI Research Supervision via a Persistent Research World Model
arXiv:2603.24402v1 Announce Type: new
Abstract: Existing automated research systems operate as stateless, linear pipelines, generating outputs without maintaining a persistent understanding of the research landscape. They process papers sequentially, propose ideas without structured gap analysis, and lack mechanisms for agents to verify or refine each other's findings. We present AutoProf (Autonomous Professor), a multi-agent orchestration framework where specialized agents provide end-to-end AI research supervision driven by human interests, from literature review through gap discovery, method development, evaluation, and paper writing, via autonomous exploration and self-correcting updates. Unlike sequential pipelines, AutoProf maintains a continuously evolving Research World Model implemented as a Knowledge Graph, capturing methods, benchmarks, limitations, and unexplored gaps as shared memory across agents. The framework introduces three contributions: first, structured gap discovery that decomposes methods into modules, evaluates them across benchmarks, and identifies module-level gaps; second, self-correcting discovery loops that analyze why modules succeed or fail, detect benchmark biases, and assess evaluation adequacy; third, self-improving development loops using cross-domain mechanism search to iteratively address failing components. All agents operate under a consensus mechanism where findings are validated before being committed to the shared model. The framework is model-agnostic, supports mainstream large language models, and scales elastically with token budget from lightweight exploration to full-scale investigation.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
The Luna Bound Propagator for Formal Analysis of Neural Networks
arXiv:2603.23878v1 Announce Type: new
Abstract: The parameterized CROWN analysis, a.k.a., alpha-CROWN, has emerged as a practically successful bound propagation method for neural network verification. However, existing implementations of alpha-CROWN are limited to Python, which complicates integration into existing DNN verifiers and long-term production-level systems. We introduce Luna, a new bound propagator implemented in C++. Luna supports Interval Bound Propagation, the CROWN analysis, and the alpha-CROWN analysis over a general computational graph. We describe the architecture of Luna and show that it is competitive with the state-of-the-art alpha-CROWN implementation in terms of both bound tightness and computational efficiency on benchmarks from VNN-COMP 2025.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization
arXiv:2603.23566v1 Announce Type: new
Abstract: AscendC (Ascend C) operator optimization on Huawei Ascend neural processing units (NPUs) faces a two-fold knowledge bottleneck: unlike the CUDA ecosystem, there are few public reference implementations to learn from, and performance hinges on a coupled two-part artifact - a host-side tiling program that orchestrates data movement and a kernel program that schedules and pipelines instructions. We present AscendOptimizer, an episodic agent that bootstraps this missing expertise by turning execution into experience. On the host side, AscendOptimizer performs profiling-in-the-loop evolutionary search to discover valid and high-performing tiling and data-movement configurations directly from hardware feedback. On the kernel side, it mines transferable optimization motifs by rewinding optimized kernels - systematically de-optimizing them to synthesize instructive "bad-to-good" trajectories - and distills these motifs into a retrievable experience bank for guided rewriting. By alternating host tuning and kernel rewriting in a closed loop, AscendOptimizer steadily expands feasibility and pushes latency down. On a benchmark of 127 real AscendC operators, AscendOptimizer achieves a 1.19x geometric-mean speedup over the open-source baseline, with 49.61% of operators outperforming their references, outperforming strong agent and search baselines.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Polynomial Speedup in Diffusion Models with the Multilevel Euler-Maruyama Method
arXiv:2603.24594v1 Announce Type: cross
Abstract: We introduce the Multilevel Euler-Maruyama (ML-EM) method compute solutions of SDEs and ODEs using a range of approximators $f^1,\dots,f^k$ to the drift $f$ with increasing accuracy and computational cost, only requiring a few evaluations of the most accurate $f^k$ and many evaluations of the less costly $f^1,\dots,f^{k-1}$. If the drift lies in the so-called Harder than Monte Carlo (HTMC) regime, i.e. it requires $\epsilon^{-\gamma}$ compute to be $\epsilon$-approximated for some $\gamma>2$, then ML-EM $\epsilon$-approximates the solution of the SDE with $\epsilon^{-\gamma}$ compute, improving over the traditional EM rate of $\epsilon^{-\gamma-1}$. In other terms it allows us to solve the SDE at the same cost as a single evaluation of the drift. In the context of diffusion models, the different levels $f^{1},\dots,f^{k}$ are obtained by training UNets of increasing sizes, and ML-EM allows us to perform sampling with the equivalent of a single evaluation of the largest UNet. Our numerical experiments confirm our theory: we obtain up to fourfold speedups for image generation on the CelebA dataset downscaled to 64x64, where we measure a $\gamma\approx2.5$. Given that this is a polynomial speedup, we expect even stronger speedups in practical applications which involve orders of magnitude larger networks.
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
An Invariant Compiler for Neural ODEs in AI-Accelerated Scientific Simulation
arXiv:2603.23861v1 Announce Type: new
Abstract: Neural ODEs are increasingly used as continuous-time models for scientific and sensor data, but unconstrained neural ODEs can drift and violate domain invariants (e.g., conservation laws), yielding physically implausible solutions. In turn, this can compound error in long-horizon prediction and surrogate simulation. Existing solutions typically aim to enforce invariance by soft penalties or other forms of regularization, which can reduce overall error but do not guarantee that trajectories will not leave the constraint manifold. We introduce the invariant compiler, a framework that enforces invariants by construction: it treats invariants as first-class types and uses an LLM-driven compilation workflow to translate a generic neural ODE specification into a structure-preserving architecture whose trajectories remain on the admissible manifold in continuous time (and up to numerical integration error in practice). This compiler view cleanly separates what must be preserved (scientific structure) from what is learned from data (dynamics within that structure). It provides a systematic design pattern for invariant-respecting neural surrogates across scientific domains.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents
arXiv:2603.22386v1 Announce Type: new
Abstract: Large language model (LLM)-based systems are becoming increasingly popular for solving tasks by constructing executable workflows that interleave LLM calls, information retrieval, tool use, code execution, memory updates, and verification. This survey reviews recent methods for designing and optimizing such workflows, which we treat as agentic computation graphs (ACGs). We organize the literature based on when workflow structure is determined, where structure refers to which components or agents are present, how they depend on each other, and how information flows between them. This lens distinguishes static methods, which fix a reusable workflow scaffold before deployment, from dynamic methods, which select, generate, or revise the workflow for a particular run before or during execution. We further organize prior work along three dimensions: when structure is determined, what part of the workflow is optimized, and which evaluation signals guide optimization (e.g., task metrics, verifier signals, preferences, or trace-derived feedback). We also distinguish reusable workflow templates, run-specific realized graphs, and execution traces, separating reusable design choices from the structures actually deployed in a given run and from realized runtime behavior. Finally, we outline a structure-aware evaluation perspective that complements downstream task metrics with graph-level properties, execution cost, robustness, and structural variation across inputs. Our goal is to provide a clear vocabulary, a unified framework for positioning new methods, a more comparable view of existing body of literature, and a more reproducible evaluation standard for future work in workflow optimizations for LLM agents.
Fonte: arXiv cs.AI
Applications • Score 85
Computational Arbitrage in AI Model Markets
arXiv:2603.22404v1 Announce Type: new
Abstract: Consider a market of competing model providers selling query access to models with varying costs and capabilities. Customers submit problem instances and are willing to pay up to a budget for a verifiable solution. An arbitrageur efficiently allocates inference budget across providers to undercut the market, thus creating a competitive offering with no model-development risk. In this work, we initiate the study of arbitrage in AI model markets, empirically demonstrating the viability of arbitrage and illustrating its economic consequences. We conduct an in-depth case study of SWE-bench GitHub issue resolution using two representative models, GPT-5 mini and DeepSeek v3.2. In this verifiable domain, simple arbitrage strategies generate net profit margins of up to 40%. Robust arbitrage strategies that generalize across different domains remain profitable. Distillation further creates strong arbitrage opportunities, potentially at the expense of the teacher model's revenue. Multiple competing arbitrageurs drive down consumer prices, reducing the marginal revenue of model providers. At the same time, arbitrage reduces market segmentation and facilitates market entry for smaller model providers by enabling earlier revenue capture. Our results suggest that arbitrage can be a powerful force in AI model markets with implications for model development, distillation, and deployment.
Fonte: arXiv cs.AI
RL • Score 85
CoMaTrack: Competitive Multi-Agent Game-Theoretic Tracking with Vision-Language-Action Models
arXiv:2603.22846v1 Announce Type: new
Abstract: Embodied Visual Tracking (EVT), a core dynamic task in embodied intelligence, requires an agent to precisely follow a language-specified target. Yet most existing methods rely on single-agent imitation learning, suffering from costly expert data and limited generalization due to static training environments. Inspired by competition-driven capability evolution, we propose CoMaTrack, a competitive game-theoretic multi-agent reinforcement learning framework that trains agents in a dynamic adversarial setting with competitive subtasks, yielding stronger adaptive planning and interference-resilient strategies. We further introduce CoMaTrack-Bench, the first benchmark for competitive EVT, featuring game scenarios between a tracker and adaptive opponents across diverse environments and instructions, enabling standardized robustness evaluation under active adversarial interactions. Experiments show that CoMaTrack achieves state-of-the-art results on both standard benchmarks and CoMaTrack-Bench. Notably, a 3B VLM trained with our framework surpasses previous single-agent imitation learning methods based on 7B models on the challenging EVT-Bench, achieving 92.1% in STT, 74.2% in DT, and 57.5% in AT. The benchmark code will be available at https://github.com/wlqcode/CoMaTrack-Bench
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Three Creates All: You Only Sample 3 Steps
arXiv:2603.22375v1 Announce Type: new
Abstract: Diffusion models deliver high-fidelity generation but remain slow at inference time due to many sequential network evaluations. We find that standard timestep conditioning becomes a key bottleneck for few-step sampling. Motivated by layer-dependent denoising dynamics, we propose Multi-layer Time Embedding Optimization (MTEO), which freeze the pretrained diffusion backbone and distill a small set of step-wise, layer-wise time embeddings from reference trajectories. MTEO is plug-and-play with existing ODE solvers, adds no inference-time overhead, and trains only a tiny fraction of parameters. Extensive experiments across diverse datasets and backbones show state-of-the-art performance in the few-step sampling and substantially narrow the gap between distillation-based and lightweight methods. Code will be available.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
MemCollab: Cross-Agent Memory Collaboration via Contrastive Trajectory Distillation
arXiv:2603.23234v1 Announce Type: new
Abstract: Large language model (LLM)-based agents rely on memory mechanisms to reuse knowledge from past problem-solving experiences. Existing approaches typically construct memory in a per-agent manner, tightly coupling stored knowledge to a single model's reasoning style. In modern deployments with heterogeneous agents, a natural question arises: can a single memory system be shared across different models? We found that naively transferring memory between agents often degrades performance, as such memory entangles task-relevant knowledge with agent-specific biases. To address this challenge, we propose MemCollab, a collaborative memory framework that constructs agent-agnostic memory by contrasting reasoning trajectories generated by different agents on the same task. This contrastive process distills abstract reasoning constraints that capture shared task-level invariants while suppressing agent-specific artifacts. We further introduce a task-aware retrieval mechanism that conditions memory access on task category, ensuring that only relevant constraints are used at inference time. Experiments on mathematical reasoning and code generation benchmarks demonstrate that MemCollab consistently improves both accuracy and inference-time efficiency across diverse agents, including cross-modal-family settings. Our results show that the collaboratively constructed memory can function as a shared reasoning resource for diverse LLM-based agents.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
AEGIS: An Operational Infrastructure for Post-Market Governance of Adaptive Medical AI Under US and EU Regulations
arXiv:2603.22322v1 Announce Type: new
Abstract: Machine learning systems deployed in medical devices require governance frameworks that ensure safety while enabling continuous improvement. Regulatory bodies including the FDA and European Union have introduced mechanisms such as the Predetermined Change Control Plan (PCCP) and Post-Market Surveillance (PMS) to manage iterative model updates without repeated submissions. This paper presents AI/ML Evaluation and Governance Infrastructure for Safety (AEGIS), a governance framework applicable to any healthcare AI system. AEGIS comprises three modules, i.e., dataset assimilation and retraining, model monitoring, and conditional decision, that operationalize FDA PCCP and EU AI Act Article 43(4) provisions. We implement a four-category deployment decision taxonomy (APPROVE, CONDITIONAL APPROVAL, CLINICAL REVIEW, REJECT) with an independent PMS ALARM signal, enabling detection of the critical state in which no deployable model exists while the released model is simultaneously at risk.
To illustrate how AEGIS can be instantiated across heterogeneous clinical contexts, we provide two examples: sepsis prediction from electronic health records and brain tumor segmentation from medical imaging. Both cases use identical governance architecture, differing only in configuration. Across 11 simulated iterations on the sepsis example, AEGIS yielded 8 APPROVE, 1 CONDITIONAL APPROVAL, 1 CLINICAL REVIEW, and 1 REJECT decision, exercising all four categories. ALARM signals were co-issued at iterations 8 and 10, including the critical state where no deployable model exists and the released model is simultaneously failing. AEGIS detected drift before observable performance degradation. These results demonstrate that AEGIS translates regulatory change-control concepts into executable governance procedures, supporting safe continuous learning for adaptive medical AI across diverse clinical applications.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
KALAVAI: Predicting When Independent Specialist Fusion Works -- A Quantitative Model for Post-Hoc Cooperative LLM Training
arXiv:2603.22755v1 Announce Type: new
Abstract: Independently trained domain specialists can be fused post-hoc into a single model that outperforms any individual specialist, and the gain is predictable: gain = 0.82 x divergence - 2.72 (R^2 = 0.856, n=6, 3-26% divergence). This enables practitioners to estimate cooperative value before committing compute. Below ~3.3% divergence, gains approach zero.In the KALAVAI protocol, contributors fine-tune copies of a shared checkpoint independently, then submit for lightweight MoE routing (500 steps). Gains are consistent: +7.72% at 410M (+/-0.02%, 3 seeds), +7.49% at 1B (+/-0.01%, 3 seeds), +6.53% at 6.9B, each over the best specialist. The router matches domain-oracle routing within <10^{-5} nats. Cross-lingual fusion (Tamil/Yoruba/Welsh/Code) achieves +21.76%, with Yoruba perplexity falling 41.9 to 7.7. A 20-contributor federation achieves +16.71% (+/-0.07pp, 3 seeds).Three requirements bound the protocol. Shared initialisation is necessary: checkpoint mismatch degrades routing. Frozen layers are optional below ~10,000 steps and beneficial beyond. Learned routing is essential: uniform averaging degrades by -1.2% vs. best specialist, while any trained router achieves oracle-optimal assignment.
Fonte: arXiv cs.CL
RL • Score 85
WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement
arXiv:2603.22352v1 Announce Type: new
Abstract: Recent progress in reinforcement learning with verifiable rewards (RLVR) offers a practical path to self-improvement of language models, but existing methods face a key trade-off: endogenous self-play can drift over iterations, while corpus-grounded approaches rely on curated data environments. We present \textbf{WIST}, a \textbf{W}eb-grounded \textbf{I}terative \textbf{S}elf-play \textbf{T}ree framework for domain-targeted reasoning improvement that learns directly from the open web without requiring any pre-arranged domain corpus. WIST incrementally expands a domain tree for exploration, and retrieves and cleans path-consistent web corpus to construct a controllable training environment. It then performs Challenger--Solver self-play with verifiable rewards, and feeds learnability signals back to update node posteriors and guide subsequent exploration through an adaptive curriculum. Across four backbones, WIST consistently improves over the base models and typically outperforms both purely endogenous self-evolution and corpus-grounded self-play baselines, with the Overall gains reaching \textbf{+9.8} (\textit{Qwen3-4B-Base}) and \textbf{+9.7} (\textit{OctoThinker-8B}). WIST is also domain-steerable, improving \textit{Qwen3-8B-Base} by \textbf{+14.79} in medicine and \textit{Qwen3-4B-Base} by \textbf{+5.28} on PhyBench. Ablations further confirm the importance of WIST's key components for stable open-web learning. Our Code is available at https://github.com/lfy-123/WIST.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Empirical Comparison of Agent Communication Protocols for Task Orchestration
arXiv:2603.22823v1 Announce Type: new
Abstract: Context. Nowadays, artificial intelligence agent systems are transforming from single-tool interactions to complex multi-agent orchestrations. As a result, two competing communication protocols have emerged: a tool integration protocol that standardizes how agents invoke external tools, and an inter-agent delegation protocol that enables autonomous agents to discover and delegate tasks to one another. Despite widespread industry adoption by dozens of enterprise partners, no empirical comparison of these protocols exists in the literature. Objective. The goal of this work is to develop the first systematic benchmark comparing tool-integration-only, multi-agent delegation, and hybrid architectures across standardized queries at three complexity levels, and to quantify the trade-offs in response time, context window consumption, monetary cost, error recovery, and implementation complexity.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
DAQ: Delta-Aware Quantization for Post-Training LLM Weight Compression
arXiv:2603.22324v1 Announce Type: new
Abstract: We introduce Delta-Aware Quantization (DAQ), a data-free post-training quantization framework that preserves the knowledge acquired during post-training. Standard quantization objectives minimize reconstruction error but are agnostic to the base model, allowing quantization noise to disproportionately corrupt the small-magnitude parameter deltas ($\Delta W$) that encode post-training behavior -- an effect we analyze through the lens of quantization as implicit regularization. DAQ replaces reconstruction-based objectives with two delta-aware metrics -- Sign Preservation Rate and Cosine Similarity -- that directly optimize for directional fidelity of $\Delta W$, requiring only the base and post-trained weight matrices. In a pilot FP8 study, DAQ recovers style-specific capabilities lost under standard quantization while maintaining general performance.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Sparsely-Supervised Data Assimilation via Physics-Informed Schr\"odinger Bridge
arXiv:2603.22319v1 Announce Type: new
Abstract: Data assimilation (DA) for systems governed by partial differential equations (PDE) aims to reconstruct full spatiotemporal fields from sparse high-fidelity (HF) observations while respecting physical constraints. While full-grid low-fidelity (LF) simulations provide informative priors in multi-fidelity settings, recovering an HF field consistent with both sparse observations and the governing PDE typically requires per-instance test-time optimization, which becomes a major bottleneck in time-critical applications. To alleviate this, amortized reconstruction using generative models has recently been proposed; however, such approaches rely on full-field HF supervision during training, which is often impractical in real-world settings. From a more realistic perspective, we propose the Physics-Informed Conditional Schr\"odinger Bridge (PICSB), which transports an informative LF prior toward an observation-conditioned HF posterior without any additional inference-time guidance. To enable learning without HF endpoints, PICSB employs an iterative surrogate-endpoint refresh scheme, and directly incorporates PDE residuals into the training objective while enforcing observations via hard conditioning throughout sampling. Experiments on fluid PDE benchmarks demonstrate that PICSB enables extremely fast spatiotemporal field reconstruction while maintaining competitive accuracy under sparse HF supervision.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction
arXiv:2603.22910v1 Announce Type: new
Abstract: The increasing memory demand of the Key-Value (KV) cache poses a significant bottleneck for Large Language Models (LLMs) in long-context applications. Existing low-rank compression methods often rely on irreversible parameter transformations, sacrificing the flexibility to switch back to full-precision inference when memory is abundant. In this paper, we propose EchoKV, a flexible KV cache compression scheme that enables on-demand transitions between standard and compressed inference. Unlike traditional compression-decompression paradigms, EchoKV utilizes a lightweight network to reconstruct the residual KV components from a partial subset, leveraging intrinsic inter-layer and intra-layer similarities among attention heads. We further introduce a two-stage fine-tuning strategy that allows for rapid, low-cost training (e.g., ~1 A100 GPU-hour for a 7B model). Experimental results on LongBench and RULER demonstrate that EchoKV consistently outperforms existing methods across various compression ratios while maintaining high throughput for short-context scenarios.
Fonte: arXiv cs.CL
MLOps/Systems • Score 85
STEM Agent: A Self-Adapting, Tool-Enabled, Extensible Architecture for Multi-Protocol AI Agent Systems
arXiv:2603.22359v1 Announce Type: new
Abstract: Current AI agent frameworks commit early to a single interaction protocol, a fixed tool integration strategy, and static user models, limiting their deployment across diverse interaction paradigms. To address these constraints, we introduce STEM Agent (Self-adapting, Tool-enabled, Extensible, Multi-agent), a modular architecture inspired by biological pluripotency in which an undifferentiated agent core differentiates into specialized protocol handlers, tool bindings, and memory subsystems that compose into a fully functioning AI system. The framework unifies five interoperability protocols (A2A, AG-UI, A2UI, UCP, and AP2) behind a single gateway, introduces a Caller Profiler that continuously learns user preferences across more than twenty behavioral dimensions, externalizes all domain capabilities through the Model Context Protocol (MCP), and implements a biologically inspired skills acquisition system in which recurring interaction patterns crystallize into reusable agent skills through a maturation lifecycle analogous to cell differentiation. Complementing these capabilities, the memory system incorporates consolidation mechanisms, including episodic pruning, semantic deduplication, and pattern extraction, designed for sub-linear growth under sustained interaction. A comprehensive 413-test suite validates protocol handler behavior and component integration across all five architectural layers, completing in under three seconds.
Fonte: arXiv cs.AI
RL • Score 85
Emergency Preemption Without Online Exploration: A Decision Transformer Approach
arXiv:2603.22315v1 Announce Type: new
Abstract: Emergency vehicle (EV) response time is a critical determinant of survival outcomes, yet deployed signal preemption strategies remain reactive and uncontrollable. We propose a return-conditioned framework for emergency corridor optimization based on the Decision Transformer (DT). By casting corridor optimization as offline, return-conditioned sequence modeling, our approach (1) eliminates online environment interaction during policy learning, (2) enables dispatch-level urgency control through a single target-return scalar, and (3) extends to multi-agent settings via a Multi-Agent Decision Transformer (MADT) with graph attention for spatial coordination. On the LightSim simulator, DT reduces average EV travel time by 37.7% relative to fixed-timing preemption on a 4x4 grid (88.6 s vs. 142.3 s), achieving the lowest civilian delay (11.3 s/veh) and fewest EV stops (1.2) among all methods, including online RL baselines that require environment interaction. MADT further improves on larger grids, overtaking DT with 45.2% reduction on 8x8 via graph-attention coordination. Return conditioning produces a smooth dispatch interface: varying the target return from 100 to -400 trades EV travel time (72.4-138.2 s) against civilian delay (16.8-5.4 s/veh), requiring no retraining. A Constrained DT extension adds explicit civilian disruption budgets as a second control knob.
Fonte: arXiv cs.LG
Multimodal • Score 85
Tiny Inference-Time Scaling with Latent Verifiers
arXiv:2603.22492v1 Announce Type: new
Abstract: Inference-time scaling has emerged as an effective way to improve generative models at test time by using a verifier to score and select candidate outputs. A common choice is to employ Multimodal Large Language Models (MLLMs) as verifiers, which can improve performance but introduce substantial inference-time cost. Indeed, diffusion pipelines operate in an autoencoder latent space to reduce computation, yet MLLM verifiers still require decoding candidates to pixel space and re-encoding them into the visual embedding space, leading to redundant and costly operations. In this work, we propose Verifier on Hidden States (VHS), a verifier that operates directly on intermediate hidden representations of Diffusion Transformer (DiT) single-step generators. VHS analyzes generator features without decoding to pixel space, thereby reducing the per-candidate verification cost while improving or matching the performance of MLLM-based competitors. We show that, under tiny inference budgets with only a small number of candidates per prompt, VHS enables more efficient inference-time scaling reducing joint generation-and-verification time by 63.3%, compute FLOPs by 51% and VRAM usage by 14.5% with respect to a standard MLLM verifier, achieving a +2.7% improvement on GenEval at the same inference-time budget.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
Bridging the Gap Between Climate Science and Machine Learning in Climate Model Emulation
arXiv:2603.22320v1 Announce Type: new
Abstract: While climate models provide insights for climate decision-making, their use is constrained by significant computational and technical demands. Although machine learning (ML) emulators offer a way to bypass the high computational costs, their effective use remains challenging. The hurdles are diverse, ranging from limited accessibility and a lack of specialized knowledge to a general mistrust of ML methods that are perceived as insufficiently physical. Here, we introduce a framework to overcome these barriers by integrating both climate science and machine learning perspectives. We find that designing easy-to-adopt emulators that address a clearly defined task and demonstrating their reliability offers a promising path for bridging the gap between our two fields.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
All you need is spin: SU(2) equivariant variational quantum circuits based on spin networks
arXiv:2309.07250v2 Announce Type: replace-cross
Abstract: Variational algorithms require architectures that naturally constrain the optimization space to run efficiently. Geometric quantum machine learning achieves this goal by encoding group structure into parameterized quantum circuits to include the symmetries of a problem as an inductive bias. However, constructing such circuits is challenging as a concrete guiding principle has yet to emerge. In this paper, we propose the use of spin networks, a form of directed tensor network invariant under a group transformation, to devise SU(2) equivariant quantum circuit ans\"atze $\unicode{x2013}$ circuits possessing spin-rotation symmetry. By changing to the basis that block diagonalizes the SU(2) group action, these networks provide a natural building block for constructing parameterized equivariant quantum circuits. We prove that our construction is mathematically equivalent to other known constructions, such as those based on twirling and generalized permutations, but more direct to implement on quantum hardware. The efficacy of our constructed circuits is tested by solving the ground state problem of SU(2) symmetric Heisenberg models on the one-dimensional triangular lattice and the Kagome lattice. Our results highlight that our equivariant circuits boost the performance of quantum variational algorithms, indicating broader applicability to other real-world problems.
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
Towards The Implicit Bias on Multiclass Separable Data Under Norm Constraints
arXiv:2603.22824v1 Announce Type: cross
Abstract: Implicit bias induced by gradient-based algorithms is essential to the generalization of overparameterized models, yet its mechanisms can be subtle. This work leverages the Normalized Steepest Descent} (NSD) framework to investigate how optimization geometry shapes solutions on multiclass separable data. We introduce NucGD, a geometry-aware optimizer designed to enforce low rank structures through nuclear norm constraints. Beyond the algorithm itself, we connect NucGD with emerging low-rank projection methods, providing a unified perspective. To enable scalable training, we derive an efficient SVD-free update rule via asynchronous power iteration. Furthermore, we empirically dissect the impact of stochastic optimization dynamics, characterizing how varying levels of gradient noise induced by mini-batch sampling and momentum modulate the convergence toward the expected maximum margin solutions.Our code is accessible at: https://github.com/Tsokarsic/observing-the-implicit-bias-on-multiclass-seperable-data.
Fonte: arXiv stat.ML
Vision • Score 85
High Resolution Flood Extent Detection Using Deep Learning with Random Forest Derived Training Labels
arXiv:2603.22518v1 Announce Type: new
Abstract: Validation of flood models, used to support risk mitigation strategies, remains challenging due to limited observations during extreme events. High-frequency, high-resolution optical imagery (~3 m), such as PlanetScope, offers new opportunities for flood mapping, although applications remain limited by cloud cover and the lack of labeled training data during disasters. To address this, we develop a flood mapping framework that integrates PlanetScope optical imagery with topographic features using machine learning (ML) and deep learning (DL) algorithms. A Random Forest model was applied to expert-annotated flood masks to generate training labels for DL models, U-Net. Two U-Net models with ResNet18 backbone were trained using optical imagery only (4 bands) and optical imagery combined with Height Above Nearest Drainage (HAND) and topographic slope (6 bands). Hurricane Ida (September 2021), which caused catastrophic flooding across the eastern United States, including the New York City metropolitan area, was used as an example to evaluate the framework. Results demonstrate that the U-Net model with topographic features achieved very close performance to the optical-only configuration (F1=0.92 and IoU=0.85 by both modeling scenarios), indicating that HAND and slope provide only marginal value to inundation extent detection. The proposed framework offers a scalable and label-efficient approach for mapping inundation extent that enables modeling under data-scarce flood scenarios.
Fonte: arXiv cs.CV
Multimodal • Score 85
Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off
arXiv:2603.22607v1 Announce Type: new
Abstract: Recent advances in Virtual Try-On (VTON) and Virtual Try-Off (VTOFF) have greatly improved photo-realistic fashion synthesis and garment reconstruction. However, existing datasets remain static, lacking instruction-driven editing for controllable and interactive fashion generation. In this work, we introduce the Dress Editing Dataset (Dress-ED), the first large-scale benchmark that unifies VTON, VTOFF, and text-guided garment editing within a single framework. Each sample in Dress-ED includes an in-shop garment image, the corresponding person image wearing the garment, their edited counterparts, and a natural-language instruction of the desired modification. Built through a fully automated multimodal pipeline that integrates MLLM-based garment understanding, diffusion-based editing, and LLM-guided verification, Dress-ED comprises over 146k verified quadruplets spanning three garment categories and seven edit types, including both appearance (e.g., color, pattern, material) and structural (e.g., sleeve length, neckline) modifications. Based on this benchmark, we further propose a unified multimodal diffusion framework that jointly reasons over linguistic instructions and visual garment cues, serving as a strong baseline for instruction-driven VTON and VTOFF. Dataset and code will be made publicly available.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Separating Diagnosis from Control: Auditable Policy Adaptation in Agent-Based Simulations with LLM-Based Diagnostics
arXiv:2603.22904v1 Announce Type: new
Abstract: Mitigating elderly loneliness requires policy interventions that achieve both adaptability and auditability. Existing methods struggle to reconcile these objectives: traditional agent-based models suffer from static rigidity, while direct large language model (LLM) controllers lack essential traceability. This work proposes a three-layer framework that separates diagnosis from control to achieve both properties simultaneously. LLMs operate strictly as diagnostic instruments that assess population state and generate structured risk evaluations, while deterministic formulas with explicit bounds translate these assessments into traceable parameter updates. This separation ensures that every policy decision can be attributed to inspectable rules while maintaining adaptive response to emergent needs. We validate the framework through systematic ablation across five experimental conditions in elderly care simulation. Results demonstrate that explicit control rules outperform end-to-end black-box LLM approaches by 11.7\% while preserving full auditability, confirming that transparency need not compromise adaptive performance.
Fonte: arXiv cs.AI
RL • Score 85
MAGICIAN: Efficient Long-Term Planning with Imagined Gaussians for Active Mapping
arXiv:2603.22650v1 Announce Type: new
Abstract: Active mapping aims to determine how an agent should move to efficiently reconstruct an unknown environment. Most existing approaches rely on greedy next-best-view prediction, resulting in inefficient exploration and incomplete scene reconstruction. To address this limitation, we introduce MAGICIAN, a novel long-term planning framework that maximizes accumulated surface coverage gain through Imagined Gaussians, a scene representation derived from a pre-trained occupancy network with strong structural priors. This representation enables efficient computation of coverage gain for any novel viewpoint via fast volumetric rendering, allowing its integration into a tree-search algorithm for long-horizon planning. We update Imagined Gaussians and refine the planned trajectory in a closed-loop manner. Our method achieves state-of-the-art performance across indoor and outdoor benchmarks with varying action spaces, demonstrating the critical advantage of long-term planning in active mapping.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
A graph neural network based chemical mechanism reduction method for combustion applications
arXiv:2603.22318v1 Announce Type: new
Abstract: Direct numerical simulations of turbulent reacting flows involving millions of grid points and detailed chemical mechanisms with hundreds of species and thousands of reactions are computationally prohibitive. To address this challenge, we present two data-driven chemical mechanism reduction formulations based on graph neural networks (GNNs) with message-passing transformer layers that learn nonlinear dependencies among species and reactions. The first formulation, GNN-SM, employs a pre-trained surrogate model to guide reduction across a broad range of reactor conditions. The second formulation, GNN-AE, uses an autoencoder formulation to obtain highly compact mechanisms that remain accurate within the thermochemical regimes used during training. The approaches are demonstrated on detailed mechanisms for methane (53 species, 325 reactions), ethylene (96 species, 1054 reactions), and iso-octane (1034 species, 8453 reactions). GNN-SM achieves reductions comparable to the established graph-based method DRGEP while maintaining accuracy across a wide range of thermochemical states. In contrast, GNN-AE achieves up to 95% reduction in species and reactions and outperforms DRGEP within its target conditions. Overall, the proposed framework provides an automated, machine-learning-based pathway for chemical mechanism reduction that can complement traditional expert-guided analytical approaches.
Fonte: arXiv cs.LG
Vision • Score 85
Color When It Counts: Grayscale-Guided Online Triggering for Always-On Streaming Video Sensing
arXiv:2603.22466v1 Announce Type: new
Abstract: Always-on sensing is essential for next-generation edge/wearable AI systems, yet continuous high-fidelity RGB video capture remains prohibitively expensive for resource-constrained mobile and edge platforms. We present a new paradigm for efficient streaming video understanding: grayscale-always, color-on-demand. Through preliminary studies, we discover that color is not always necessary. Sparse RGB frames suffice for comparable performance when temporal structure is preserved via continuous grayscale streams. Building on this insight, we propose ColorTrigger, an online training-free trigger that selectively activates color capture based on windowed grayscale affinity analysis. Designed for real-time edge deployment, ColorTrigger uses lightweight quadratic programming to detect chromatic redundancy causally, coupled with credit-budgeted control and dynamic token routing to jointly reduce sensing and inference costs. On streaming video understanding benchmarks, ColorTrigger achieves 91.6% of full-color baseline performance while using only 8.1% RGB frames, demonstrating substantial color redundancy in natural videos and enabling practical always-on video sensing on resource-constrained devices.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Cloud-Edge Collaborative Large Models for Robust Photovoltaic Power Forecasting
arXiv:2603.22343v1 Announce Type: new
Abstract: Photovoltaic (PV) power forecasting in edge-enabled grids requires balancing forecasting accuracy, robustness under weather-driven distribution shifts, and strict latency constraints. Local specialized models are efficient for routine conditions but often degrade under rare ramp events and unseen weather patterns, whereas always relying on cloud-side large models incurs substantial communication delay and cloud overhead. To address this challenge, we propose a risk-aware cloud-edge collaborative framework for latency-sensitive PV forecasting. The framework integrates a site-specific expert predictor for routine cases, a lightweight edge-side model for enhanced local inference, and a cloud-side large retrieval model that provides matched historical context when needed through a retrieval-prediction pipeline. A lightweight screening module estimates predictive uncertainty, out-of-distribution risk, weather mutation intensity, and model disagreement, while a Lyapunov-guided router selectively escalates inference to the edge-small or cloud-assisted branches under long-term latency, communication, and cloud-usage constraints. The outputs of the activated branches are combined through adaptive fusion. Experiments on two real-world PV datasets demonstrate a favorable overall trade-off among forecasting accuracy, routing quality, robustness, and system efficiency.
Fonte: arXiv cs.LG
Vision • Score 85
Efficient Universal Perception Encoder
arXiv:2603.22387v1 Announce Type: new
Abstract: Running AI models on smart edge devices can unlock versatile user experiences, but presents challenges due to limited compute and the need to handle multiple tasks simultaneously. This requires a vision encoder with small size but powerful and versatile representations. We present our method, Efficient Universal Perception Encoder (EUPE), which offers both inference efficiency and universally good representations for diverse downstream tasks. We achieve this by distilling from multiple domain-expert foundation vision encoders. Unlike previous agglomerative methods that directly scale down from multiple teachers to an efficient encoder, we demonstrate the importance of first scaling up to a large proxy teacher and then scaling down from this single teacher. Experiments show that EUPE achieves on-par or better performance than individual domain experts of the same size on diverse task domains and also outperforms previous agglomerative encoders. We will release the full family of EUPE models and the code to foster future research.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
A Theoretical Framework for Energy-Aware Gradient Pruning in Federated Learning
arXiv:2603.22465v1 Announce Type: new
Abstract: Federated Learning (FL) is constrained by the communication and energy limitations of decentralized edge devices. While gradient sparsification via Top-K magnitude pruning effectively reduces the communication payload, it remains inherently energy-agnostic. It assumes all parameter updates incur identical downstream transmission and memory-update costs, ignoring hardware realities. We formalize the pruning process as an energy-constrained projection problem that accounts for the hardware-level disparities between memory-intensive and compute-efficient operations during the post-backpropagation phase. We propose Cost-Weighted Magnitude Pruning (CWMP), a selection rule that prioritizes parameter updates based on their magnitude relative to their physical cost. We demonstrate that CWMP is the optimal greedy solution to this constrained projection and provide a probabilistic analysis of its global energy efficiency. Numerical results on a non-IID CIFAR-10 benchmark show that CWMP consistently establishes a superior performance-energy Pareto frontier compared to the Top-K baseline.
Fonte: arXiv cs.LG
RL • Score 85
Describe-Then-Act: Proactive Agent Steering via Distilled Language-Action World Models
arXiv:2603.23149v1 Announce Type: new
Abstract: Deploying safety-critical agents requires anticipating the consequences of actions before they are executed. While world models offer a paradigm for this proactive foresight, current approaches relying on visual simulation incur prohibitive latencies, often exceeding several seconds per step. In this work, we challenge the assumption that visual processing is necessary for failure prevention. We show that a trained policy's latent state, combined with its planned actions, already encodes sufficient information to anticipate action outcomes, making visual simulation redundant for failure prevention. To this end, we introduce DILLO (DIstiLLed Language-ActiOn World Model), a fast steering layer that shifts the paradigm from "simulate-then-act" to "describe-then-act." DILLO is trained via cross-modal distillation, where a privileged Vision Language Model teacher annotates offline trajectories and a latent-conditioned Large Language Model student learns to predict semantic outcomes. This creates a text-only inference path, bypassing heavy visual generation entirely, achieving a 14x speedup over baselines. Experiments on MetaWorld and LIBERO demonstrate that DILLO produces high-fidelity descriptions of the next state and is able to steer the policy, improving episode success rate by up to 15 pp and 9.3 pp on average across tasks.
Fonte: arXiv cs.AI
NLP/LLMs • Score 90
Knowledge Access Beats Model Size: Memory Augmented Routing for Persistent AI Agents
arXiv:2603.23013v1 Announce Type: new
Abstract: Production AI agents frequently receive user-specific queries that are highly repetitive, with up to 47\% being semantically similar to prior interactions, yet each query is typically processed with the same computational cost. We argue that this redundancy can be exploited through conversational memory, transforming repetition from a cost burden into an efficiency advantage. We propose a memory-augmented inference framework in which a lightweight 8B-parameter model leverages retrieved conversational context to answer all queries via a low-cost inference path. Without any additional training or labeled data, this approach achieves 30.5\% F1, recovering 69\% of the performance of a full-context 235B model while reducing effective cost by 96\%. Notably, a 235B model without memory (13.7\% F1) underperforms even the standalone 8B model (15.4\% F1), indicating that for user-specific queries, access to relevant knowledge outweighs model scale. We further analyze the role of routing and confidence. At practical confidence thresholds, routing alone already directs 96\% of queries to the small model, but yields poor accuracy (13.0\% F1) due to confident hallucinations. Memory does not substantially alter routing decisions; instead, it improves correctness by grounding responses in retrieved user-specific information. As conversational memory accumulates over time, coverage of recurring topics increases, further narrowing the performance gap. We evaluate on 152 LoCoMo questions (Qwen3-8B/235B) and 500 LongMemEval questions. Incorporating hybrid retrieval (BM25 + cosine similarity) improves performance by an additional +7.7 F1, demonstrating that retrieval quality directly enhances end-to-end system performance. Overall, our results highlight that memory, rather than model size, is the primary driver of accuracy and efficiency in persistent AI agents.
Fonte: arXiv cs.CL
Theory/Optimization • Score 85
A Multi-Task Targeted Learning Framework for Lithium-Ion Battery State-of-Health and Remaining Useful Life
arXiv:2603.22323v1 Announce Type: new
Abstract: Accurately predicting the state-of-health (SOH) and remaining useful life (RUL) of lithium-ion batteries is crucial for ensuring the safe and efficient operation of electric vehicles while minimizing associated risks. However, current deep learning methods are limited in their ability to selectively extract features and model time dependencies for these two parameters. Moreover, most existing methods rely on traditional recurrent neural networks, which have inherent shortcomings in long-term time-series modeling. To address these issues, this paper proposes a multi-task targeted learning framework for SOH and RUL prediction, which integrates multiple neural networks, including a multi-scale feature extraction module, an improved extended LSTM, and a dual-stream attention module. First, a feature extraction module with multi-scale CNNs is designed to capture detailed local battery decline patterns. Secondly, an improved extended LSTM network is employed to enhance the model's ability to retain long-term temporal information, thus improving temporal relationship modeling. Building on this, the dual-stream attention module-comprising polarized attention and sparse attention to selectively focus on key information relevant to SOH and RUL, respectively, by assigning higher weights to important features. Finally, a many-to-two mapping is achieved through the dual-task layer. To optimize the model's performance and reduce the need for manual hyperparameter tuning, the Hyperopt optimization algorithm is used. Extensive comparative experiments on battery aging datasets demonstrate that the proposed method reduces the average RMSE for SOH and RUL predictions by 111.3\% and 33.0\%, respectively, compared to traditional and state-of-the-art methods.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
PersonalQ: Select, Quantize, and Serve Personalized Diffusion Models for Efficient Inference
arXiv:2603.22943v1 Announce Type: new
Abstract: Personalized text-to-image generation lets users fine-tune diffusion models into repositories of concept-specific checkpoints, but serving these repositories efficiently is difficult for two reasons: natural-language requests are often ambiguous and can be misrouted to visually similar checkpoints, and standard post-training quantization can distort the fragile representations that encode personalized concepts. We present PersonalQ, a unified framework that connects checkpoint selection and quantization through a shared signal -- the checkpoint's trigger token. Check-in performs intent-aligned selection by combining intent-aware hybrid retrieval with LLM-based reranking over checkpoint context and asks a brief clarification question only when multiple intents remain plausible; it then rewrites the prompt by inserting the selected checkpoint's canonical trigger. Complementing this, Trigger-Aware Quantization (TAQ) applies trigger-aware mixed precision in cross-attention, preserving trigger-conditioned key/value rows (and their attention weights) while aggressively quantizing the remaining pathways for memory-efficient inference. Experiments show that PersonalQ improves intent alignment over retrieval and reranking baselines, while TAQ consistently offers a stronger compression-quality trade-off than prior diffusion PTQ methods, enabling scalable serving of personalized checkpoints without sacrificing fidelity.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Towards Automated Community Notes Generation with Large Vision Language Models for Combating Contextual Deception
arXiv:2603.22453v1 Announce Type: new
Abstract: Community Notes have emerged as an effective crowd-sourced mechanism for combating online deception on social media platforms. However, its reliance on human contributors limits both the timeliness and scalability. In this work, we study the automated Community Notes generation method for image-based contextual deception, where an authentic image is paired with misleading context (e.g., time, entity, and event). Unlike prior work that primarily focuses on deception detection (i.e., judging whether a post is true or false in a binary manner), Community Notes-style systems need to generate concise and grounded notes that help users recover the missing or corrected context. This problem remains underexplored due to three reasons: (i) datasets that support the research are scarce; (ii) methods must handle the dynamic nature of contextual deception; (iii) evaluation is difficult because standard metrics do not capture whether notes actually improve user understanding. To address these gaps, we curate a real-world dataset, XCheck, comprising X posts with associated Community Notes and external contexts. We further propose the Automated Context-Corrective Note generation method, named ACCNote, which is a retrieval-augmented, multi-agent collaboration framework built on large vision-language models. Finally, we introduce a new evaluation metric, Context Helpfulness Score (CHS), that aligns with user study outcomes rather than relying on lexical overlap. Experiments on our XCheck dataset show that the proposed ACCNote improves both deception detection and note generation performance over baselines, and exceeds a commercial tool GPT5-mini. Together, our dataset, method, and metric advance practical automated generation of context-corrective notes toward more responsible online social networks.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
FAAR: Format-Aware Adaptive Rounding for NVFP4
arXiv:2603.22370v1 Announce Type: new
Abstract: Deploying large language models (LLMs) on edge devices requires extremely low-bit quantization. Ultra-low precision formats such as NVFP4 offer a promising solution for reducing memory footprint and accelerating computation. However, existing quantization methods typically rely on conventional rounding strategies and fail to account for the non-uniformity of the NVFP4 numerical grid, resulting in suboptimal rounding decisions and amplified quantization errors. To address this, we propose Format-Aware Adaptive Rounding (FAAR), a learnable rounding strategy tailored for the NVFP4 format. Unlike conventional quantization paradigms, FAAR explicitly incorporates the non-uniform NVFP4 grid into the optimization process. By adaptively adjusting rounding decisions guided by loss gradients, our method effectively approximates the theoretically optimal quantization. To complement FAAR, we introduce a 2-stages Format Alignment (2FA) fine-tuning scheme that aligns LLM parameters layer-by-layer to the NVFP4 numerical space, further narrowing the performance gap. Remarkably, this learnable optimization incurs a minimal training overhead of only 4 GPU hours on Llama3-1B. Extensive experiments demonstrate the effectiveness of our approach. Compared with Round-to-Nearest (RTN), our method reduces perplexity on WikiText-2 from 14.28 to 12.60 on Llama3-1B and from 23.06 to 21.27 on Qwen3-1.7B. Additionally, our method consistently outperforms state-of-the-art approaches across various zero-shot downstream tasks.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Efficient Embedding-based Synthetic Data Generation for Complex Reasoning Tasks
arXiv:2603.22294v1 Announce Type: new
Abstract: Synthetic Data Generation (SDG), leveraging Large Language Models (LLMs), has recently been recognized and broadly adopted as an effective approach to improve the performance of smaller but more resource and compute efficient LLMs through fine-tuning. A key challenge in SDG is ensuring the quality and diversity of the generated data. In this paper, we analyze the diversity and distribution of generated data in the embedding space, and demonstrate a strong correlation between the density of examples within a specific neighborhood and the accuracy of predictions on examples drawn from that region. Building on this insight, we present a targeted pipeline for embedding-based sampling that enhances data diversity and consistently improves performance across several benchmarks.
Fonte: arXiv cs.LG
Multimodal • Score 95
A Multi-Modal CNN-LSTM Framework with Multi-Head Attention and Focal Loss for Real-Time Elderly Fall Detection
arXiv:2603.22313v1 Announce Type: new
Abstract: The increasing global aging population has intensified the demand for reliable health monitoring systems, particularly those capable of detecting critical events such as falls among elderly individuals. Traditional fall detection approaches relying on single-modality acceleration data suffer from high false alarm rates, while conventional machine learning methods require extensive hand-crafted feature engineering. This paper proposes a novel multi-modal deep learning framework, MultiModalFallDetector, designed for real-time elderly fall detection using wearable sensors. Our approach integrates multiple innovations: a multi-scale CNN-based feature extractor capturing motion dynamics at varying temporal resolutions; fusion of tri-axial accelerometer, gyroscope, and four-channel physiological signals; incorporation of a multi-head self-attention mechanism for dynamic temporal weighting; adoption of Focal Loss to mitigate severe class imbalance; introduction of an auxiliary activity classification task for regularization; and implementation of transfer learning from UCI HAR to SisFall dataset. Extensive experiments on the SisFall dataset, which includes real-world simulated fall trials from elderly participants (aged 60-85), demonstrate that our framework achieves an F1-score of 98. 7, Recall of 98. 9, and AUC-ROC of 99. 4, significantly outperforming baseline methods including traditional machine learning and standard deep learning approaches. The model maintains sub- 50ms inference latency on edge devices, confirming its suitability for real-time deployment in geriatric care settings.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Distributed Gradient Clustering: Convergence and the Effect of Initialization
arXiv:2603.20507v1 Announce Type: new
Abstract: We study the effects of center initialization on the performance of a family of distributed gradient-based clustering algorithms introduced in [1], that work over connected networks of users. In the considered scenario, each user contains a local dataset and communicates only with its immediate neighbours, with the aim of finding a global clustering of the joint data. We perform extensive numerical experiments, evaluating the effects of center initialization on the performance of our family of methods, demonstrating that our methods are more resilient to the effects of initialization, compared to centralized gradient clustering [2]. Next, inspired by the $K$-means++ initialization [3], we propose a novel distributed center initialization scheme, which is shown to improve the performance of our methods, compared to the baseline random initialization.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Sinkhorn Based Associative Memory Retrieval Using Spherical Hellinger Kantorovich Dynamics
arXiv:2603.20656v1 Announce Type: new
Abstract: We propose a dense associative memory for empirical measures (weighted point clouds). Stored patterns and queries are finitely supported probability measures, and retrieval is defined by minimizing a Hopfield-style log-sum-exp energy built from the debiased Sinkhorn divergence. We derive retrieval dynamics as a spherical Hellinger Kantorovich (SHK) gradient flow, which updates both support locations and weights. Discretizing the flow yields a deterministic algorithm that uses Sinkhorn potentials to compute barycentric transport steps and a multiplicative simplex reweighting. Under local separation and PL-type conditions we prove basin invariance, geometric convergence to a local minimizer, and a bound showing the minimizer remains close to the corresponding stored pattern. Under a random pattern model, we further show that these Sinkhorn basins are disjoint with high probability, implying exponential capacity in the ambient dimension. Experiments on synthetic Gaussian point-cloud memories demonstrate robust recovery from perturbed queries versus a Euclidean Hopfield-type baseline.
Fonte: arXiv stat.ML
RL • Score 85
Understanding Behavior Cloning with Action Quantization
arXiv:2603.20538v1 Announce Type: new
Abstract: Behavior cloning is a fundamental paradigm in machine learning, enabling policy learning from expert demonstrations across robotics, autonomous driving, and generative models. Autoregressive models like transformer have proven remarkably effective, from large language models (LLMs) to vision-language-action systems (VLAs). However, applying autoregressive models to continuous control requires discretizing actions through quantization, a practice widely adopted yet poorly understood theoretically. This paper provides theoretical foundations for this practice. We analyze how quantization error propagates along the horizon and interacts with statistical sample complexity. We show that behavior cloning with quantized actions and log-loss achieves optimal sample complexity, matching existing lower bounds, and incurs only polynomial horizon dependence on quantization error, provided the dynamics are stable and the policy satisfies a probabilistic smoothness condition. We further characterize when different quantization schemes satisfy or violate these requirements, and propose a model-based augmentation that provably improves the error bound without requiring policy smoothness. Finally, we establish fundamental limits that jointly capture the effects of quantization error and statistical complexity.
Fonte: arXiv cs.LG
NLP/LLMs • Score 90
ConsRoute:Consistency-Aware Adaptive Query Routing for Cloud-Edge-Device Large Language Models
arXiv:2603.21237v1 Announce Type: new
Abstract: Large language models (LLMs) deliver impressive capabilities but incur substantial inference latency and cost, which hinders their deployment in latency-sensitive and resource-constrained scenarios. Cloud-edge-device collaborative inference has emerged as a promising paradigm by dynamically routing queries to models of different capacities across tiers. In this paper, we propose ConsRoute, a lightweight, semantic-aware, and adaptive routing framework that significantly improves inference efficiency while minimizing impact on response quality. Unlike prior routing methods that rely on predicting coarse-grained output quality gaps, ConsRoute leverages a reranker to directly assess the semantic consistency between responses generated by models at different tiers, yielding fine-grained soft supervision signals for routing. To minimize device-side overhead, ConsRoute reuses hidden states from the LLM prefilling stage as compact query representations, avoiding additional encoders or inference passes. Furthermore, these representations are clustered, and Bayesian optimization is employed to learn cluster-specific routing thresholds that dynamically balance quality, latency, and cost under heterogeneous query distributions. Extensive experiments demonstrate that ConsRoute achieves near-cloud performance (>=95%) while reducing end-to-end latency and inference cost by nearly 40%, consistently outperforming existing routing baselines in both response quality and system efficiency.
Fonte: arXiv cs.AI
RL • Score 85
Profit is the Red Team: Stress-Testing Agents in Strategic Economic Interactions
arXiv:2603.20925v1 Announce Type: new
Abstract: As agentic systems move into real-world deployments, their decisions increasingly depend on external inputs such as retrieved content, tool outputs, and information provided by other actors. When these inputs can be strategically shaped by adversaries, the relevant security risk extends beyond a fixed library of prompt attacks to adaptive strategies that steer agents toward unfavorable outcomes. We propose profit-driven red teaming, a stress-testing protocol that replaces handcrafted attacks with a learned opponent trained to maximize its profit using only scalar outcome feedback. The protocol requires no LLM-as-judge scoring, attack labels, or attack taxonomy, and is designed for structured settings with auditable outcomes. We instantiate it in a lean arena of four canonical economic interactions, which provide a controlled testbed for adaptive exploitability. In controlled experiments, agents that appear strong against static baselines become consistently exploitable under profit-optimized pressure, and the learned opponent discovers probing, anchoring, and deceptive commitments without explicit instruction. We then distill exploit episodes into concise prompt rules for the agent, which make most previously observed failures ineffective and substantially improve target performance. These results suggest that profit-driven red-team data can provide a practical route to improving robustness in structured agent settings with auditable outcomes.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
A Multihead Continual Learning Framework for Fine-Grained Fashion Image Retrieval with Contrastive Learning and Exponential Moving Average Distillation
arXiv:2603.20648v1 Announce Type: new
Abstract: Most fine-grained fashion image retrieval (FIR) methods assume a static setting, requiring full retraining when new attributes appear, which is costly and impractical for dynamic scenarios. Although pretrained models support zero-shot inference, their accuracy drops without supervision, and no prior work explores class-incremental learning (CIL) for fine-grained FIR. We propose a multihead continual learning framework for fine-grained fashion image retrieval with contrastive learning and exponential moving average (EMA) distillation (MCL-FIR). MCL-FIR adopts a multi-head design to accommodate evolving classes across increments, reformulates triplet inputs into doublets with InfoNCE for simpler and more effective training, and employs EMA distillation for efficient knowledge transfer. Experiments across four datasets demonstrate that, beyond its scalability, MCL-FIR achieves a strong balance between efficiency and accuracy. It significantly outperforms CIL baselines under similar training cost, and compared with static methods, it delivers comparable performance while using only about 30% of the training cost. The source code is publicly available in https://github.com/Dr-LingXiao/MCL-FIR.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
AgenticGEO: A Self-Evolving Agentic System for Generative Engine Optimization
arXiv:2603.20213v1 Announce Type: new
Abstract: Generative search engines represent a transition from traditional ranking-based retrieval to Large Language Model (LLM)-based synthesis, transforming optimization goals from ranking prominence towards content inclusion. Generative Engine Optimization (GEO), specifically, aims to maximize visibility and attribution in black-box summarized outputs by strategically manipulating source content. However, existing methods rely on static heuristics, single-prompt optimization, or engine preference rule distillation that is prone to overfitting. They cannot flexibly adapt to diverse content or the changing behaviors of generative engines. Moreover, effectively optimizing these strategies requires an impractical amount of interaction feedback from the engines. To address these challenges, we propose AgenticGEO, a self-evolving agentic framework formulating optimization as a content-conditioned control problem, which enhances intrinsic content quality to robustly adapt to the unpredictable behaviors of black-box engines. Unlike fixed-strategy methods, AgenticGEO employs a MAP-Elites archive to evolve diverse, compositional strategies. To mitigate interaction costs, we introduce a Co-Evolving Critic, a lightweight surrogate that approximates engine feedback for content-specific strategy selection and refinement, efficiently guiding both evolutionary search and inference-time planning. Through extensive in-domain and cross-domain experiments on two representative engines, AgenticGEO achieves state-of-the-art performance and demonstrates robust transferability, outperforming 14 baselines across 3 datasets. Our code and model are available at: https://github.com/AIcling/agentic_geo.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Collaborative Adaptive Curriculum for Progressive Knowledge Distillation
arXiv:2603.20296v1 Announce Type: new
Abstract: Recent advances in collaborative knowledge distillation have demonstrated cutting-edge performance for resource-constrained distributed multimedia learning scenarios. However, achieving such competitiveness requires addressing a fundamental mismatch: high-dimensional teacher knowledge complexity versus heterogeneous client learning capacities, which currently prohibits deployment in edge-based visual analytics systems. Drawing inspiration from curriculum learning principles, we introduce Federated Adaptive Progressive Distillation (FAPD), a consensus-driven framework that orchestrates adaptive knowledge transfer. FAPD hierarchically decomposes teacher features via PCA-based structuring, extracting principal components ordered by variance contribution to establish a natural visual knowledge hierarchy. Clients progressively receive knowledge of increasing complexity through dimension-adaptive projection matrices. Meanwhile, the server monitors network-wide learning stability by tracking global accuracy fluctuations across a temporal consensus window, advancing curriculum dimensionality only when collective consensus emerges. Consequently, FAPD provably adapts knowledge transfer pace while achieving superior convergence over fixed-complexity approaches. Extensive experiments on three datasets validate FAPD's effectiveness: it attains 3.64% accuracy improvement over FedAvg on CIFAR-10, demonstrates 2x faster convergence, and maintains robust performance under extreme data heterogeneity ({\alpha}=0.1), outperforming baselines by over 4.5%.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
Mix-and-Match Pruning: Globally Guided Layer-Wise Sparsification of DNNs
arXiv:2603.20280v1 Announce Type: new
Abstract: Deploying deep neural networks (DNNs) on edge devices requires strong compression with minimal accuracy loss. This paper introduces Mix-and-Match Pruning, a globally guided, layer-wise sparsification framework that leverages sensitivity scores and simple architectural rules to generate diverse, high-quality pruning configurations. The framework addresses a key limitation that different layers and architectures respond differently to pruning, making single-strategy approaches suboptimal. Mix-and-Match derives architecture-aware sparsity ranges, e.g., preserving normalization layers while pruning classifiers more aggressively, and systematically samples these ranges to produce ten strategies per sensitivity signal (magnitude, gradient, or their combination). This eliminates repeated pruning runs while offering deployment-ready accuracy-sparsity trade-offs. Experiments on CNNs and Vision Transformers demonstrate Pareto-optimal results, with Mix-and-Match reducing accuracy degradation on Swin-Tiny by 40% relative to standard single-criterion pruning. These findings show that coordinating existing pruning signals enables more reliable and efficient compressed models than introducing new criteria.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
FAAR: Efficient Frequency-Aware Multi-Task Fine-Tuning via Automatic Rank Selection
arXiv:2603.20403v1 Announce Type: new
Abstract: Adapting models pre-trained on large-scale datasets is a proven way to reach strong performance quickly for down-stream tasks. However, the growth of state-of-the-art mod-els makes traditional full fine-tuning unsuitable and difficult, especially for multi-task learning (MTL) where cost scales with the number of tasks. As a result, recent studies investigate parameter-efficient fine-tuning (PEFT) using low-rank adaptation to significantly reduce the number of trainable parameters. However, these existing methods use a single, fixed rank, which may not be optimal for differ-ent tasks or positions in the MTL architecture. Moreover, these methods fail to learn spatial information that cap-tures inter-task relationships and helps to improve diverse task predictions. This paper introduces Frequency-Aware and Automatic Rank (FAAR) for efficient MTL fine-tuning. Our method introduces Performance-Driven Rank Shrink-ing (PDRS) to allocate the optimal rank per adapter location and per task. Moreover, by analyzing the image frequency spectrum, FAAR proposes a Task-Spectral Pyramidal Decoder (TS-PD) that injects input-specific context into spatial bias learning to better reflect cross-task relationships. Experiments performed on dense visual task benchmarks show the superiority of our method in terms of both accuracy and efficiency compared to other PEFT methods in MTL. FAAR reduces the number of parameters by up to 9 times compared to traditional MTL fine-tuning whilst improving overall performance. Our code is available.
Fonte: arXiv cs.CV
Vision • Score 85
Efficient Visual Anomaly Detection at the Edge: Enabling Real-Time Industrial Inspection on Resource-Constrained Devices
arXiv:2603.20288v1 Announce Type: new
Abstract: Visual Anomaly Detection (VAD) is essential for industrial quality control, enabling automatic defect detection in manufacturing. In real production lines, VAD systems must satisfy strict real-time and privacy requirements, necessitating a shift from cloud-based processing to local edge deployment. However, processing data locally on edge devices introduces new challenges because edge hardware has limited memory and computational resources. To overcome these limitations, we propose two efficient VAD methods designed for edge deployment: PatchCore-Lite and Padim-Lite, based on the popular PatchCore and PaDiM models. PatchCore-Lite runs first a coarse search on a product-quantized memory bank, then an exact search on a decoded subset. Padim-Lite is sped up using diagonal covariance, turning Mahalanobis distance into efficient element-wise computation. We evaluate our methods on the MVTec AD and VisA benchmarks and show their suitability for edge environments. PatchCore-Lite achieves a remarkable 79% reduction in total memory footprint, while PaDiM-Lite achieves substantial efficiency gains with a 77% reduction in total memory and a 31% decrease in inference time. These results show that VAD can be effectively deployed on edge devices, enabling real-time, private, and cost-efficient industrial inspection.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Agentic AI and the next intelligence explosion
arXiv:2603.20639v1 Announce Type: new
Abstract: The "AI singularity" is often miscast as a monolithic, godlike mind. Evolution suggests a different path: intelligence is fundamentally plural, social, and relational. Recent advances in agentic AI reveal that frontier reasoning models, such as DeepSeek-R1, do not improve simply by "thinking longer". Instead, they simulate internal "societies of thought," spontaneous cognitive debates that argue, verify, and reconcile to solve complex tasks. Moreover, we are entering an era of human-AI centaurs: hybrid actors where collective agency transcends individual control. Scaling this intelligence requires shifting from dyadic alignment (RLHF) toward institutional alignment. By designing digital protocols, modeled on organizations and markets, we can build a social infrastructure of checks and balances. The next intelligence explosion will not be a single silicon brain, but a complex, combinatorial society specializing and sprawling like a city. No mind is an island.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
An experimental study of KV cache reuse strategies in chunk-level caching systems
arXiv:2603.20218v1 Announce Type: new
Abstract: Retrieval-augmented generation improves large language models' accuracy by adding relevant retrieved text to the prompt. Chunk level caching (CLC) accelerates inference by precomputing KV caches for these retrieved chunks and reusing them. However, these caches miss cross-attention dependencies between chunks, which can reduce output quality. Several methods try to improve CLC accuracy using different techniques. We make two main contributions. First, we show that existing CLC approaches have fundamental limitations that limit their accuracy or their applicability. We back this conclusion with an extensive CLC system experimental evaluation. Second, we observe that existing CLC techniques are complementary. We leverage this insight to propose a new CLC design that carefully combines them and achieves better accuracy.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
Optimal low-rank stochastic gradient estimation for LLM training
arXiv:2603.20632v1 Announce Type: new
Abstract: Large language model (LLM) training is often bottlenecked by memory constraints and stochastic gradient noise in extremely high-dimensional parameter spaces. Motivated by empirical evidence that many LLM gradient matrices are effectively low-rank during training, we present an unbiased, memory-efficient, low-rank matrix estimator with the lowest variance that is applicable across common stochastic gradient estimation paradigms. The core idea is to project a high-dimensional stochastic gradient estimator onto a random low-dimensional subspace and lift it back, reducing memory while keeping the estimator unbiased and controlling mean-squared error via an optimally designed projection distribution, including Haar--Stiefel projections. The projection distribution is derived by solving a constrained functional optimization problem, yielding an optimal random projector that guides algorithm design. Empirically, the resulting low-rank gradient estimators deliver both practical memory savings and improved training behavior. In RoBERTa-large fine-tuning, our method attains the lowest peak GPU memory among compared methods (e.g., 3.83GB versus 16.7GB for full BP) while remaining competitive in accuracy; in autoregressive LLM pretraining (LLaMA-20M/60M/100M), our method outperforms the traditional methods, supporting the benefit of the proposed optimal projection strategy.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization
arXiv:2603.20527v1 Announce Type: new
Abstract: Preconditioned adaptive methods have gained significant attention for training deep neural networks, as they capture rich curvature information of the loss landscape . The central challenge in this field lies in balancing preconditioning effectiveness with computational efficiency of implementing the preconditioner. Among recent advances, \textsc{Muon} stands out by using Newton-Schulz iteration to obtain preconditioned updates without explicitly constructing the preconditioning matrix. Despite its advantages, the efficiency of \textsc{Muon} still leaves room for further improvement. In this paper, we introduce \textsc{RMNP} (Row Momentum Normalized Preconditioning), an optimizer that replaces Newton-Schulz iteration with a simple row-wise $\ell_2$ normalization operation, motivated by the empirically observed diagonal block structure of the Transformer layerwise Hessian. This substitution reduces the per-iteration computational complexity from $\mathcal{O}(mn\cdot\min(m,n))$ to $\mathcal{O}(mn)$ for an $m\times n$ weight matrix while maintaining comparable optimization performance. Theoretically, we establish convergence guarantees for \textsc{RMNP} in the non-convex setting that match recent results for \textsc{Muon} optimizers, achieving the information-theoretic minimax optimal complexity. Extensive experiments on large language model pretraining show that \textsc{RMNP} delivers competitive optimization performance compared with \textsc{Muon} while substantially reducing preconditioning wall-clock time. Our code is available at \href{https://anonymous.4open.science/r/RMNP-E8E1/}{this link}.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
JointFM-0.1: A Foundation Model for Multi-Target Joint Distributional Prediction
arXiv:2603.20266v1 Announce Type: new
Abstract: Despite the rapid advancements in Artificial Intelligence (AI), Stochastic Differential Equations (SDEs) remain the gold-standard formalism for modeling systems under uncertainty. However, applying SDEs in practice is fraught with challenges: modeling risk is high, calibration is often brittle, and high-fidelity simulations are computationally expensive. This technical report introduces JointFM, a foundation model that inverts this paradigm. Instead of fitting SDEs to data, we sample an infinite stream of synthetic SDEs to train a generic model to predict future joint probability distributions directly. This approach establishes JointFM as the first foundation model for distributional predictions of coupled time series - requiring no task-specific calibration or finetuning. Despite operating in a purely zero-shot setting, JointFM reduces the energy loss by 14.2% relative to the strongest baseline when recovering oracle joint distributions generated by unseen synthetic SDEs.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
CoNBONet: Conformalized Neuroscience-inspired Bayesian Operator Network for Reliability Analysis
arXiv:2603.21678v1 Announce Type: new
Abstract: Time-dependent reliability analysis of nonlinear dynamical systems under stochastic excitations is a critical yet computationally demanding task. Conventional approaches, such as Monte Carlo simulation, necessitate repeated evaluations of computationally expensive numerical solvers, leading to significant computational bottlenecks. To address this challenge, we propose \textit{CoNBONet}, a neuroscience-inspired surrogate model that enables fast, energy-efficient, and uncertainty-aware reliability analysis, providing a scalable alternative to techniques such as Monte Carlo simulations. CoNBONet, short for \textbf{Co}nformalized \textbf{N}euroscience-inspired \textbf{B}ayesian \textbf{O}perator \textbf{Net}work, leverages the expressive power of deep operator networks while integrating neuroscience-inspired neuron models to achieve fast, low-power inference. Unlike traditional surrogates such as Gaussian processes, polynomial chaos expansions, or support vector regression, that may face scalability challenges for high-dimensional, time-dependent reliability problems, CoNBONet offers \textit{fast and energy-efficient inference} enabled by a neuroscience-inspired network architecture, \textit{calibrated uncertainty quantification with theoretical guarantees} via split conformal prediction, and \textit{strong generalization capability} through an operator-learning paradigm that maps input functions to system response trajectories. Validation of the proposed CoNBONet for various nonlinear dynamical systems demonstrates that CoNBONet preserves predictive fidelity, and achieves reliable coverage of failure probabilities, making it a powerful tool for robust and scalable reliability analysis in engineering design.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
KV Cache Optimization Strategies for Scalable and Efficient LLM Inference
arXiv:2603.20397v1 Announce Type: new
Abstract: The key-value (KV) cache is a foundational optimization in Transformer-based large language models (LLMs), eliminating redundant recomputation of past token representations during autoregressive generation. However, its memory footprint scales linearly with context length, imposing critical bottlenecks on GPU memory capacity, memory bandwidth, and inference throughput as production LLMs push context windows from thousands to millions of tokens. Efficient KV cache management has thus become a first-order challenge for scalable LLM deployment. This paper provides a systematic review of recent KV cache optimization techniques, organizing them into five principal directions: cache eviction, cache compression, hybrid memory solutions, novel attention mechanisms, and combination strategies. For each category we analyze the underlying mechanisms, deployment trade-offs, and empirical performance across memory reduction, throughput, and model accuracy metrics. We further map techniques to seven practical deployment scenarios, including long-context single requests, high-throughput datacenter serving, edge devices, multi-turn conversations, and accuracy-critical reasoning, providing actionable guidance for practitioners selecting among competing approaches. Our analysis reveals that no single technique dominates across all settings; instead, the optimal strategy depends on context length, hardware constraints, and workload characteristics, pointing toward adaptive, multi-stage optimization pipelines as a promising direction for future research.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
LLM-Driven Heuristic Synthesis for Industrial Process Control: Lessons from Hot Steel Rolling
arXiv:2603.20537v1 Announce Type: new
Abstract: Industrial process control demands policies that are interpretable and auditable, requirements that black-box neural policies struggle to meet. We study an LLM-driven heuristic synthesis framework for hot steel rolling, in which a language model iteratively proposes and refines human-readable Python controllers using rich behavioral feedback from a physics-based simulator. The framework combines structured strategic ideation, executable code generation, and per-component feedback across diverse operating conditions to search over control logic for height reduction, interpass time, and rolling velocity. Our first contribution is an auditable controller-synthesis pipeline for industrial process control. The generated controllers are explicit programs accessible to expert review, and we pair them with an automated audit pipeline that formally verifies key safety and monotonicity properties for the best synthesized heuristic. Our second contribution is a principled budget allocation strategy for LLM-driven heuristic search: we show that Luby-style universal restarts -- originally developed for randomized algorithms -- transfer directly to this setting, eliminating the need for problem-specific budget tuning. A single 160-iteration Luby campaign approaches the hindsight-optimal budget allocation derived from 52 ad-hoc runs totalling 730 iterations.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
FactorSmith: Agentic Simulation Generation via Markov Decision Process Decomposition with Planner-Designer-Critic Refinement
arXiv:2603.20270v1 Announce Type: new
Abstract: Generating executable simulations from natural language specifications remains a challenging problem due to the limited reasoning capacity of large language models (LLMs) when confronted with large, interconnected codebases. This paper presents FactorSmith, a framework that synthesizes playable game simulations in code from textual descriptions by combining two complementary ideas: factored POMDP decomposition for principled context reduction and a hierarchical planner-designer-critic agentic workflow for iterative quality refinement at every generation step. Drawing on the factored partially observable Markov decision process (POMDP) representation introduced by FactorSim [Sun et al., 2024], the proposed method decomposes a simulation specification into modular steps where each step operates only on a minimal subset of relevant state variables, limiting the context window that any single LLM call must process. Inspired by the agentic trio architecture of SceneSmith [Pfaff et al., 2025], FactorSmith embeds within every factored step a three-agent interaction: a planner that orchestrates workflow, a designer that proposes code artifacts, and a critic that evaluates quality through structured scoring, enabling iterative refinement with checkpoint rollback. This paper formalizes the combined approach, presents the mathematical framework underpinning context selection and agentic refinement, and describes the open-source implementation. Experiments on the PyGame Learning Environment benchmark demonstrate that FactorSmith generates simulations with improved prompt alignment, fewer runtime errors, and higher code quality compared to non-agentic factored baselines.
Fonte: arXiv cs.AI
Applications • Score 85
GMPilot: An Expert AI Agent For FDA cGMP Compliance
arXiv:2603.20815v1 Announce Type: new
Abstract: The pharmaceutical industry is facing challenges with quality management such as high costs of compliance, slow responses and disjointed knowledge. This paper presents GMPilot, a domain-specific AI agent that is designed to support FDA cGMP compliance. GMPilot is based on a curated knowledge base of regulations and historical inspection observations and uses Retrieval-Augmented Generation (RAG) and Reasoning-Acting (ReAct) frameworks to provide real-time and traceable decision support to the quality professionals. In a simulated inspection scenario, GMPilot shows how it can improve the responsiveness and professionalism of quality professionals by providing structured knowledge retrieval and verifiable regulatory and case-based support. Although GMPilot lacks in the aspect of regulatory scope and model interpretability, it is a viable avenue of improving quality management decision-making in the pharmaceutical sector using intelligent approaches and an example of specialized application of AI in highly regulated sectors.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
Transformer-Based Predictive Maintenance for Risk-Aware Instrument Calibration
arXiv:2603.20297v1 Announce Type: new
Abstract: Accurate calibration is essential for instruments whose measurements must remain traceable, reliable, and compliant over long operating periods. Fixed-interval programs are easy to administer, but they ignore that instruments drift at different rates under different conditions. This paper studies calibration scheduling as a predictive maintenance problem: given recent sensor histories, estimate time-to-drift (TTD) and intervene before a violation occurs. We adapt the NASA C-MAPSS benchmark into a calibration setting by selecting drift-sensitive sensors, defining virtual calibration thresholds, and inserting synthetic reset events that emulate repeated recalibration. We then compare classical regressors, recurrent and convolutional sequence models, and a compact Transformer for TTD prediction. The Transformer provides the strongest point forecasts on the primary FD001 split and remains competitive on the harder FD002--FD004 splits, while a quantile-based uncertainty model supports conservative scheduling when drift behavior is noisier. Under a violation-aware cost model, predictive scheduling lowers cost relative to reactive and fixed policies, and uncertainty-aware triggers sharply reduce violations when point forecasts are less reliable. The results show that condition-based calibration can be framed as a joint forecasting and decision problem, and that combining sequence models with risk-aware policies is a practical route toward smarter calibration planning.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
Uni-Classifier: Leveraging Video Diffusion Priors for Universal Guidance Classifier
arXiv:2603.20382v1 Announce Type: new
Abstract: In practical AI workflows, complex tasks often involve chaining multiple generative models, such as using a video or 3D generation model after a 2D image generator. However, distributional mismatches between the output of upstream models and the expected input of downstream models frequently degrade overall generation quality. To address this issue, we propose Uni-Classifier (Uni-C), a simple yet effective plug-and-play module that leverages video diffusion priors to guide the denoising process of preceding models, thereby aligning their outputs with downstream requirements. Uni-C can also be applied independently to enhance the output quality of individual generative models. Extensive experiments across video and 3D generation tasks demonstrate that Uni-C consistently improves generation quality in both workflow-based and standalone settings, highlighting its versatility and strong generalization capability.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
AutoMOOSE: An Agentic AI for Autonomous Phase-Field Simulation
arXiv:2603.20986v1 Announce Type: new
Abstract: Multiphysics simulation frameworks such as MOOSE provide rigorous engines for phase-field materials modeling, yet adoption is constrained by the expertise required to construct valid input files, coordinate parameter sweeps, diagnose failures, and extract quantitative results. We introduce AutoMOOSE, an open-source agentic framework that orchestrates the full simulation lifecycle from a single natural-language prompt. AutoMOOSE deploys a five-agent pipeline in which the Input Writer coordinates six sub-agents and the Reviewer autonomously corrects runtime failures without user intervention. A modular plugin architecture enables new phase-field formulations without modifying the core framework, and a Model Context Protocol (MCP) server exposes the workflow as ten structured tools for interoperability with any MCP-compatible client. Validated on a four-temperature copper grain growth benchmark, AutoMOOSE generates MOOSE input files with 6 of 12 structural blocks matching a human expert reference exactly and 4 functionally equivalent, executes all runs in parallel with a 1.8x speedup, and performs an end-to-end physical consistency check spanning intent, finite-element execution, and Arrhenius kinetics with no human verification. Grain coarsening kinetics are recovered with R^2 = 0.90-0.95 at T >= 600 K; the recovered activation energy Q_fit = 0.296 eV is consistent with a human-written reference (Q_fit = 0.267 eV) under identical parameters. Three runtime failure classes were diagnosed and resolved autonomously within a single correction cycle, and every run produces a provenance record satisfying FAIR data principles. These results show that the gap between knowing the physics and executing a validated simulation campaign can be bridged by a lightweight multi-agent orchestration layer, providing a pathway toward AI-driven materials discovery and self-driving laboratories.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Seed1.8 Model Card: Towards Generalized Real-World Agency
arXiv:2603.20633v1 Announce Type: new
Abstract: We present Seed1.8, a foundation model aimed at generalized real-world agency: going beyond single-turn prediction to multi-turn interaction, tool use, and multi-step execution. Seed1.8 keeps strong LLM and vision-language performance while supporting a unified agentic interface-search, code generation and execution, and GUI interaction. For deployment, it offers latency- and cost-aware inference, including configurable thinking modes and optimized visual encoding for images and video. We report evaluations on standard benchmarks and application-aligned workflows spanning foundational skills, multimodal understanding, and agentic behavior. Seed1.8 is released to support further research and development on interactive, real-world use cases.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
Which Workloads Belong in Orbit? A Workload-First Framework for Orbital Data Centers Using Semantic Abstraction
arXiv:2603.20317v1 Announce Type: new
Abstract: Space-based compute is becoming plausible as launch costs fall and data-intensive AI workloads grow. This paper proposes a workload-centric framework for deciding which tasks belong in orbit versus terrestrial cloud, along with a phased adoption model tied to orbital data center maturity. We ground the framework with in-orbit semantic-reduction prototypes. An Earth-observation pipeline on Sentinel-2 imagery from Seattle and Bengaluru (formerly Bangalore) achieves 99.7-99.99% payload reduction by converting raw imagery to compact semantic artifacts. A multi-pass stereo reconstruction prototype reduces ~306 MB to ~1.57 MB of derived 3D representations (99.49% reduction). These results support a workload-first view in which semantic abstraction, not raw compute scale, drives early workload suitability.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Beyond Test-Time Compute Strategies: Advocating Energy-per-Token in LLM Inference
arXiv:2603.20224v1 Announce Type: new
Abstract: Large Language Models (LLMs) demonstrate exceptional performance across diverse tasks but come with substantial energy and computational costs, particularly in request-heavy scenarios. In many real-world applications, the full scale and capabilities of LLMs are often unnecessary, as Small Language Models (SLMs) can provide accurate responses for simpler text generation tasks. When enhanced with advanced reasoning strategies, such as Chain-of-Thought (CoT) prompting or Majority Voting, SLMs can approach the performance of larger models while reducing overall computational requirements. However, these strategies can also introduce additional energy costs, creating an energy-accuracy trade-off. Our analysis examines these trade-offs in test-time compute strategies for smaller models compared to larger ones, using the MMLU benchmark. Additionally, we explore the input-output token dynamics of transformer architectures, which result in nonlinear hardware energy operation curves for LLMs. To bridge AI research with its physical impact, we propose \textit{energy efficiency metrics}, including Energy-per-Token, as complements to traditional accuracy benchmarks. Beyond model selection, we propose controlled reasoning in CoT token generation, using operating curves to regulate reasoning depth dynamically. This vision integrates a energy-aware routing mechanism, ensuring that model selection and inference strategies balance accuracy for sustainable AI deployment.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
Expected Reward Prediction, with Applications to Model Routing
arXiv:2603.20217v1 Announce Type: new
Abstract: Reward models are a standard tool to score responses from LLMs. Reward models are built to rank responses to a fixed prompt sampled from a single model, for example to choose the best of n sampled responses. In this paper, we study whether scores from response-level reward models lifted to score a model's suitability for a prompt, prior to seeing responses from that model. Specifically, we show that it is straightforward to predict the expected reward that an LLM would earn from the reward model under repeated sampling. Further, we show that these expected reward predictions are precise and discriminative enough to support an application to a model routing protocol that routes prompts to models at inference time to maximize reward while controlling computational cost. We demonstrate the performance of this routing procedure on the open-perfectblend dataset, using a model pool composed of Llama3.1-Instruct 8B/70B, Gemma2-IT 9B/27B, and Gemma1-IT 7B models. Our simple expected reward prediction--based routing (ERP) outperforms baselines that route prompts to models with the best average performance within each prompt's category, and explains the success of more complex routing protocols that implicitly estimate an expected reward. Our approach has the added advantage of being trivially extensible as new models are added to the pool.
Fonte: arXiv cs.CL
Theory/Optimization • Score 85
Constrained Online Convex Optimization with Memory and Predictions
arXiv:2603.21375v1 Announce Type: cross
Abstract: We study Constrained Online Convex Optimization with Memory (COCO-M), where both the loss and the constraints depend on a finite window of past decisions made by the learner. This setting extends the previously studied unconstrained online optimization with memory framework and captures practical problems such as the control of constrained dynamical systems and scheduling with reconfiguration budgets. For this problem, we propose the first algorithms that achieve sublinear regret and sublinear cumulative constraint violation under time-varying constraints, both with and without predictions of future loss and constraint functions. Without predictions, we introduce an adaptive penalty approach that guarantees sublinear regret and constraint violation. When short-horizon and potentially unreliable predictions are available, we reinterpret the problem as online learning with delayed feedback and design an optimistic algorithm whose performance improves as prediction accuracy improves, while remaining robust when predictions are inaccurate. Our results bridge the gap between classical constrained online convex optimization and memory-dependent settings, and provide a versatile learning toolbox with diverse applications.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
Spatio-Temporal Grid Intelligence: A Hybrid Graph Neural Network and LSTM Framework for Robust Electricity Theft Detection
arXiv:2603.20488v1 Announce Type: new
Abstract: Electricity theft, or non-technical loss (NTL), presents a persistent threat to global power systems, driving significant financial deficits and compromising grid stability. Conventional detection methodologies, predominantly reactive and meter-centric, often fail to capture the complex spatio-temporal dynamics and behavioral patterns associated with fraudulent consumption. This study introduces a novel AI-driven Grid Intelligence Framework that fuses Time-Series Anomaly Detection, Supervised Machine Learning, and Graph Neural Networks (GNN) to identify theft with high precision in imbalanced datasets. Leveraging an enriched feature set, including rolling averages, voltage drop estimates, and a critical Grid Imbalance Index, the methodology employs a Long Short-Term Memory (LSTM) autoencoder for temporal anomaly scoring, a Random Forest classifier for tabular feature discrimination, and a GNN to model spatial dependencies across the distribution network. Experimental validation demonstrates that while standalone anomaly detection yields a low theft F1-score of 0.20, the proposed hybrid fusion achieves an overall accuracy of 93.7%. By calibrating decision thresholds via precision-recall analysis, the system attains a balanced theft precision of 0.55 and recall of 0.50, effectively mitigating the false positives inherent in single-model approaches. These results confirm that integrating topological grid awareness with temporal and supervised analytics provides a scalable, risk-based solution for proactive electricity theft detection and enhanced smart grid reliability.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Beyond Token Eviction: Mixed-Dimension Budget Allocation for Efficient KV Cache Compression
arXiv:2603.20616v1 Announce Type: new
Abstract: Key-value (KV) caching is widely used to accelerate transformer inference, but its memory cost grows linearly with input length, limiting long-context deployment. Existing token eviction methods reduce memory by discarding less important tokens, which can be viewed as a coarse form of dimensionality reduction that assigns each token either zero or full dimension. We propose MixedDimKV, a mixed-dimension KV cache compression method that allocates dimensions to tokens at a more granular level, and MixedDimKV-H, which further integrates head-level importance information. Experiments on long-context benchmarks show that MixedDimKV outperforms prior KV cache compression methods that do not rely on head-level importance profiling. When equipped with the same head-level importance information, MixedDimKV-H consistently outperforms HeadKV. Notably, our approach achieves comparable performance to full attention on LongBench with only 6.25% of the KV cache. Furthermore, in the Needle-in-a-Haystack test, our solution maintains 100% accuracy at a 50K context length while using as little as 0.26% of the cache.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
Improving Coherence and Persistence in Agentic AI for System Optimization
arXiv:2603.21321v1 Announce Type: new
Abstract: Designing high-performance system heuristics is a creative, iterative process requiring experts to form hypotheses and execute multi-step conceptual shifts. While Large Language Models (LLMs) show promise in automating this loop, they struggle with complex system problems due to two critical failure modes: evolutionary neighborhood bias and the coherence ceiling. Evolutionary methods often remain trapped in local optima by relying on scalar benchmark scores, failing when coordinated multi-step changes are required. Conversely, existing agentic frameworks suffer from context degradation over long horizons or fail to accumulate knowledge across independent runs.
We present Engram, an agentic researcher architecture that addresses these limitations by decoupling long-horizon exploration from the constraints of a single context window. Engram organizes exploration into a sequence of agents that iteratively design, test, and analyze mechanisms. At the conclusion of each run, an agent stores code snapshots, logs, and results in a persistent Archive and distills high-level modeling insights into a compact, persistent Research Digest. Subsequent agents then begin with a fresh context window, reading the Research Digest to build on prior discoveries.
We find that Engram exhibits superior performance across diverse domains including multi-cloud multicast, LLM inference request routing, and optimizing KV cache reuse in databases with natural language queries.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
MAGPI: Multifidelity-Augmented Gaussian Process Inputs for Surrogate Modeling from Scarce Data
arXiv:2603.22050v1 Announce Type: new
Abstract: Supervised machine learning describes the practice of fitting a parameterized model to labeled input-output data. Supervised machine learning methods have demonstrated promise in learning efficient surrogate models that can (partially) replace expensive high-fidelity models, making many-query analyses, such as optimization, uncertainty quantification, and inference, tractable. However, when training data must be obtained through the evaluation of an expensive model or experiment, the amount of training data that can be obtained is often limited, which can make learned surrogate models unreliable. However, in many engineering and scientific settings, cheaper \emph{low-fidelity} models may be available, for example arising from simplified physics modeling or coarse grids. These models may be used to generate additional low-fidelity training data. The goal of \emph{multifidelity} machine learning is to use both high- and low-fidelity training data to learn a surrogate model which is cheaper to evaluate than the high-fidelity model, but more accurate than any available low-fidelity model. This work proposes a new multifidelity training approach for Gaussian process regression which uses low-fidelity data to define additional features that augment the input space of the learned model. The approach unites desirable properties from two separate classes of existing multifidelity GPR approaches, cokriging and autoregressive estimators. Numerical experiments on several test problems demonstrate both increased predictive accuracy and reduced computational cost relative to the state of the art.
Fonte: arXiv stat.ML
Theory/Optimization • Score 92
ARYA: A Physics-Constrained Composable & Deterministic World Model Architecture
arXiv:2603.21340v1 Announce Type: new
Abstract: This paper presents ARYA, a composable, physics-constrained, deterministic world model architecture built on five foundational principles: nano models, composability, causal reasoning, determinism, and architectural AI safety. We demonstrate that ARYA satisfies all canonical world model requirements, including state representation, dynamic prediction, causal and physical awareness, temporal consistency, generalization, learnability, and planning and control. Unlike monolithic foundation models, the ARYA foundation model implements these capabilities through a hierarchical system-of-system-of-systems of specialized nano models, orchestrated by AARA (ARYA Autonomous Research Agent), an always-on cognitive daemon that executes a continuous sense-decide-act-learn loop. The nano model architecture provides linear scaling, sparse activation, selective untraining, and sub-20-second training cycles, resolving the traditional tension between capability and computational efficiency. A central contribution is the Unfireable Safety Kernel: an architecturally immutable safety boundary that cannot be disabled or circumvented by any system component, including its own self-improvement engine. This is not a social or ethical alignment statement; it is a technical framework ensuring human control persists as autonomy increases. Safety is an architectural constraint governing every operation, not a policy layer applied after the fact. We present formal alignment between ARYA's architecture and canonical world model requirements, and report summarizing its state-of-the-art performance across 6 of 9 competitive benchmarks head-to-head with GPT-5.2, Opus 4.6, and V-JEPA-2. All with zero neural network parameters, across seven active industry domain nodes spanning aerospace, pharma manufacturing, oil and gas, smart cities, biotech, defense, and medical devices.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
MKA: Memory-Keyed Attention for Efficient Long-Context Reasoning
arXiv:2603.20586v1 Announce Type: new
Abstract: As long-context language modeling becomes increasingly important, the cost of maintaining and attending to large Key/Value (KV) caches grows rapidly, becoming a major bottleneck in both training and inference. While prior works such as Multi-Query Attention (MQA) and Multi-Latent Attention (MLA) reduce memory by sharing or compressing KV features, they often trade off representation quality or incur runtime overhead. We propose Memory-Keyed Attention (MKA), a hierarchical attention mechanism that integrates multi-level KV caches (local, session, and long-term) and learns to route attention across them dynamically. We further introduce Route-Fused MKA (FastMKA), a broadcast-routed variant that fuses memory sources before attention computation for improved efficiency. Experiments on different sequence lengths show that FastMKA achieves a favorable accuracy-efficiency trade-off: comparable perplexity to MLA while achieving up to 5x faster training throughput and 1.8x lower evaluation latency. These results highlight MKA as a practical and extensible framework for efficient long-context attention.
Fonte: arXiv cs.LG
Theory/Optimization • Score 92
ALMAB-DC: Active Learning, Multi-Armed Bandits, and Distributed Computing for Sequential Experimental Design and Black-Box Optimization
arXiv:2603.21180v1 Announce Type: cross
Abstract: Sequential experimental design under expensive, gradient-free objectives is a central challenge in computational statistics: evaluation budgets are tightly constrained and information must be extracted efficiently from each observation. We propose \textbf{ALMAB-DC}, a GP-based sequential design framework combining active learning, multi-armed bandits (MAB), and distributed asynchronous computing for expensive black-box experimentation. A Gaussian process surrogate with uncertainty-aware acquisition identifies informative query points; a UCB or Thompson-sampling bandit controller allocates evaluations across parallel workers; and an asynchronous scheduler handles heterogeneous runtimes. We present cumulative regret bounds for the bandit components and characterize parallel scalability via Amdahl's Law.
We validate ALMAB-DC on five benchmarks. On the two statistical experimental-design tasks, ALMAB-DC achieves lower simple regret than Equal Spacing, Random, and D-optimal designs in dose--response optimization, and in adaptive spatial field estimation matches the Greedy Max-Variance benchmark while outperforming Latin Hypercube Sampling; at $K=4$ the distributed setting reaches target performance in one-quarter of sequential wall-clock rounds. On three ML/engineering tasks (CIFAR-10 HPO, CFD drag minimization, MuJoCo RL), ALMAB-DC achieves 93.4\% CIFAR-10 accuracy (outperforming BOHB by 1.7\,pp and Optuna by 1.1\,pp), reduces airfoil drag to $C_D = 0.059$ (36.9\% below Grid Search), and improves RL return by 50\% over Grid Search. All advantages over non-ALMAB baselines are statistically significant under Bonferroni-corrected Mann--Whitney $U$ tests. Distributed execution achieves $7.5\times$ speedup at $K = 16$ agents, consistent with Amdahl's Law.
Fonte: arXiv stat.ML
Vision • Score 85
STAC: Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstruction
arXiv:2603.20284v1 Announce Type: new
Abstract: Online 3D reconstruction from streaming inputs requires both long-term temporal consistency and efficient memory usage. Although causal VGGT transformers address this challenge through a key-value (KV) cache mechanism, the cache grows linearly with the stream length, creating a major memory bottleneck. Under limited memory budgets, early cache eviction significantly degrades reconstruction quality and temporal consistency.
In this work, we observe that attention in causal transformers for 3D reconstruction exhibits intrinsic spatio-temporal sparsity. Based on this insight, we propose STAC, a Spatio-Temporally Aware Cache Compression framework for streaming 3D reconstruction with large causal transformers. STAC consists of three key components: (1) a Working Temporal Token Caching mechanism that preserves long-term informative tokens using decayed cumulative attention scores; (2) a Long-term Spatial Token Caching scheme that compresses spatially redundant tokens into voxel-aligned representations for memory-efficient storage; and (3) a Chunk-based Multi-frame Optimization strategy that jointly processes consecutive frames to improve temporal coherence and GPU efficiency.
Extensive experiments show that STAC achieves state-of-the-art reconstruction quality while reducing memory consumption by nearly 10x and accelerating inference by 4x, substantially improving the scalability of real-time 3D reconstruction in streaming settings.
Fonte: arXiv cs.CV
Multimodal • Score 85
ScaleEdit-12M: Scaling Open-Source Image Editing Data Generation via Multi-Agent Framework
arXiv:2603.20644v1 Announce Type: new
Abstract: Instruction-based image editing has emerged as a key capability for unified multimodal models (UMMs), yet constructing large-scale, diverse, and high-quality editing datasets without costly proprietary APIs remains challenging. Previous image editing datasets either rely on closed-source models for annotation, which prevents cost-effective scaling, or employ fixed synthetic editing pipelines, which suffer from limited quality and generalizability. To address these challenges, we propose ScaleEditor, a fully open-source hierarchical multi-agent framework for end-to-end construction of large-scale, high-quality image editing datasets. Our pipeline consists of three key components: source image expansion with world-knowledge infusion, adaptive multi-agent editing instruction-image synthesis, and a task-aware data quality verification mechanism. Using ScaleEditor, we curate ScaleEdit-12M, the largest open-source image editing dataset to date, spanning 23 task families across diverse real and synthetic domains. Fine-tuning UniWorld-V1 and Bagel on ScaleEdit yields consistent gains, improving performance by up to 10.4% on ImgEdit and 35.1% on GEdit for general editing benchmarks and by up to 150.0% on RISE and 26.5% on KRIS-Bench for knowledge-infused benchmarks. These results demonstrate that open-source, agentic pipelines can approach commercial-grade data quality while retaining cost-effectiveness and scalability. Both the framework and dataset will be open-sourced.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
AE-LLM: Adaptive Efficiency Optimization for Large Language Models
arXiv:2603.20492v1 Announce Type: new
Abstract: Large Language Models (LLMs) have achieved remarkable success across diverse applications, yet their deployment remains challenging due to substantial computational costs, memory requirements, and energy consumption. Recent empirical studies have demonstrated that no single efficiency technique is universally optimal; instead, the effectiveness of methods such as efficient attention mechanisms, mixture-of-experts (MoE), parameter-efficient fine-tuning, and quantization varies significantly depending on task characteristics, resource constraints, and model scales. Building upon these insights, we propose AE-LLM, a unified framework that automatically selects and combines optimal efficiency techniques tailored to specific deployment scenarios. Our approach introduces a multi-objective optimization framework that jointly considers accuracy, latency, memory footprint, and energy consumption, while accounting for hardware constraints and task requirements. We develop an efficient search algorithm that explores the combinatorial space of efficiency techniques across architecture, fine-tuning, and inference stages, identifying Pareto-optimal configurations. Extensive experiments across 15 models (0.5B-70B parameters) and 10 diverse tasks demonstrate that AE-LLM achieves an average of $2.8\times$ improvement in efficiency metrics while maintaining competitive accuracy (within 1.2\% of baseline), compared to static efficiency configurations. Furthermore, our framework generalizes effectively to vision-language models, achieving similar efficiency gains. Our contributions provide practitioners with an automated tool for navigating the complex trade-off landscape of LLM efficiency optimization.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
FedAgain: A Trust-Based and Robust Federated Learning Strategy for an Automated Kidney Stone Identification in Ureteroscopy
arXiv:2603.19512v1 Announce Type: new
Abstract: The reliability of artificial intelligence (AI) in medical imaging critically depends on its robustness to heterogeneous and corrupted images acquired with diverse devices across different hospitals which is highly challenging. Therefore, this paper introduces FedAgain, a trust-based Federated Learning (Federated Learning) strategy designed to enhance robustness and generalization for automated kidney stone identification from endoscopic images. FedAgain integrates a dual trust mechanism that combines benchmark reliability and model divergence to dynamically weight client contributions, mitigating the impact of noisy or adversarial updates during aggregation. The framework enables the training of collaborative models across multiple institutions while preserving data privacy and promoting stable convergence under real-world conditions. Extensive experiments across five datasets, including two canonical benchmarks (MNIST and CIFAR-10), two private multi-institutional kidney stone datasets, and one public dataset (MyStone), demonstrate that FedAgain consistently outperforms standard Federated Learning baselines under non-identically and independently distributed (non-IID) data and corrupted-client scenarios. By maintaining diagnostic accuracy and performance stability under varying conditions, FedAgain represents a practical advance toward reliable, privacy-preserving, and clinically deployable federated AI for medical imaging.
Fonte: arXiv cs.CV
Vision • Score 85
VeloxNet: Efficient Spatial Gating for Lightweight Embedded Image Classification
arXiv:2603.19496v1 Announce Type: new
Abstract: Deploying deep learning models on embedded devices for tasks such as aerial disaster monitoring and infrastructure inspection requires architectures that balance accuracy with strict constraints on model size, memory, and latency. This paper introduces VeloxNet, a lightweight CNN architecture that replaces SqueezeNet's fire modules with gated multi-layer perceptron (gMLP) blocks for embedded image classification. Each gMLP block uses a spatial gating unit (SGU) that applies learned spatial projections and multiplicative gating, enabling the network to capture spatial dependencies across the full feature map in a single layer. Unlike fire modules, which are limited to local receptive fields defined by small convolutional kernels, the SGU provides global spatial modeling at each layer with fewer parameters. We evaluate VeloxNet on three aerial image datasets: the Aerial Image Database for Emergency Response (AIDER), the Comprehensive Disaster Dataset (CDD), and the Levee Defect Dataset (LDD), comparing against eleven baselines including MobileNet variants, ShuffleNet, EfficientNet, and recent vision transformers. VeloxNet reduces the parameter count by 46.1% relative to SqueezeNet (from 740,970 to 399,366) while improving weighted F1 scores by 6.32% on AIDER, 30.83% on CDD, and 2.51% on LDD. These results demonstrate that substituting local convolutional modules with spatial gating blocks can improve both classification accuracy and parameter efficiency for resource-constrained deployment. The source code will be made publicly available upon acceptance of the paper.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
PowerLens: Taming LLM Agents for Safe and Personalized Mobile Power Management
arXiv:2603.19584v1 Announce Type: new
Abstract: Battery life remains a critical challenge for mobile devices, yet existing power management mechanisms rely on static rules or coarse-grained heuristics that ignore user activities and personal preferences. We present PowerLens, a system that tames the reasoning power of Large Language Models (LLMs) for safe and personalized mobile power management on Android devices. The key idea is that LLMs' commonsense reasoning can bridge the semantic gap between user activities and system parameters, enabling zero-shot, context-aware policy generation that adapts to individual preferences through implicit feedback. PowerLens employs a multi-agent architecture that recognizes user context from UI semantics and generates holistic power policies across 18 device parameters. A PDL-based constraint framework verifies every action before execution, while a two-tier memory system learns individualized preferences from implicit user overrides through confidence-based distillation, requiring no explicit configuration and converging within 3--5 days. Extensive experiments on a rooted Android device show that PowerLens achieves 81.7% action accuracy and 38.8% energy saving over stock Android, outperforming rule-based and LLM-based baselines, with high user satisfaction, fast preference convergence, and strong safety guarantees, with the system itself consuming only 0.5% of daily battery capacity.
Fonte: arXiv cs.AI
Privacy/Security/Fairness • Score 85
DPxFin: Adaptive Differential Privacy for Anti-Money Laundering Detection via Reputation-Weighted Federated Learning
arXiv:2603.19314v1 Announce Type: new
Abstract: In the modern financial system, combating money laundering is a critical challenge complicated by data privacy concerns and increasingly complex fraud transaction patterns. Although federated learning (FL) is a promising problem-solving approach as it allows institutions to train their models without sharing their data, it has the drawback of being prone to privacy leakage, specifically in tabular data forms like financial data. To address this, we propose DPxFin, a novel federated framework that integrates reputation-guided adaptive differential privacy. Our approach computes client reputation by evaluating the alignment between locally trained models and the global model. Based on this reputation, we dynamically assign differential privacy noise to client updates, enhancing privacy while maintaining overall model utility. Clients with higher reputations receive lower noise to amplify their trustworthy contributions, while low-reputation clients are allocated stronger noise to mitigate risk. We validate DPxFin on the Anti-Money Laundering (AML) dataset under both IID and non-IID settings using Multi Layer Perceptron (MLP). Experimental analysis established that our approach has a more desirable trade-off between accuracy and privacy than those of traditional FL and fixed-noise Differential Privacy (DP) baselines, where performance improvements were consistent, even though on a modest scale. Moreover, DPxFin does withstand tabular data leakage attacks, proving its effectiveness under real-world financial conditions.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Speculating Experts Accelerates Inference for Mixture-of-Experts
arXiv:2603.19289v1 Announce Type: cross
Abstract: Mixture-of-Experts (MoE) models have gained popularity as a means of scaling the capacity of large language models (LLMs) while maintaining sparse activations and reduced per-token compute. However, in memory-constrained inference settings, expert weights must be offloaded to CPU, creating a performance bottleneck from CPU-GPU transfers during decoding. We propose an expert prefetching scheme that leverages currently computed internal model representations to speculate future experts, enabling memory transfers to overlap with computation. Across multiple MoE architectures, we demonstrate that future experts can be reliably predicted by these internal representations. We also demonstrate that executing speculated experts generally maintains downstream task accuracy, thus preserving more effective compute-memory overlap by eliminating the need to re-fetch true router-selected experts. Integrated into an optimized inference engine, our approach achieves up to 14\% reduction in time per output token (TPOT) over on-demand loading of experts from CPU memory. For MoEs where speculative execution alone yields suboptimal accuracy, we further examine lightweight estimators that improve expert prediction hit rates, thereby reducing performance degradation. Our code is released in open-source at https://github.com/axonn-ai/yalis/tree/offload_prefetch.
Fonte: arXiv cs.AI
RecSys • Score 85
DIAL-KG: Schema-Free Incremental Knowledge Graph Construction via Dynamic Schema Induction and Evolution-Intent Assessment
arXiv:2603.20059v1 Announce Type: new
Abstract: Knowledge Graphs (KGs) are foundational to applications such as search, question answering, and recommendation. Conventional knowledge graph construction methods are predominantly static, rely ing on a single-step construction from a fixed corpus with a prede f
ined schema. However, such methods are suboptimal for real-world sce narios where data arrives dynamically, as incorporating new informa tion requires complete and computationally expensive graph reconstruc tions. Furthermore, predefined schemas hinder the flexibility of knowl edge graph construction. To address these limitations, we introduce DIAL KG, a closed-loop framework for incremental KG construction orches trated by a Meta-Knowledge Base (MKB). The framework oper ates in a three-stage cycle: (i) Dual-Track Extraction, which ensures knowledge completeness by defaulting to triple generation and switching to event extraction for complex knowledge; (ii) Governance Adjudica tion, which ensures the fidelity and currency of extracted facts to prevent hallucinations and knowledge staleness; and (iii) Schema Evolution, in which new schemas are induced from validated knowledge to guide subsequent construction cycles, and knowledge from the current round is incrementally applied to the existing KG. Extensive experiments demon strate that our framework achieves state-of-the-art (SOTA) performance in the quality of both the constructed graph and the induced schemas.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Autonoma: A Hierarchical Multi-Agent Framework for End-to-End Workflow Automation
arXiv:2603.19270v1 Announce Type: new
Abstract: The increasing complexity of user demands necessitates automation frameworks that can reliably translate open-ended instructions into robust, multi-step workflows. Current monolithic agent architectures often struggle with the challenges of scalability, error propagation, and maintaining focus across diverse tasks. This paper introduces Autonoma, a structured, hierarchical multi-agent framework designed for end-to-end workflow automation from natural language prompts. Autonoma employs a principled, multi-tiered architecture where a high-level Coordinator validates user intent, a Planner generates structured workflows, and a Supervisor dynamically manages the execution by orchestrating a suite of modular, specialized agents (e.g., for web browsing, coding, file management). This clear separation between orchestration logic and specialized execution ensures robustness through active monitoring and error handling, while enabling extensibility by allowing new capabilities to be integrated as plug-and-play agents without modifying the core engine. Implemented as a fully functional system operating within a secure LAN environment, Autonoma addresses critical data privacy and reliability concerns. The system is further engineered for inclusivity, accepting multi-modal input (text, voice, image, files) and supporting both English and Arabic. Autonoma achieved a 97% task completion rate and a 98% successful agent handoff rate, confirming its operational reliability and efficient collaboration.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
A Dynamic Bayesian and Machine Learning Framework for Quantitative Evaluation and Prediction of Operator Situation Awareness in Nuclear Power Plants
arXiv:2603.19298v1 Announce Type: new
Abstract: Operator situation awareness is a pivotal yet elusive determinant of human reliability in complex nuclear control environments. Existing assessment methods, such as SAGAT and SART, remain static, retrospective, and detached from the evolving cognitive dynamics that drive operational risk. To overcome these limitations, this study introduces the dynamic Bayesian machine learning framework for situation awareness (DBML SA), a unified approach that fuses probabilistic reasoning and data driven intelligence to achieve quantitative, interpretable, and predictive situation awareness modeling. Leveraging 212 operational event reports (2007 to 2021), the framework reconstructs the causal temporal structure of 11 performance shaping factors across multiple cognitive layers. The Bayesian component enables time evolving inference of situation awareness reliability under uncertainty, while the neural component establishes a nonlinear predictive mapping from PSFs to SART scores, achieving a mean absolute percentage error of 13.8 % with statistical consistency to subjective evaluations (p > 0.05). Results highlight training quality and stress dynamics as primary drivers of situation awareness degradation. Overall, DBML SA transcends traditional questionnaire-based assessments by enabling real-time cognitive monitoring, sensitivity analysis, and early-warning prediction, paving the way toward intelligent human machine reliability management in next-generation digital main control rooms.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
Joint Return and Risk Modeling with Deep Neural Networks for Portfolio Construction
arXiv:2603.19288v1 Announce Type: cross
Abstract: Portfolio construction traditionally relies on separately estimating expected returns and covariance matrices using historical statistics, often leading to suboptimal allocation under time-varying market conditions. This paper proposes a joint return and risk modeling framework based on deep neural networks that enables end-to-end learning of dynamic expected returns and risk structures from sequential financial data. Using daily data from ten large-cap US equities spanning 2010 to 2024, the proposed model is evaluated across return prediction, risk estimation, and portfolio-level performance. Out-of-sample results during 2020 to 2024 show that the deep forecasting model achieves competitive predictive accuracy (RMSE = 0.0264) with economically meaningful directional accuracy (51.9%). More importantly, the learned representation effectively captures volatility clustering and regime shifts. When integrated into portfolio optimization, the proposed Neural Portfolio strategy achieves an annual return of 36.4% and a Sharpe ratio of 0.91, outperforming equal weight and historical mean-variance benchmarks in terms of risk-adjusted performance. These findings demonstrate that jointly modeling return and covariance dynamics can provide consistent improvements over traditional allocation approaches. The framework offers a scalable and practical alternative for data-driven portfolio construction under nonstationary market conditions.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
Do Post-Training Algorithms Actually Differ? A Controlled Study Across Model Scales Uncovers Scale-Dependent Ranking Inversions
arXiv:2603.19335v1 Announce Type: new
Abstract: Post-training alignment has produced dozens of competing algorithms -- DPO, SimPO, KTO, GRPO, and others -- yet practitioners lack controlled comparisons to guide algorithm selection. We present OXRL, a unified framework implementing 51 post-training algorithms with identical infrastructure, enabling the first large-scale apples-to-apples evaluation. Our study spans 8 algorithms across 4 model scales (0.5B--7B), 3 evaluation domains, and a 20-variant DPO taxonomy (100 runs at 1.5B, 5 seeds each), totaling $\sim$240 training runs on H100 GPUs. Three headline findings emerge. (1)~Algorithm rankings are unstable across scale: at 1.5B, online RL (SGRPO) tops all methods at 58.0\%~$\pm$0.57 on GSM8K; by 7B, the worst small-scale method (SimPO) becomes the best (85.8\%), a complete ranking inversion driven by model scale rather than LoRA regularization (confirmed via 2$\times$2 factorial). (2)~Loss function modifications yield negligible gains: none of 20 DPO variants significantly outperform vanilla DPO after Bonferroni correction; the sole significant outlier, SimPO, is worse ($-$11.5~pp, $p < 10^{-4}$). (3)~Algorithm leverage is task-specific: the 19.3~pp GSM8K spread collapses to 0.54~pp on MATH ($36\times$) and 0.47~pp on general-domain benchmarks ($41\times$), confirming that algorithm choice matters primarily within the training distribution. These findings yield a hierarchy of leverage for practitioners: model scale (${\sim}$50~pp) $\gg$ training paradigm (${\sim}$10~pp) $\gg$ online vs.\ offline (${\sim}$9~pp) $\gg$ loss function (${\sim}$1~pp). We release all code, configs, and evaluation data as a living community benchmark.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion
arXiv:2603.19266v1 Announce Type: cross
Abstract: Distilling robust reasoning capabilities from large language models (LLMs) into smaller, computationally efficient student models remains an unresolved challenge. Despite recent advances, distilled models frequently suffer from superficial pattern memorization and subpar generalization. To overcome these limitations, we introduce a novel distillation framework that moves beyond simple mimicry to instill a deeper conceptual understanding. Our framework features two key innovations. \underline{\textit{First}}, to address pattern memorization, Explanatory Inversion (EI) generates targeted ``explanatory probes'' that compel the student to articulate the underlying logic behind an answer, rather than just memorizing it. \underline{\textit{Second}}, to improve generalization, Explanatory GRPO (\texttt{EXGRPO}) uses a reinforcement learning algorithm with a novel Dialogue Structure Utility Bonus, which explicitly rewards the student for maintaining a coherent reasoning process across these probes. Extensive evaluations on 12 datasets demonstrate significant improvements. Using Gemma-7b as the student model, our method yields an average \textbf{20.39\%} increase over zero-shot performance and a \textbf{6.02\%} improvement over the state-of-the-art distillation baselines. Moreover, models distilled with our method show remarkable training efficiency (e.g., surpassing vanilla fine-tuning with \textbf{10-25\%} training data) and strong generalization to out-of-distribution tasks. Implementation is released at https://github.com/Zhen-Tan-dmml/ExGRPO.git.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
PRIME-CVD: A Parametrically Rendered Informatics Medical Environment for Education in Cardiovascular Risk Modelling
arXiv:2603.19299v1 Announce Type: new
Abstract: In recent years, progress in medical informatics and machine learning has been accelerated by the availability of openly accessible benchmark datasets. However, patient-level electronic medical record (EMR) data are rarely available for teaching or methodological development due to privacy, governance, and re-identification risks. This has limited reproducibility, transparency, and hands-on training in cardiovascular risk modelling. Here we introduce PRIME-CVD, a parametrically rendered informatics medical environment designed explicitly for medical education. PRIME-CVD comprises two openly accessible synthetic data assets representing a cohort of 50,000 adults undergoing primary prevention for cardiovascular disease. The datasets are generated entirely from a user-specified causal directed acyclic graph parameterised using publicly available Australian population statistics and published epidemiologic effect estimates, rather than from patient-level EMR data or trained generative models. Data Asset 1 provides a clean, analysis-ready cohort suitable for exploratory analysis, stratification, and survival modelling, while Data Asset 2 restructures the same cohort into a relational, EMR-style database with realistic structural and lexical heterogeneity. Together, these assets enable instruction in data cleaning, harmonisation, causal reasoning, and policy-relevant risk modelling without exposing sensitive information. Because all individuals and events are generated de novo, PRIME-CVD preserves realistic subgroup imbalance and risk gradients while ensuring negligible disclosure risk. PRIME-CVD is released under a Creative Commons Attribution 4.0 licence to support reproducible research and scalable medical education.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
BEAVER: A Training-Free Hierarchical Prompt Compression Method via Structure-Aware Page Selection
arXiv:2603.19635v1 Announce Type: new
Abstract: The exponential expansion of context windows in LLMs has unlocked capabilities for long-document understanding but introduced severe bottlenecks in inference latency and information utilization. Existing compression methods often suffer from high training costs or semantic fragmentation due to aggressive token pruning. In this paper, we propose BEAVER, a novel training-free framework that shifts compression from linear token removal to structure-aware hierarchical selection. BEAVER maximizes hardware parallelism by mapping variable-length contexts into dense page-level tensors via dual-path pooling, and preserves discourse integrity through a hybrid planner combining semantic and lexical dual-branch selection with sentence smoothing. Extensive evaluations on four long-context benchmarks demonstrate that BEAVER achieves comparable performance to state-of-the-art (SOTA) methods like LongLLMLingua. Notably, on the RULER benchmark, BEAVER maintains high fidelity in multi-needle retrieval where baselines deteriorate. Regarding efficiency, BEAVER reduces latency by 26.4x on 128k contexts, offering a scalable solution for high-throughput applications. Our code is available at https://cslikai.cn/BEAVER/.
Fonte: arXiv cs.CL
MLOps/Systems • Score 85
ARMOR: Adaptive Resilience Against Model Poisoning Attacks in Continual Federated Learning for Mobile Indoor Localization
arXiv:2603.19594v1 Announce Type: new
Abstract: Indoor localization has become increasingly essential for applications ranging from asset tracking to delivering personalized services. Federated learning (FL) offers a privacy-preserving approach by training a centralized global model (GM) using distributed data from mobile devices without sharing raw data. However, real-world deployments require a continual federated learning (CFL) setting, where the GM receives continual updates under device heterogeneity and evolving indoor environments. In such dynamic conditions, erroneous or biased updates can cause the GM to deviate from its expected learning trajectory, gradually degrading internal GM representations and GM localization performance. This vulnerability is further exacerbated by adversarial model poisoning attacks. To address this challenge, we propose ARMOR, a novel CFL-based framework that monitors and safeguards the GM during continual updates. ARMOR introduces a novel state-space model (SSM) that learns the historical evolution of GM weight tensors and predicts the expected next state of weight tensors of the GM. By comparing incoming local updates with this SSM projection, ARMOR detects deviations and selectively mitigates corrupted updates before local updates are aggregated with the GM. This mechanism enables robust adaptation to temporal environmental dynamics and mitigate the effects of model poisoning attacks while preventing GM corruption. Experimental evaluations in real-world conditions indicate that ARMOR achieves notable improvements, with up to 8.0x reduction in mean error and 4.97x reduction in worst-case error compared to state-of-the-art indoor localization frameworks, demonstrating strong resilience against model corruption tested using real-world data and mobile devices.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
A Federated Many-to-One Hopfield model for associative Neural Networks
arXiv:2603.19902v1 Announce Type: cross
Abstract: Federated learning enables collaborative training without sharing raw data, but struggles under client heterogeneity and streaming distribution shifts, where drift and novel data can impair convergence and cause forgetting. We propose a federated associative-memory framework that learns shared archetypes in heterogeneous, continual settings, where client data are independent but not necessarily balanced. Each client encodes its experience as a low-rank Hebbian operator, sent to a central server for aggregation and factorization into global archetypes. This approach preserves privacy, avoids centralized replay buffers, and is robust to small, noisy, or evolving datasets. We cast aggregation as a low-rank-plus-noise spectral inference problem, deriving theoretical thresholds for detectability and retrieval robustness. An entropy-based controller balances stability and plasticity in streaming regimes. Experiments with heterogeneous clients, drift, and novelty show improved global archetype reconstruction and associative retrieval, supporting the spectral view of federated consolidation.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
Warm-Start Flow Matching for Guaranteed Fast Text/Image Generation
arXiv:2603.19360v1 Announce Type: new
Abstract: Current auto-regressive (AR) LLMs, diffusion-based text/image generative models, and recent flow matching (FM) algorithms are capable of generating premium quality text/image samples. However, the inference or sample generation in these models is often very time-consuming and computationally demanding, mainly due to large numbers of function evaluations corresponding to the lengths of tokens or the numbers of diffusion steps. This also necessitates heavy GPU resources, time, and electricity. In this work we propose a novel solution to reduce the sample generation time of flow matching algorithms by a guaranteed speed-up factor, without sacrificing the quality of the generated samples. Our key idea is to utilize computationally lightweight generative models whose generation time is negligible compared to that of the target AR/FM models. The draft samples from a lightweight model, whose quality is not satisfactory but fast to generate, are regarded as an initial distribution for a FM algorithm. Unlike conventional usage of FM that takes a pure noise (e.g., Gaussian or uniform) initial distribution, the draft samples are already of decent quality, so we can set the starting time to be closer to the end time rather than 0 in the pure noise FM case. This will significantly reduce the number of time steps to reach the target data distribution, and the speed-up factor is guaranteed. Our idea, dubbed {\em Warm-Start FM} or WS-FM, can essentially be seen as a {\em learning-to-refine} generative model from low-quality draft samples to high-quality samples. As a proof of concept, we demonstrate the idea on some synthetic toy data as well as real-world text and image generation tasks, illustrating that our idea offers guaranteed speed-up in sample generation without sacrificing the quality of the generated samples.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Enhancing Legal LLMs through Metadata-Enriched RAG Pipelines and Direct Preference Optimization
arXiv:2603.19251v1 Announce Type: new
Abstract: Large Language Models (LLMs) perform well in short contexts but degrade on long legal documents, often producing hallucinations such as incorrect clauses or precedents. In the legal domain, where precision is critical, such errors undermine reliability and trust.
Retrieval Augmented Generation (RAG) helps ground outputs but remains limited in legal settings, especially with small, locally deployed models required for data privacy. We identify two failure modes: retrieval errors due to lexical redundancy in legal corpora, and decoding errors where models generate answers despite insufficient context.
To address this, we propose Metadata Enriched Hybrid RAG to improve document level retrieval, and apply Direct Preference Optimization (DPO) to enforce safe refusal when context is inadequate. Together, these methods improve grounding, reliability, and safety in legal language models.
Fonte: arXiv cs.CL
MLOps/Systems • Score 85
Simulation-based Inference with the Python Package sbijax
arXiv:2409.19435v2 Announce Type: replace-cross
Abstract: Neural simulation-based inference (SBI) describes an emerging family of methods for Bayesian inference with intractable likelihood functions that use neural networks as surrogate models. Here we introduce sbijax, a Python package that implements a wide variety of state-of-the-art methods in neural simulation-based inference using a user-friendly programming interface. sbijax offers high-level functionality to quickly construct SBI estimators, and compute and visualize posterior distributions with only a few lines of code. In addition, the package provides functionality for conventional approximate Bayesian computation, to compute model diagnostics, and to automatically estimate summary statistics. By virtue of being entirely written in JAX, sbijax is extremely computationally efficient, allowing rapid training of neural networks and executing code automatically in parallel on both CPU and GPU.
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
Alternating Diffusion for Proximal Sampling with Zeroth Order Queries
arXiv:2603.19633v1 Announce Type: new
Abstract: This work introduces a new approximate proximal sampler that operates solely with zeroth-order information of the potential function. Prior theoretical analyses have revealed that proximal sampling corresponds to alternating forward and backward iterations of the heat flow. The backward step was originally implemented by rejection sampling, whereas we directly simulate the dynamics. Unlike diffusion-based sampling methods that estimate scores via learned models or by invoking auxiliary samplers, our method treats the intermediate particle distribution as a Gaussian mixture, thereby yielding a Monte Carlo score estimator from directly samplable distributions. Theoretically, when the score estimation error is sufficiently controlled, our method inherits the exponential convergence of proximal sampling under isoperimetric conditions on the target distribution. In practice, the algorithm avoids rejection sampling, permits flexible step sizes, and runs with a deterministic runtime budget. Numerical experiments demonstrate that our approach converges rapidly to the target distribution, driven by interactions among multiple particles and by exploiting parallel computation.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Scalable Prompt Routing via Fine-Grained Latent Task Discovery
arXiv:2603.19415v1 Announce Type: new
Abstract: Prompt routing dynamically selects the most appropriate large language model from a pool of candidates for each query, optimizing performance while managing costs. As model pools scale to include dozens of frontier models with narrow performance gaps, existing approaches face significant challenges: manually defined task taxonomies cannot capture fine-grained capability distinctions, while monolithic routers struggle to differentiate subtle differences across diverse tasks. We propose a two-stage routing architecture that addresses these limitations through automated fine-grained task discovery and task-aware quality estimation. Our first stage employs graph-based clustering to discover latent task types and trains a classifier to assign prompts to discovered tasks. The second stage uses a mixture-of-experts architecture with task-specific prediction heads for specialized quality estimates. At inference, we aggregate predictions from both stages to balance task-level stability with prompt-specific adaptability. Evaluated on 10 benchmarks with 11 frontier models, our method consistently outperforms existing baselines and surpasses the strongest individual model while incurring less than half its cost.
Fonte: arXiv cs.CL
Theory/Optimization • Score 85
Scalable Learning of Multivariate Distributions via Coresets
arXiv:2603.19792v1 Announce Type: cross
Abstract: Efficient and scalable non-parametric or semi-parametric regression analysis and density estimation are of crucial importance to the fields of statistics and machine learning. However, available methods are limited in their ability to handle large-scale data. We address this issue by developing a novel coreset construction for multivariate conditional transformation models (MCTMs) to enhance their scalability and training efficiency. To the best of our knowledge, these are the first coresets for semi-parametric distributional models. Our approach yields substantial data reduction via importance sampling. It ensures with high probability that the log-likelihood remains within multiplicative error bounds of $(1\pm\varepsilon)$ and thereby maintains statistical model accuracy. Compared to conventional full-parametric models, where coresets have been incorporated before, our semi-parametric approach exhibits enhanced adaptability, particularly in scenarios where complex distributions and non-linear relationships are present, but not fully understood. To address numerical problems associated with normalizing logarithmic terms, we follow a geometric approximation based on the convex hull of input data. This ensures feasible, stable, and accurate inference in scenarios involving large amounts of data. Numerical experiments demonstrate substantially improved computational efficiency when handling large and complex datasets, thus laying the foundation for a broad range of applications within the statistics and machine learning communities.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
On Performance Guarantees for Federated Learning with Personalized Constraints
arXiv:2603.19617v1 Announce Type: new
Abstract: Federated learning (FL) has emerged as a communication-efficient algorithmic framework for distributed learning across multiple agents. While standard FL formulations capture unconstrained or globally constrained problems, many practical settings involve heterogeneous resource or model constraints, leading to optimization problems with agent-specific feasible sets. Here, we study a personalized constrained federated optimization problem in which each agent is associated with a convex local objective and a private constraint set. We propose PC-FedAvg, a method in which each agent maintains cross-estimates of the other agents' variables through a multi-block local decision vector. Each agent updates all blocks locally, penalizing infeasibility only in its own block. Moreover, the cross-estimate mechanism enables personalization without requiring consensus or sharing constraint information among agents. We establish communication-complexity rates of $\mathcal{O}(\epsilon^{-2})$ for suboptimality and $\mathcal{O}(\epsilon^{-1})$ for agent-wise infeasibility. Preliminary experiments on the MNIST and CIFAR-10 datasets validate our theoretical findings.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
DAPA: Distribution Aware Piecewise Activation Functions for On-Device Transformer Inference and Training
arXiv:2603.19338v1 Announce Type: new
Abstract: Non-linear activation functions play a pivotal role in on-device inference and training, as they not only consume substantial hardware resources but also impose a significant impact on system performance and energy efficiency. In this work, we propose Distribution-Aware Piecewise Activation (DAPA), a differentiable and hardware-friendly activation function for Transformer architectures by exploiting the distribution of pre-activation data. DAPA employs a non-uniform piecewise approximation that allocates finer segments to high-probability regions of the distribution, improving generalizability over prior piecewise linear methods. The resulting approximation is further quantized using Distribution-Weighted Mean Square Error to reduce latency and resource utilization for hardware deployment. Our HLS implementation demonstrates that DAPA speeds up GELU computation by 16$\times$ and decreases DSP utilization by 16$\times$ while maintaining comparable or better performance across vision Transformers and GPT-2 models.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoning
arXiv:2603.19639v1 Announce Type: new
Abstract: Although agentic workflows have demonstrated strong potential for solving complex tasks, existing automated generation methods remain inefficient and underperform, as they rely on predefined operator libraries and homogeneous LLM-only workflows in which all task-level computation is performed through probabilistic inference. To address these limitations, we propose HyEvo, an automated workflow-generation framework that leverages heterogeneous atomic synthesis. HyEvo integrates probabilistic LLM nodes for semantic reasoning with deterministic code nodes for rule-based execution, offloading predictable operations from LLM inference and reducing inference cost and execution latency. To efficiently navigate the hybrid search space, HyEvo employs an LLM-driven multi-island evolutionary strategy with a reflect-then-generate mechanism, iteratively refining both workflow topology and node logic via execution feedback. Comprehensive experiments show that HyEvo consistently outperforms existing methods across diverse reasoning and coding benchmarks, while reducing inference cost and execution latency by up to 19$\times$ and 16$\times$, respectively, compared to the state-of-the-art open-source baseline.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
ParallelVLM: Lossless Video-LLM Acceleration with Visual Alignment Aware Parallel Speculative Decoding
arXiv:2603.19610v1 Announce Type: new
Abstract: Although current Video-LLMs achieve impressive performance in video understanding tasks, their autoregressive decoding efficiency remains constrained by the massive number of video tokens. Visual token pruning can partially ease this bottleneck, yet existing approaches still suffer from information loss and yield only modest acceleration in decoding. In this paper, we propose ParallelVLM, a training-free draft-then-verify speculative decoding framework that overcomes both mutual waiting and limited speedup-ratio problems between draft and target models in long-video settings. ParallelVLM features two parallelized stages that maximize hardware utilization and incorporate an Unbiased Verifier-Guided Pruning strategy to better align the draft and target models by eliminating the positional bias in attention-guided pruning. Extensive experiments demonstrate that ParallelVLM effectively expands the draft window by $1.6\sim1.8\times$ with high accepted lengths, and accelerates various video understanding benchmarks by 3.36$\times$ on LLaVA-Onevision-72B and 2.42$\times$ on Qwen2.5-VL-32B compared with vanilla autoregressive decoding.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Beyond Quadratic: Linear-Time Change Detection with RWKV
arXiv:2603.19606v1 Announce Type: new
Abstract: Existing paradigms for remote sensing change detection are caught in a trade-off: CNNs excel at efficiency but lack global context, while Transformers capture long-range dependencies at a prohibitive computational cost. This paper introduces ChangeRWKV, a new architecture that reconciles this conflict. By building upon the Receptance Weighted Key Value (RWKV) framework, our ChangeRWKV uniquely combines the parallelizable training of Transformers with the linear-time inference of RNNs. Our approach core features two key innovations: a hierarchical RWKV encoder that builds multi-resolution feature representation, and a novel Spatial-Temporal Fusion Module (STFM) engineered to resolve spatial misalignments across scales while distilling fine-grained temporal discrepancies. ChangeRWKV not only achieves state-of-the-art performance on the LEVIR-CD benchmark, with an 85.46% IoU and 92.16% F1 score, but does so while drastically reducing parameters and FLOPs compared to previous leading methods. This work demonstrates a new, efficient, and powerful paradigm for operational-scale change detection. Our code and model are publicly available.
Fonte: arXiv cs.CV
NLP/LLMs • Score 90
A Subgoal-driven Framework for Improving Long-Horizon LLM Agents
arXiv:2603.19685v1 Announce Type: new
Abstract: Large language model (LLM)-based agents have emerged as powerful autonomous controllers for digital environments, including mobile interfaces, operating systems, and web browsers. Web navigation, for example, requires handling dynamic content and long sequences of actions, making it particularly challenging. Existing LLM-based agents struggle with long-horizon planning in two main ways. During online execution, they often lose track as new information arrives, lacking a clear and adaptive path toward the final goal. This issue is further exacerbated during reinforcement learning (RL) fine-tuning, where sparse and delayed rewards make it difficult for agents to identify which actions lead to success, preventing them from maintaining coherent reasoning over extended tasks. To address these challenges, we propose two contributions. First, we introduce an agent framework that leverages proprietary models for online planning through subgoal decomposition. Second, we present MiRA (Milestoning your Reinforcement Learning Enhanced Agent), an RL training framework that uses dense, milestone-based reward signals. The real-time planning mechanism improves proprietary models such as Gemini by approximately a 10% absolute increase in success rate (SR) on the WebArena-Lite benchmark. Meanwhile, applying MiRA to the open Gemma3-12B model increases its success rate from 6.4% to 43.0%. This performance surpasses proprietary systems such as GPT-4-Turbo (17.6%) and GPT-4o (13.9%), as well as the previous open-model state of the art, WebRL (38.4%). Overall, our findings demonstrate that combining explicit inference-time planning with milestone-based rewards significantly improves an agent's long-horizon capabilities, paving the way for more robust and general-purpose autonomous systems.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Diffusion-Guided Semantic Consistency for Multimodal Heterogeneity
arXiv:2603.19337v1 Announce Type: new
Abstract: Federated learning (FL) is severely challenged by non-independent and identically distributed (non-IID) client data, a problem that degrades global model performance, especially in multimodal perception settings. Conventional methods often fail to address the underlying semantic discrepancies between clients, leading to suboptimal performance for multimedia systems requiring robust perception. To overcome this, we introduce SemanticFL, a novel framework that leverages the rich semantic representations of pre-trained diffusion models to provide privacy-preserving guidance for local training. Our approach leverages multi-layer semantic representations from a pre-trained Stable Diffusion model (including VAE-encoded latents and U-Net hierarchical features) to create a shared latent space that aligns heterogeneous clients, facilitated by an efficient client-server architecture that offloads heavy computation to the server. A unified consistency mechanism, employing cross-modal contrastive learning, further stabilizes convergence. We conduct extensive experiments on benchmarks including CIFAR-10, CIFAR-100, and TinyImageNet under diverse heterogeneity scenarios. Our results demonstrate that SemanticFL surpasses existing federated learning approaches, achieving accuracy gains of up to 5.49% over FedAvg, validating its effectiveness in learning robust representations for heterogeneous and multimodal data for perception tasks.
Fonte: arXiv cs.CV
Vision • Score 85
Instruction-Free Tuning of Large Vision Language Models for Medical Instruction Following
arXiv:2603.19482v1 Announce Type: new
Abstract: Large vision language models (LVLMs) have demonstrated impressive performance across a wide range of tasks. These capabilities largely stem from visual instruction tuning, which fine-tunes models on datasets consisting of curated image-instruction-output triplets. However, in the medical domain, constructing large-scale, high-quality instruction datasets is particularly challenging due to the need for specialized expert knowledge. To address this issue, we propose an instruction-free tuning approach that reduces reliance on handcrafted instructions, leveraging only image-description pairs for fine-tuning. Specifically, we introduce a momentum proxy instruction as a replacement for curated text instructions, which preserves the instruction-following capability of the pre-trained LVLM while promoting updates to parameters that remain valid during inference. Consequently, the fine-tuned LVLM can flexibly respond to domain-specific instructions, even though explicit instructions are absent during fine-tuning. Additionally, we incorporate a response shuffling strategy to mitigate the model's over-reliance on previous words, facilitating more effective fine-tuning. Our approach achieves state-of-the-art accuracy on multiple-choice visual question answering tasks across SKINCON, WBCAtt, CBIS, and MIMIC-CXR datasets, significantly enhancing the fine-tuning efficiency of LVLMs in medical domains.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
An Auditable AI Agent Loop for Empirical Economics: A Case Study in Forecast Combination
arXiv:2603.17381v3 Announce Type: replace-cross
Abstract: AI coding agents make empirical specification search fast and cheap, but they also widen hidden researcher degrees of freedom. Building on an open-source agent-loop architecture, this paper adapts that framework to an empirical economics workflow and adds a post-search holdout evaluation. In a forecast-combination illustration, multiple independent agent runs outperform standard benchmarks in the original rolling evaluation, but not all continue to do so on a post-search holdout. Logged search and holdout evaluation together make adaptive specification search more transparent and help distinguish robust improvements from sample-specific discoveries.
Fonte: arXiv stat.ML
Multimodal • Score 90
CurveStream: Boosting Streaming Video Understanding in MLLMs via Curvature-Aware Hierarchical Visual Memory Management
arXiv:2603.19571v1 Announce Type: new
Abstract: Multimodal Large Language Models have achieved significant success in offline video understanding, yet their application to streaming videos is severely limited by the linear explosion of visual tokens, which often leads to Out-of-Memory (OOM) errors or catastrophic forgetting. Existing visual retention and memory management methods typically rely on uniform sampling, low-level physical metrics, or passive cache eviction. However, these strategies often lack intrinsic semantic awareness, potentially disrupting contextual coherence and blurring transient yet critical semantic transitions. To address these limitations, we propose CurveStream, a training-free, curvature-aware hierarchical visual memory management framework. Our approach is motivated by the key observation that high-curvature regions along continuous feature trajectories closely align with critical global semantic transitions. Based on this geometric insight, CurveStream evaluates real-time semantic intensity via a Curvature Score and integrates an online K-Sigma dynamic threshold to adaptively route frames into clear and fuzzy memory states under a strict token budget. Evaluations across diverse temporal scales confirm that this lightweight framework, CurveStream, consistently yields absolute performance gains of over 10% (e.g., 10.69% on StreamingBench and 13.58% on OVOBench) over respective baselines, establishing new state-of-the-art results for streaming video perception.The code will be released at https://github.com/streamingvideos/CurveStream.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems
arXiv:2603.19677v1 Announce Type: new
Abstract: Large language model (LLM)-based multi-agent systems (MAS) have demonstrated exceptional capabilities in solving complex tasks, yet their effectiveness depends heavily on the underlying communication topology that coordinates agent interactions. Within these systems, successful problem-solving often necessitates task-specific group structures to divide and conquer subtasks. However, most existing approaches generate communication topologies in a node-centric manner, leaving group structures to emerge implicitly from local connectivity decisions rather than modeling them explicitly, often leading to suboptimal coordination and unnecessary communication overhead. To address this limitation, we propose GoAgent (Group-of-Agents), a communication topology generation method that explicitly treats collaborative groups as the atomic units of MAS construction. Specifically, GoAgent first enumerates task-relevant candidate groups through an LLM and then autoregressively selects and connects these groups as atomic units to construct the final communication graph, jointly capturing intra-group cohesion and inter-group coordination. To mitigate communication redundancy and noise propagation inherent in expanding topologies, we further introduce a conditional information bottleneck (CIB) objective that compresses inter-group communication, preserving task-relevant signals while filtering out redundant historical noise. Extensive experiments on six benchmarks demonstrate the state-of-the-art performance of GoAgent with 93.84% average accuracy while reducing token consumption by about 17%.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
The Residual Stream Is All You Need: On the Redundancy of the KV Cache in Transformer Inference
arXiv:2603.19664v1 Announce Type: new
Abstract: The key-value (KV) cache is widely treated as essential state in transformer inference, and a large body of work engineers policies to compress, evict, or approximate its entries. We prove that this state is entirely redundant: keys and values at every layer are deterministic projections of the residual stream, and recomputing them from a single residual vector per token incurs exactly zero reconstruction error, not approximately, but bit-identically. We verify this across six models from four architecture families (135M to 4B parameters). Cross-task residual patching at every layer produces D_KL = 0 between patched and original output distributions, confirming that the residual stream satisfies a Markov property and is the sole information-carrying state. Removing the cache entirely and recomputing from scratch yields token-identical output under greedy decoding on all models tested. We build on this result with KV-Direct, a bounded-memory inference scheme that checkpoints residual vectors (5 KB per token on Gemma 3-4B) instead of full KV pairs (136 KB), recomputing keys and values on demand. Over 20 conversation turns, KV-Direct holds peak memory at 42 MB while the standard cache grows past 103 MB. Against five eviction baselines (H2O, StreamingLLM, SnapKV, TOVA, window-only), KV-Direct maintains 100% token match at every cache budget; all baselines degrade to 5-28%. A per-operation latency analysis shows recomputation runs up to 5x faster than reading cached tensors at moderate batch sizes. Code is available at https://github.com/Kaleemullahqasim/KV-Direct.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
Scalable Cross-Facility Federated Learning for Scientific Foundation Models on Multiple Supercomputers
arXiv:2603.19544v1 Announce Type: new
Abstract: Artificial Intelligence for scientific applications increasingly requires training large models on data that cannot be centralized due to privacy constraints, data sovereignty, or the sheer volume of data generated. Federated learning (FL) addresses this by enabling collaborative training without centralizing raw data, but scientific applications demand model scales that requires extensive computing resources, typically offered at High Performance Computing (HPC) facilities. Deploying FL experiments across HPC facilities introduces challenges beyond cloud or enterprise settings. We present a comprehensive cross-facility FL framework for heterogeneous HPC environments, built on Advanced Privacy-Preserving Federated Learning (APPFL) framework with Globus Compute and Transfer orchestration, and evaluate it across four U.S. Department of Energy (DOE) leadership-class supercomputers. We demonstrate that FL experiments across HPC facilities are practically achievable, characterize key sources of heterogeneity impacting the training performance, and show that algorithmic choices matter significantly under realistic HPC scheduling conditions. We validate the scientific applicability by fine-tuning a large language model on a chemistry instruction dataset, and identify scheduler-aware algorithm design as a critical open challenge for future deployments.
Fonte: arXiv cs.LG
RL • Score 85
Stochastic Sequential Decision Making over Expanding Networks with Graph Filtering
arXiv:2603.19501v1 Announce Type: new
Abstract: Graph filters leverage topological information to process networked data with existing methods mainly studying fixed graphs, ignoring that graphs often expand as nodes continually attach with an unknown pattern. The latter requires developing filter-based decision-making paradigms that take evolution and uncertainty into account. Existing approaches rely on either pre-designed filters or online learning, limited to a myopic view considering only past or present information. To account for future impacts, we propose a stochastic sequential decision-making framework for filtering networked data with a policy that adapts filtering to expanding graphs. By representing filter shifts as agents, we model the filter as a multi-agent system and train the policy following multi-agent reinforcement learning. This accounts for long-term rewards and captures expansion dynamics through sequential decision-making. Moreover, we develop a context-aware graph neural network to parameterize the policy, which tunes filter parameters based on information of both the graph and agents. Experiments on synthetic and real datasets from cold-start recommendation to COVID prediction highlight the benefits of using a sequential decision-making perspective over batch and online filtering alternatives.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Subspace Kernel Learning on Tensor Sequences
arXiv:2603.19546v1 Announce Type: new
Abstract: Learning from structured multi-way data, represented as higher-order tensors, requires capturing complex interactions across tensor modes while remaining computationally efficient. We introduce Uncertainty-driven Kernel Tensor Learning (UKTL), a novel kernel framework for $M$-mode tensors that compares mode-wise subspaces derived from tensor unfoldings, enabling expressive and robust similarity measure. To handle large-scale tensor data, we propose a scalable Nystr\"{o}m kernel linearization with dynamically learned pivot tensors obtained via soft $k$-means clustering. A key innovation of UKTL is its uncertainty-aware subspace weighting, which adaptively down-weights unreliable mode components based on estimated confidence, improving robustness and interpretability in comparisons between input and pivot tensors. Our framework is fully end-to-end trainable and naturally incorporates both multi-way and multi-mode interactions through structured kernel compositions. Extensive evaluations on action recognition benchmarks (NTU-60, NTU-120, Kinetics-Skeleton) show that UKTL achieves state-of-the-art performance, superior generalization, and meaningful mode-wise insights. This work establishes a principled, scalable, and interpretable kernel learning paradigm for structured multi-way and multi-modal tensor sequences.
Fonte: arXiv cs.LG
Applications • Score 85
TRACE: Trajectory Recovery with State Propagation Diffusion for Urban Mobility
arXiv:2603.19474v1 Announce Type: new
Abstract: High-quality GPS trajectories are essential for location-based web services and smart city applications, including navigation, ride-sharing and delivery. However, due to low sampling rates and limited infrastructure coverage during data collection, real-world trajectories are often sparse and feature unevenly distributed location points. Recovering these trajectories into dense and continuous forms is essential but challenging, given their complex and irregular spatio-temporal patterns. In this paper, we introduce a novel diffusion model for trajectory recovery named TRACE, which reconstruct dense and continuous trajectories from sparse and incomplete inputs. At the core of TRACE, we propose a State Propagation Diffusion Model (SPDM), which integrates a novel memory mechanism, so that during the denoising process, TRACE can retain and leverage intermediate results from previous steps to effectively reconstruct those hard-to-recover trajectory segments. Extensive experiments on multiple real-world datasets show that TRACE outperforms the state-of-the-art, offering $>$26\% accuracy improvement without significant inference overhead. Our work strengthens the foundation for mobile and web-connected location services, advancing the quality and fairness of data-driven urban applications. Code is available at: https://github.com/JinmingWang/TRACE
Fonte: arXiv cs.LG
NLP/LLMs • Score 90
DuCCAE: A Hybrid Engine for Immersive Conversation via Collaboration, Augmentation, and Evolution
arXiv:2603.19248v1 Announce Type: cross
Abstract: Immersive conversational systems in production face a persistent trade-off between responsiveness and long-horizon task capability. Real-time interaction is achievable for lightweight turns, but requests involving planning and tool invocation (e.g., search and media generation) produce heavy-tail execution latency that degrades turn-taking, persona consistency, and user trust. To address this challenge, we propose DuCCAE (Conversation while Collaboration with Augmentation and Evolution), a hybrid engine for immersive conversation deployed within Baidu Search, serving millions of users. DuCCAE decouples real-time response generation from asynchronous agentic execution and synchronizes them via a shared state that maintains session context and execution traces, enabling asynchronous results to be integrated back into the ongoing dialogue. The system orchestrates five subsystems-Info, Conversation, Collaboration, Augmentation, and Evolution-to support multi-agent collaboration and continuous improvement. We evaluate DuCCAE through a comprehensive framework that combines offline benchmarking on the Du-Interact dataset and large-scale production evaluation within Baidu Search. Experimental results demonstrate that DuCCAE outperforms strong baselines in agentic execution reliability and dialogue quality while reducing latency to fit strict real-time budgets. Crucially, deployment metrics since June 2025 confirm substantial real-world effectiveness, evidenced by a tripling of Day-7 user retention to 34.2% and a surge in the complex task completion rate to 65.2%. Our hybrid architecture successfully preserves conversational continuity while enabling reliable agentic execution, offering practical guidelines for deploying scalable agentic systems in industrial settings.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Utility-Guided Agent Orchestration for Efficient LLM Tool Use
arXiv:2603.19896v1 Announce Type: new
Abstract: Tool-using large language model (LLM) agents often face a fundamental tension between answer quality and execution cost. Fixed workflows are stable but inflexible, while free-form multi-step reasoning methods such as ReAct may improve task performance at the expense of excessive tool calls, longer trajectories, higher token consumption, and increased latency. In this paper, we study agent orchestration as an explicit decision problem rather than leaving it entirely to prompt-level behavior. We propose a utility-guided orchestration policy that selects among actions such as respond, retrieve, tool call, verify, and stop by balancing estimated gain, step cost, uncertainty, and redundancy. Our goal is not to claim universally best task performance, but to provide a controllable and analyzable policy framework for studying quality-cost trade-offs in tool-using LLM agents. Experiments across direct answering, threshold control, fixed workflows, ReAct, and several policy variants show that explicit orchestration signals substantially affect agent behavior. Additional analyses on cost definitions, workflow fairness, and redundancy control further demonstrate that lightweight utility design can provide a defensible and practical mechanism for agent control.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
TTQ: Activation-Aware Test-Time Quantization to Accelerate LLM Inference On The Fly
arXiv:2603.19296v1 Announce Type: new
Abstract: To tackle the huge computational demand of large foundation models, activation-aware compression techniques without retraining have been introduced. However, since these methods highly rely on calibration data, domain shift issues may arise for unseen downstream tasks. We propose a test-time quantization (TTQ) framework which compresses large models on the fly at inference time to resolve this issue. With an efficient online calibration, instant activation-aware quantization can adapt every prompt regardless of the downstream tasks, yet achieving inference speedup. Several experiments demonstrate that TTQ can improve the quantization performance over state-of-the-art baselines.
Fonte: arXiv cs.LG
Vision • Score 85
Dual-Domain Representation Alignment: Bridging 2D and 3D Vision via Geometry-Aware Architecture Search
arXiv:2603.19563v1 Announce Type: new
Abstract: Modern computer vision requires balancing predictive accuracy with real-time efficiency, yet the high inference cost of large vision models (LVMs) limits deployment on resource-constrained edge devices. Although Evolutionary Neural Architecture Search (ENAS) is well suited for multi-objective optimization, its practical use is hindered by two issues: expensive candidate evaluation and ranking inconsistency among subnetworks. To address them, we propose EvoNAS, an efficient distributed framework for multi-objective evolutionary architecture search. We build a hybrid supernet that integrates Vision State Space and Vision Transformer (VSS-ViT) modules, and optimize it with a Cross-Architecture Dual-Domain Knowledge Distillation (CA-DDKD) strategy. By coupling the computational efficiency of VSS blocks with the semantic expressiveness of ViT modules, CA-DDKD improves the representational capacity of the shared supernet and enhances ranking consistency, enabling reliable fitness estimation during evolution without extra fine-tuning. To reduce the cost of large-scale validation, we further introduce a Distributed Multi-Model Parallel Evaluation (DMMPE) framework based on GPU resource pooling and asynchronous scheduling. Compared with conventional data-parallel evaluation, DMMPE improves efficiency by over 70% through concurrent multi-GPU, multi-model execution. Experiments on COCO, ADE20K, KITTI, and NYU-Depth v2 show that the searched architectures, termed EvoNets, consistently achieve Pareto-optimal trade-offs between accuracy and efficiency. Compared with representative CNN-, ViT-, and Mamba-based models, EvoNets deliver lower inference latency and higher throughput under strict computational budgets while maintaining strong generalization on downstream tasks such as novel view synthesis. Code is available at https://github.com/EMI-Group/evonas
Fonte: arXiv cs.CV
Privacy/Security/Fairness • Score 85
Parameter-Efficient Token Embedding Editing for Clinical Class-Level Unlearning
arXiv:2603.19302v1 Announce Type: new
Abstract: Machine unlearning is increasingly important for clinical language models, where privacy regulations and institutional policies may require removing sensitive information from deployed systems without retraining from scratch. In practice, deletion requests must balance effective forgetting of targeted information with preservation of model utility and minimal parameter modification. We introduce Sparse Token Embedding Unlearning (STEU), a parameter-efficient method for behavioral class-level unlearning that updates only PMI-selected token embeddings together with a small classifier head while keeping all encoder layers frozen. Across experiments on MIMIC-IV, MIMIC-III, and eICU using BioClinicalBERT, BERT-base, and DistilBERT, STEU consistently suppresses the target class while largely preserving retained task performance. In the primary MIMIC-IV setting, STEU achieves near-complete forgetting (forget F1 = 0.0004) while maintaining competitive retained utility (retain avg F1 = 0.4766) after modifying only 0.19\% of model parameters. These results suggest that targeted behavioral unlearning can be achieved through sparse embedding edits without modifying deeper encoder representations.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
Starting Off on the Wrong Foot: Pitfalls in Data Preparation
arXiv:2603.18190v1 Announce Type: new
Abstract: When working with real-world insurance data, practitioners often encounter challenges during the data preparation stage that can undermine the statistical validity and reliability of downstream modeling. This study illustrates that conventional data preparation procedures such as random train-test partitioning, often yield unreliable and unstable results when confronted with highly imbalanced insurance loss data. To mitigate these limitations, we propose a novel data preparation framework leveraging two recent statistical advancements: support points for representative data splitting to ensure distributional consistency across partitions, and the Chatterjee correlation coefficient for initial, non-parametric feature screening to capture feature relevance and dependence structure. We further integrate these theoretical advances into a unified, efficient framework that also incorporates missing-data handling, and embed this framework within our custom InsurAutoML pipeline. The performance of the proposed approach is evaluated using both simulated datasets and datasets often cited in the academic literature. Our findings definitively demonstrate that incorporating statistically rigorous data preparation methods not only significantly enhances model robustness and interpretability but also substantially reduces computational resource requirements across diverse insurance loss modeling tasks. This work provides a crucial methodological upgrade for achieving reliable results in high stakes insurance applications.
Fonte: arXiv stat.ML
Privacy/Security/Fairness • Score 85
NANOZK: Layerwise Zero-Knowledge Proofs for Verifiable Large Language Model Inference
arXiv:2603.18046v1 Announce Type: new
Abstract: When users query proprietary LLM APIs, they receive outputs with no cryptographic assurance that the claimed model was actually used. Service providers could substitute cheaper models, apply aggressive quantization, or return cached responses - all undetectable by users paying premium prices for frontier capabilities. We present METHOD, a zero-knowledge proof system that makes LLM inference verifiable: users can cryptographically confirm that outputs correspond to the computation of a specific model.
Our approach exploits the fact that transformer inference naturally decomposes into independent layer computations, enabling a layerwise proof framework where each layer generates a constant-size proof regardless of model width. This decomposition sidesteps the scalability barrier facing monolithic approaches and enables parallel proving. We develop lookup table approximations for non-arithmetic operations (softmax, GELU, LayerNorm) that introduce zero measurable accuracy loss, and introduce Fisher information-guided verification for scenarios where proving all layers is impractical.
On transformer models up to d=128, METHOD generates constant-size layer proofs of 5.5KB (2.1KB attention + 3.5KB MLP) with 24 ms verification time. Compared to EZKL, METHOD achieves 70x smaller proofs and 5.7x faster proving time at d=128, while maintaining formal soundness guarantees (epsilon < 1e-37). Lookup approximations preserve model perplexity exactly, enabling verification without quality compromise.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Lightweight Adaptation for LLM-based Technical Service Agent: Latent Logic Augmentation and Robust Noise Reduction
arXiv:2603.18074v1 Announce Type: new
Abstract: Adapting Large Language Models in complex technical service domains is constrained by the absence of explicit cognitive chains in human demonstrations and the inherent ambiguity arising from the diversity of valid responses. These limitations severely hinder agents from internalizing latent decision dynamics and generalizing effectively. Moreover, practical adaptation is often impeded by the prohibitive resource and time costs associated with standard training paradigms. To overcome these challenges and guarantee computational efficiency, we propose a lightweight adaptation framework comprising three key contributions. (1) Latent Logic Augmentation: We introduce Planning-Aware Trajectory Modeling and Decision Reasoning Augmentation to bridge the gap between surface-level supervision and latent decision logic. These approaches strengthen the stability of Supervised Fine-Tuning alignment. (2) Robust Noise Reduction: We construct a Multiple Ground Truths dataset through a dual-filtering method to reduce the noise by validating diverse responses, thereby capturing the semantic diversity. (3) Lightweight Adaptation: We design a Hybrid Reward mechanism that fuses an LLM-based judge with a lightweight relevance-based Reranker to distill high-fidelity reward signals while reducing the computational cost compared to standard LLM-as-a-Judge reinforcement learning. Empirical evaluations on real-world Cloud service tasks, conducted across semantically diverse settings, demonstrate that our framework achieves stability and performance gains through Latent Logic Augmentation and Robust Noise Reduction. Concurrently, our Hybrid Reward mechanism achieves alignment comparable to standard LLM-as-a-judge methods with reduced training time, underscoring the practical value for deploying technical service agents.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
Tula: Optimizing Time, Cost, and Generalization in Distributed Large-Batch Training
arXiv:2603.18112v1 Announce Type: new
Abstract: Distributed training increases the number of batches processed per iteration either by scaling-out (adding more nodes) or scaling-up (increasing the batch-size). However, the largest configuration does not necessarily yield the best performance. Horizontal scaling introduces additional communication overhead, while vertical scaling is constrained by computation cost and device memory limits. Thus, simply increasing the batch-size leads to diminishing returns: training time and cost decrease initially but eventually plateaus, creating a knee-point in the time/cost versus batch-size pareto curve. The optimal batch-size therefore depends on the underlying model, data and available compute resources. Large batches also suffer from worse model quality due to the well-known generalization gap. In this paper, we present Tula, an online service that automatically optimizes time, cost, and convergence quality for large-batch training of convolutional models. It combines parallel-systems modeling with statistical performance prediction to identify the optimal batch-size. Tula predicts training time and cost within 7.5-14% error across multiple models, and achieves up to 20x overall speedup and improves test accuracy by 9% on average over standard large-batch training on various vision tasks, thus successfully mitigating the generalization gap and accelerating training at the same time.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Continually self-improving AI
arXiv:2603.18073v1 Announce Type: new
Abstract: Modern language model-based AI systems are remarkably powerful, yet their capabilities remain fundamentally capped by their human creators in three key ways. First, although a model's weights can be updated via fine-tuning, acquiring new knowledge from small, specialized corpora after pretraining remains highly data-inefficient. Second, the training of these systems relies heavily on finite, human-generated data from across history. Third, the pipelines used to train AI models are confined by the algorithms that human researchers can discover and explore. This thesis takes a small step toward overcoming these inherent limitations, presenting three chapters aimed at breaking these dependencies to create continually self-improving AI. First, to overcome this data-efficiency barrier in knowledge acquisition, we propose a synthetic data approach that diversifies and amplifies small corpora into rich knowledge representations, enabling a model to effectively update its parameters from limited source material. Second, to reduce reliance on human data, we show that given a fixed amount of such data, the model can self-generate synthetic data to bootstrap its fundamental pretraining capabilities without distillation from any off-the-shelf, instruction-tuned LM. Finally, to transcend human-engineered training paradigms, we demonstrate that by scaling search during test time over the space of algorithms, AI can search over a larger space of learning algorithm configurations than human researchers can explore manually.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
Access Controlled Website Interaction for Agentic AI with Delegated Critical Tasks
arXiv:2603.18197v1 Announce Type: new
Abstract: Recent studies reveal gaps in delegating critical tasks to agentic AI that accesses websites on the user's behalf, primarily due to limited access control mechanisms on websites designed for agentic AI. In response, we propose a design of website-based interaction for AI agents with fine-grained access control for delegated critical tasks. Our approach encompasses a website design and implementation, as well as modifications to the access grant protocols in an open-source authorization service to tailor it to agentic AI, with delegated critical tasks on the website. The evaluation of our approach demonstrates the capabilities of our access-controlled website used by AI agents.
Fonte: arXiv cs.AI
Vision • Score 85
R&D: Balancing Reliability and Diversity in Synthetic Data Augmentation for Semantic Segmentation
arXiv:2603.18427v1 Announce Type: new
Abstract: Collecting and annotating datasets for pixel-level semantic segmentation tasks are highly labor-intensive. Data augmentation provides a viable solution by enhancing model generalization without additional real-world data collection. Traditional augmentation techniques, such as translation, scaling, and color transformations, create geometric variations but fail to generate new structures. While generative models have been employed to extend semantic information of datasets, they often struggle to maintain consistency between the original and generated images, particularly for pixel-level tasks. In this work, we propose a novel synthetic data augmentation pipeline that integrates controllable diffusion models. Our approach balances diversity and reliability data, effectively bridging the gap between synthetic and real data. We utilize class-aware prompting and visual prior blending to improve image quality further, ensuring precise alignment with segmentation labels. By evaluating benchmark datasets such as PASCAL VOC and BDD100K, we demonstrate that our method significantly enhances semantic segmentation performance, especially in data-scarce scenarios, while improving model robustness in real-world applications. Our code is available at \href{https://github.com/chequanghuy/Enhanced-Generative-Data-Augmentation-for-Semantic-Segmentation-via-Stronger-Guidance}{https://github.com/chequanghuy/Enhanced-Generative-Data-Augmentation-for-Semantic-Segmentation-via-Stronger-Guidance}.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
An Agentic System for Schema Aware NL2SQL Generation
arXiv:2603.18018v1 Announce Type: new
Abstract: The natural language to SQL (NL2SQL) task plays a pivotal role in democratizing data access by enabling non-expert users to interact with relational databases through intuitive language. While recent frameworks have enhanced translation accuracy via task specialization, their reliance on Large Language Models (LLMs) raises significant concerns regarding computational overhead, data privacy, and real-world deployability in resource-constrained environments. To address these challenges, we propose a schema based agentic system that strategically employs Small Language Models (SLMs) as primary agents, complemented by a selective LLM fallback mechanism. The LLM is invoked only upon detection of errors in SLM-generated output, the proposed system significantly minimizes computational expenditure. Experimental results on the BIRD benchmark demonstrate that our system achieves an execution accuracy of 47.78% and a validation efficiency score of 51.05%, achieving over 90% cost reduction compared to LLM-centric baselines as approximately 67% of queries are resolved using local SLMs. The system achieves an average cost per query of 0.0085 compared to 0.094 for LLM-only systems, achieving near-zero operational costs for locally executed queries. [Github repository: https://github.com/mindslab25/CESMA.]
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
Foundations and Architectures of Artificial Intelligence for Motor Insurance
arXiv:2603.18508v1 Announce Type: new
Abstract: This handbook presents a systematic treatment of the foundations and architectures of artificial intelligence for motor insurance, grounded in large-scale real-world deployment. It formalizes a vertically integrated AI paradigm that unifies perception, multimodal reasoning, and production infrastructure into a cohesive intelligence stack for automotive risk assessment and claims processing. At its core, the handbook develops domain-adapted transformer architectures for structured visual understanding, relational vehicle representation learning, and multimodal document intelligence, enabling end-to-end automation of vehicle damage analysis, claims evaluation, and underwriting workflows. These components are composed into a scalable pipeline operating under practical constraints observed in nationwide motor insurance systems in Thailand. Beyond model design, the handbook emphasizes the co-evolution of learning algorithms and MLOps practices, establishing a principled framework for translating modern artificial intelligence into reliable, production-grade systems in high-stakes industrial environments.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Data-efficient pre-training by scaling synthetic megadocs
arXiv:2603.18534v1 Announce Type: new
Abstract: Synthetic data augmentation has emerged as a promising solution when pre-training is constrained by data rather than compute. We study how to design synthetic data algorithms that achieve better loss scaling: not only lowering loss at finite compute but especially as compute approaches infinity. We first show that pre-training on web data mixed with synthetically generated rephrases improves i.i.d. validation loss on the web data, despite the synthetic data coming from an entirely different distribution. With optimal mixing and epoching, loss and benchmark accuracy improve without overfitting as the number of synthetic generations grows, plateauing near $1.48\times$ data efficiency at 32 rephrases per document. We find even better loss scaling under a new perspective: synthetic generations from the same document can form a single substantially longer megadocument instead of many short documents. We show two ways to construct megadocs: stitching synthetic rephrases from the same web document or stretching a document by inserting rationales. Both methods improve i.i.d. loss, downstream benchmarks, and especially long-context loss relative to simple rephrasing, increasing data efficiency from $1.48\times$ to $1.80\times$ at $32$ generations per document. Importantly, the improvement of megadocs over simple rephrasing widens as more synthetic data is generated. Our results show how to design synthetic data algorithms that benefit more from increasing compute when data-constrained.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Fast and Interpretable Autoregressive Estimation with Neural Network Backpropagation
arXiv:2603.19041v1 Announce Type: new
Abstract: Autoregressive (AR) models remain widely used in time series analysis due to their interpretability, but convencional parameter estimation methods can be computationally expensive and prone to convergence issues. This paper proposes a Neural Network (NN) formulation of AR estimation by embedding the autoregressive structure directly into a feedforward NN, enabling coefficient estimation through backpropagation while preserving interpretability. Simulation experiments on 125,000 synthetic AR(p) time series with short-term dependence (1 <= p <= 5) show that the proposed NN-based method consistently recovers model coefficients for all series, while Conditional Maximum Likelihood (CML) fails to converge in approximately 55% of cases. When both methods converge, estimation accuracy is comparable with negligible differences in relative error, R2 and, perplexity/likelihood. However, when CML fails, the NN-based approach still provides reliable estimates. In all cases, the NN estimator achieves substantial computational gains, reaching a median speedup of 12.6x and up to 34.2x for higher model orders. Overall, results demonstrate that gradient-descent NN optimization can provide a fast and efficient alternative for interpretable AR parameter estimation.
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
A Family of Adaptive Activation Functions for Mitigating Failure Modes in Physics-Informed Neural Networks
arXiv:2603.18328v1 Announce Type: new
Abstract: Physics-Informed Neural Networks(PINNs) are a powerful and flexible learning framework that has gained significant attention in recent years. It has demonstrated strong performance across a wide range of scientific and engineering problems. In parallel, wavelets have been extensively used as efficient computational tools due to their strong approximation capabilities. Motivated by the common failure modes observed in standard PINNs, this work introduces a novel family of adaptive wavelet-based activation functions. The proposed activation functions significantly improve training stability and expressive power by combining trainable wavelet functions with either trainable or fixed hyperbolic tangent and softplus functions. Five distinct activation functions are developed within the PINN framework and systematically evaluated across four representative classes of partial differential equations (PDEs). Comprehensive comparisons using bar plots demonstrate improved robustness and accuracy compared to traditional activation functions. Furthermore, the proposed approach is validated through direct comparisons with baseline PINNs, transformer-based architectures such as PINNsFormer, and other deep learning models, highlighting its effectiveness and generality.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
MemArchitect: A Policy Driven Memory Governance Layer
arXiv:2603.18330v1 Announce Type: new
Abstract: Persistent Large Language Model (LLM) agents expose a critical governance gap in memory management. Standard Retrieval-Augmented Generation (RAG) frameworks treat memory as passive storage, lacking mechanisms to resolve contradictions, enforce privacy, or prevent outdated information ("zombie memories") from contaminating the context window.
We introduce MemArchitect, a governance layer that decouples memory lifecycle management from model weights. MemArchitect enforces explicit, rule-based policies, including memory decay, conflict resolution, and privacy controls.
We demonstrate that governed memory consistently outperforms unmanaged memory in agentic settings, highlighting the necessity of structured memory governance for reliable and safe autonomous systems.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Fast and Generalizable NeRF Architecture Selection for Satellite Scene Reconstruction
arXiv:2603.18306v1 Announce Type: new
Abstract: Neural Radiance Fields (NeRF) have emerged as a powerful approach for photorealistic 3D reconstruction from multi-view images. However, deploying NeRF for satellite imagery remains challenging. Each scene requires individual training, and optimizing architectures via Neural Architecture Search (NAS) demands hours to days of GPU time. While existing approaches focus on architectural improvements, our SHAP analysis reveals that multi-view consistency, rather than model architecture, determines reconstruction quality. Based on this insight, we develop PreSCAN, a predictive framework that estimates NeRF quality prior to training using lightweight geometric and photometric descriptors. PreSCAN selects suitable architectures in < 30 seconds with < 1 dB prediction error, achieving 1000$\times$ speedup over NAS. We further demonstrate PreSCAN's deployment utility on edge platforms (Jetson Orin), where combining its predictions with offline cost profiling reduces inference power by 26% and latency by 43% with minimal quality loss. Experiments on DFC2019 datasets confirm that PreSCAN generalizes across diverse satellite scenes without retraining.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Q-Drift: Quantization-Aware Drift Correction for Diffusion Model Sampling
arXiv:2603.18095v1 Announce Type: new
Abstract: Post-training quantization (PTQ) is a practical path to deploy large diffusion models, but quantization noise can accumulate over the denoising trajectory and degrade generation quality. We propose Q-Drift, a principled sampler-side correction that treats quantization error as an implicit stochastic perturbation on each denoising step and derives a marginal-distribution-preserving drift adjustment. Q-Drift estimates a timestep-wise variance statistic from calibration, in practice requiring as few as 5 paired full-precision/quantized calibration runs. The resulting sampler correction is plug-and-play with common samplers, diffusion models, and PTQ methods, while incurring negligible overhead at inference. Across six diverse text-to-image models (spanning DiT and U-Net), three samplers (Euler, flow-matching, DPM-Solver++), and two PTQ methods (SVDQuant, MixDQ), Q-Drift improves FID over the corresponding quantized baseline in most settings, with up to 4.59 FID reduction on PixArt-Sigma (SVDQuant W3A4), while preserving CLIP scores.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
LRConv-NeRV: Low Rank Convolution for Efficient Neural Video Compression
arXiv:2603.18261v1 Announce Type: new
Abstract: Neural Representations for Videos (NeRV) encode entire video sequences within neural network parameters, offering an alternative paradigm to conventional video codecs. However, the convolutional decoder of NeRV remains computationally expensive and memory intensive, limiting its deployment in resource-constrained environments. This paper proposes LRConv-NeRV, an efficient NeRV variant that replaces selected dense 3x3 convolutional layers with structured low-rank separable convolutions, trained end-to-end within the decoder architecture. By progressively applying low-rank factorization from the largest to earlier decoder stages, LRConv-NeRV enables controllable trade-offs between reconstruction quality and efficiency. Extensive experiments demonstrate that applying LRConv only to the final decoder stage reduces decoder complexity by 68%, from 201.9 to 64.9 GFLOPs, and model size by 9.3%, while incurring negligible quality loss and achieving approximately 9.2% bitrate reduction. Under INT8 post-training quantization, LRConv-NeRV preserves reconstruction quality close to the dense NeRV baseline, whereas more aggressive factorization of early decoder stages leads to disproportionate quality degradation. Compared to existing work under layer-aligned settings, LRConv-NeRV achieves a more favorable efficiency versus quality trade-off, offering substantial GFLOPs and parameter reductions while maintaining higher PSNR/MS-SSIM and improved temporal stability. Temporal flicker analysis using LPIPS further shows that the proposed solution preserves temporal coherence close to the NeRV baseline, results establish LRConv-NeRV as a potential architectural alternative for efficient neural video decoding under low-precision and resource-constrained settings.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Real-Time Trustworthiness Scoring for LLM Structured Outputs and Data Extraction
arXiv:2603.18014v1 Announce Type: new
Abstract: Structured Outputs from current LLMs exhibit sporadic errors, hindering enterprise AI efforts from realizing their immense potential. We present CONSTRUCT, a method to score the trustworthiness of LLM Structured Outputs in real-time, such that lower-scoring outputs are more likely to contain errors. This reveals the best places to focus limited human review bandwidth. CONSTRUCT additionally scores the trustworthiness of each field within a LLM Structured Output, helping reviewers quickly identify which parts of the output are wrong. Our method is suitable for any LLM (including black-box LLM APIs without logprobs such as reasoning models and Anthropic models), does not require labeled training data nor custom model deployment, and works for complex Structured Outputs with many fields of diverse types (including nested JSON schemas).
We additionally present one of the first public LLM Structured Output benchmarks with reliable ground-truth values that are not full of mistakes. Over this four-dataset benchmark, CONSTRUCT detects errors from various LLMs (including Gemini 3 and GPT-5) with significantly higher precision/recall than other scoring methods.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
GRAFITE: Generative Regression Analysis Framework for Issue Tracking and Evaluation
arXiv:2603.18173v1 Announce Type: new
Abstract: Large language models (LLMs) are largely motivated by their performance on popular topics and benchmarks at the time of their release. However, over time, contamination occurs due to significant exposure of benchmark data during training. This poses a risk of model performance inflation if testing is not carefully executed. To address this challenge, we present GRAFITE, a continuous LLM evaluation platform through a comprehensive system for maintaining and evaluating model issues. Our approach enables building a repository of model problems based on user feedback over time and offers a pipeline for assessing LLMs against these issues through quality assurance (QA) tests using LLM-as-a-judge. The platform enables side-by-side comparison of multiple models, facilitating regression detection across different releases. The platform is available at https://github.com/IBM/grafite. The demo video is available at www.youtube.com/watch?v=XFZyoleN56k.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
EntropyCache: Decoded Token Entropy Guided KV Caching for Diffusion Language Models
arXiv:2603.18489v1 Announce Type: new
Abstract: Diffusion-based large language models (dLLMs) rely on bidirectional attention, which prevents lossless KV caching and requires a full forward pass at every denoising step. Existing approximate KV caching methods reduce this cost by selectively updating cached states, but their decision overhead scales with context length or model depth. We propose EntropyCache, a training-free KV caching method that uses the maximum entropy of newly decoded token distributions as a constant-cost signal for deciding when to recompute. Our design is grounded in two empirical observations: (1) decoded token entropy correlates with KV cache drift, providing a cheap proxy for cache staleness, and (2) feature volatility of decoded tokens persists for multiple steps after unmasking, motivating recomputation of the $k$ most recently decoded tokens. The skip-or-recompute decision requires only $O(V)$ computation per step, independent of context length and model scale. Experiments on LLaDA-8B-Instruct and Dream-7B-Instruct show that EntropyCache achieves $15.2\times$-$26.4\times$ speedup on standard benchmarks and $22.4\times$-$24.1\times$ on chain-of-thought benchmarks, with competitive accuracy and decision overhead accounting for only $0.5\%$ of inference time. Code is available at https://github.com/mscheong01/EntropyCache.
Fonte: arXiv cs.CL
Privacy/Security/Fairness • Score 85
Entity-Specific Cyber Risk Assessment using InsurTech Empowered Risk Factors
arXiv:2507.08193v3 Announce Type: replace-cross
Abstract: The lack of high-quality public cyber incident data limits empirical research and predictive modeling for cyber risk assessment. This challenge persists due to the reluctance of companies to disclose incidents that could damage their reputation or investor confidence. Therefore, from an actuarial perspective, potential resolutions conclude two aspects: the enhancement of existing cyber incident datasets and the implementation of advanced modeling techniques to optimize the use of the available data. A review of existing data-driven methods highlights a significant lack of entity-specific organizational features in publicly available datasets. To address this gap, we propose a novel InsurTech framework that enriches cyber incident data with entity-specific attributes. We develop various machine learning (ML) models: a multilabel classification model to predict the occurrence of cyber incident types (e.g., Privacy Violation, Data Breach, Fraud and Extortion, IT Error, and Others) and a multioutput regression model to estimate their annual frequencies. While classifier and regressor chains are implemented to explore dependencies among cyber incident types as well, no significant correlations are observed in our datasets. Besides, we apply multiple interpretable ML techniques to identify and cross-validate potential risk factors developed by InsurTech across ML models. We find that InsurTech empowered features enhance prediction occurrence and frequency estimation robustness compared to only using conventional risk factors. The framework generates transparent, entity-specific cyber risk profiles, supporting customized underwriting and proactive cyber risk mitigation. It provides insurers and organizations with data-driven insights to support decision-making and compliance planning.
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
On the Surprising Effectiveness of a Single Global Merging in Decentralized Learning
arXiv:2507.06542v3 Announce Type: replace-cross
Abstract: Decentralized learning provides a scalable alternative to parameter-server-based training, yet its performance is often hindered by limited peer-to-peer communication. In this paper, we study how communication should be scheduled over time, including determining when and how frequently devices synchronize. Counterintuitive empirical results show that concentrating communication budgets in the later stages of decentralized training remarkably improves global test performance. Surprisingly, we uncover that fully connected communication at the final step, implemented by a single global merging, can significantly improve the performance of decentralized learning under high data heterogeneity. Our theoretical contributions, which explain these phenomena, are the first to establish that the globally merged model of decentralized SGD can match the convergence rate of parallel SGD. Technically, we reinterpret part of the discrepancy among local models, which were previously considered as detrimental noise, as constructive components essential for matching this rate. This work provides evidence that decentralized learning is able to generalize under high data heterogeneity and limited communication, while offering broad new avenues for model merging research.
Fonte: arXiv stat.ML
Vision • Score 90
CytoSyn: a Foundation Diffusion Model for Histopathology -- Tech Report
arXiv:2603.18089v1 Announce Type: new
Abstract: Computational pathology has made significant progress in recent years, fueling advances in both fundamental disease understanding and clinically ready tools. This evolution is driven by the availability of large amounts of digitized slides and specialized deep learning methods and models. Multiple self-supervised foundation feature extractors have been developed, enabling downstream predictive applications from cell segmentation to tumor sub-typing and survival analysis. In contrast, generative foundation models designed specifically for histopathology remain scarce. Such models could address tasks that are beyond the capabilities of feature extractors, such as virtual staining. In this paper, we introduce CytoSyn, a state-of-the-art foundation latent diffusion model that enables the guided generation of highly realistic and diverse histopathology H&E-stained images, as shown in an extensive benchmark. We explored methodological improvements, training set scaling, sampling strategies and slide-level overfitting, culminating in the improved CytoSyn-v2, and compared our work to PixCell, a state-of-the-art model, in an in-depth manner. This comparison highlighted the strong sensitivity of both diffusion models and performance metrics to preprocessing-specific details such as JPEG compression. Our model has been trained on a dataset obtained from more than 10,000 TCGA diagnostic whole-slide images of 32 different cancer types. Despite being trained only on oncology slides, it maintains state-of-the-art performance generating inflammatory bowel disease images. To support the research community, we publicly release CytoSyn's weights, its training and validation datasets, and a sample of synthetic images in this repository: https://huggingface.co/Owkin-Bioptimus/CytoSyn.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning
arXiv:2603.18423v1 Announce Type: new
Abstract: How can we accurately quantize a pre-trained model without any data? Quantization algorithms are widely used for deploying neural networks on resource-constrained edge devices. Zero-shot Quantization (ZSQ) addresses the crucial and practical scenario where training data are inaccessible for privacy or security reasons. However, three significant challenges hinder the performance of existing ZSQ methods: 1) noise in the synthetic dataset, 2) predictions based on off-target patterns, and the 3) misguidance by erroneous hard labels. In this paper, we propose SynQ (Synthesis-aware Fine-tuning for Zero-shot Quantization), a carefully designed ZSQ framework to overcome the limitations of existing methods. SynQ minimizes the noise from the generated samples by exploiting a low-pass filter. Then, SynQ trains the quantized model to improve accuracy by aligning its class activation map with the pre-trained model. Furthermore, SynQ mitigates misguidance from the pre-trained model's error by leveraging only soft labels for difficult samples. Extensive experiments show that SynQ provides the state-of-the-art accuracy, over existing ZSQ methods.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
Efficient Video Diffusion with Sparse Information Transmission for Video Compression
arXiv:2603.18501v1 Announce Type: new
Abstract: Video compression aims to maximize reconstruction quality with minimal bitrates. Beyond standard distortion metrics, perceptual quality and temporal consistency are also critical. However, at ultra-low bitrates, traditional end-to-end compression models tend to produce blurry images of poor perceptual quality. Besides, existing generative compression methods often treat video frames independently and show limitations in time coherence and efficiency. To address these challenges, we propose the Efficient Video Diffusion with Sparse Information Transmission (Diff-SIT), which comprises the Sparse Temporal Encoding Module (STEM) and the One-Step Video Diffusion with Frame Type Embedder (ODFTE). The STEM sparsely encodes the original frame sequence into an information-rich intermediate sequence, achieving significant bitrate savings. Subsequently, the ODFTE processes this intermediate sequence as a whole, which exploits the temporal correlation. During this process, our proposed Frame Type Embedder (FTE) guides the diffusion model to perform adaptive reconstruction according to different frame types to optimize the overall quality. Extensive experiments on multiple datasets demonstrate that Diff-SIT establishes a new state-of-the-art in perceptual quality and temporal consistency, particularly in the challenging ultra-low-bitrate regime. Code is released at https://github.com/MingdeZhou/Diff-SIT.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Unrolled Reconstruction with Integrated Super-Resolution for Accelerated 3D LGE MRI
arXiv:2603.18309v1 Announce Type: new
Abstract: Accelerated 3D late gadolinium enhancement (LGE) MRI requires robust reconstruction methods to recover thin atrial structures from undersampled k-space data. While unrolled model-based networks effectively integrate physics-driven data consistency with learned priors, they operate at the acquired resolution and may fail to fully recover high-frequency detail. We propose a hybrid unrolled reconstruction framework in which an Enhanced Deep Super-Resolution (EDSR) network replaces the proximal operator within each iteration of the optimization loop, enabling joint super-resolution enhancement and data consistency enforcement. The model is trained end-to-end on retrospectively undersampled preclinical 3D LGE datasets and compared against compressed sensing, Model-Based Deep Learning (MoDL), and self-guided Deep Image Prior (DIP) baselines. Across acceleration factors, the proposed method consistently improves PSNR and SSIM over standard unrolled reconstruction and better preserves fine cardiac structures, leading to improved LA (left atrium) segmentation performance. These results demonstrate that integrating super-resolution priors directly within model-based reconstruction provides measurable gains in accelerated 3D LGE MRI.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
MineDraft: A Framework for Batch Parallel Speculative Decoding
arXiv:2603.18016v1 Announce Type: new
Abstract: Speculative decoding (SD) accelerates large language model inference by using a smaller draft model to propose draft tokens that are subsequently verified by a larger target model. However, the performance of standard SD is often limited by the strictly sequential execution of these drafting and verification stages. To address this, this paper proposes MineDraft, a batch parallel speculative decoding (PSD) framework designed to effectively hide drafting latency by overlapping it with verification. Our theoretical analysis shows that PSD is substantially more efficient than standard SD. MineDraft realizes the PSD through a novel batch-parallel design that maintains two batches of requests, overlapping drafting for one batch with verification for the other. Our experimental results show significant improvements of MineDraft in both throughput (up to 75%) and end-to-end latency (up to 39%) over standard SD. Furthermore, we have implemented MineDraft as a plugin for vLLM, demonstrating its practicality for production-ready inference systems.
Fonte: arXiv cs.CL
MLOps/Systems • Score 85
A Computationally Efficient Learning of Artificial Intelligence System Reliability Considering Error Propagation
arXiv:2603.18201v1 Announce Type: new
Abstract: Artificial Intelligence (AI) systems are increasingly prominent in emerging smart cities, yet their reliability remains a critical concern. These systems typically operate through a sequence of interconnected functional stages, where upstream errors may propagate to downstream stages, ultimately affecting overall system reliability. Quantifying such error propagation is essential for accurate modeling of AI system reliability. However, this task is challenging due to: i) data availability: real-world AI system reliability data are often scarce and constrained by privacy concerns; ii) model validity: recurring error events across sequential stages are interdependent, violating the independence assumptions of statistical inference; and iii) computational complexity: AI systems process large volumes of high-speed data, resulting in frequent and complex recurrent error events that are difficult to track and analyze. To address these challenges, this paper leverages a physics-based autonomous vehicle simulation platform with a justifiable error injector to generate high-quality data for AI system reliability analysis. Building on this data, a new reliability modeling framework is developed to explicitly characterize error propagation across stages. Model parameters are estimated using a computationally efficient, theoretically guaranteed composite likelihood expectation - maximization algorithm. Its application to the reliability modeling for autonomous vehicle perception systems demonstrates its predictive accuracy and computational efficiency.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
Multifidelity Simulation-based Inference for Computationally Expensive Simulators
arXiv:2502.08416v4 Announce Type: replace
Abstract: Across many domains of science, stochastic models are an essential tool to understand the mechanisms underlying empirically observed data. Models can be of different levels of detail and accuracy, with models of high-fidelity (i.e., high accuracy) to the phenomena under study being often preferable. However, inferring parameters of high-fidelity models via simulation-based inference is challenging, especially when the simulator is computationally expensive. We introduce a multifidelity approach to neural posterior estimation that uses transfer learning to leverage inexpensive low-fidelity simulations to efficiently infer parameters of high-fidelity simulators. Our method applies the multifidelity scheme to both amortized and non-amortized neural posterior estimation. We further improve simulation efficiency by introducing a sequential variant that uses an acquisition function targeting the predictive uncertainty of the density estimator to adaptively select high-fidelity parameters. On established benchmark and neuroscience tasks, our approaches require up to two orders of magnitude fewer high-fidelity simulations than current methods, while showing comparable performance. Overall, our approaches open new opportunities to perform efficient Bayesian inference on computationally expensive simulators.
Fonte: arXiv stat.ML
NLP/LLMs • Score 75
On Additive Gaussian Processes for Wind Farm Power Prediction
arXiv:2603.18281v1 Announce Type: new
Abstract: Population-based Structural Health Monitoring (PBSHM) aims to share information between similar machines or structures. This paper takes a population-level perspective, exploring the use of additive Gaussian processes to reveal variations in turbine-specific and farm-level power models over a collected wind farm dataset. The predictions illustrate patterns in wind farm power generation, which follow intuition and should enable more informed control and decision-making.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Self-Tuning Sparse Attention: Multi-Fidelity Hyperparameter Optimization for Transformer Acceleration
arXiv:2603.18417v1 Announce Type: new
Abstract: Sparse attention mechanisms promise to break the quadratic bottleneck of long-context transformers, yet production adoption remains limited by a critical usability gap: optimal hyperparameters vary substantially across layers and models, and current methods (e.g., SpargeAttn) rely on manual grid search to identify them. We propose AFBS-BO (Adaptive Fidelity Binary Search with Bayesian Optimization), a fully automated framework that discovers optimal layer- and head-specific hyperparameters without human intervention. Our hybrid algorithm combines Bayesian Optimization for global exploration with binary search for local refinement, leveraging multi-fidelity evaluation across sequence lengths to reduce tuning cost. On Llama-2-7B, AFBS-BO accelerates hyperparameter discovery by 3.4x with 8.8x fewer evaluations than grid search, and identifies high-sparsity configurations that outperform existing sparse attention baselines while closely matching dense attention quality. By transforming sparse attention from a manually tuned heuristic into a self-optimizing primitive, AFBS-BO enables plug-and-play acceleration across diverse transformer architectures and domains.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Gradient-Informed Temporal Sampling Improves Rollout Accuracy in PDE Surrogate Training
arXiv:2603.18237v1 Announce Type: new
Abstract: Researchers train neural simulators on uniformly sampled numerical simulation data. But under the same budget, does systematically sampled data provide the most effective information? A fundamental yet unformalized problem is how to sample training data for neural simulators so as to maximize rollout accuracy. Existing data sampling methods either tend to collapse into locally high-information-density regions, or preserve diversity but remain insufficiently model-specific, often leading to performance that is no better than uniform sampling. To address this, we propose a data sampling method tailored to neural simulators, Gradient-Informed Temporal Sampling (GITS). GITS jointly optimizes pilot-model local gradients and set-level temporal coverage, thereby effectively balancing model specificity and dynamical information. Compared with multiple sampling baselines, the data selected by GITS achieves lower rollout error across multiple PDE systems, model backbones and sample ratios. Furthermore, ablation studies demonstrate the necessity and complementarity of the two optimization objectives in GITS. In addition, we analyze the successful sampling patterns of GITS as well as the typical PDE systems and model backbones on which GITS fails.
Fonte: arXiv cs.LG
RL • Score 85
CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbacks
arXiv:2603.18736v1 Announce Type: cross
Abstract: Despite the success of reinforcement learning from human feedback (RLHF) in aligning language models, current reward modeling heavily relies on experimental feedback data collected from human annotators under controlled and costly conditions. In this work, we introduce observational reward modeling -- learning reward models with observational user feedback (e.g., clicks, copies, and upvotes) -- as a scalable and cost-effective alternative. We identify two fundamental challenges in this setting: (1) observational feedback is noisy due to annotation errors, which deviates it from true user preference; (2) observational feedback is biased by user preference, where users preferentially provide feedback on responses they feel strongly about, which creats a distribution shift between training and inference data. To address these challenges, we propose CausalRM, a causal-theoretic reward modeling framework that aims to learn unbiased reward models from observational feedback. To tackle challenge (1), CausalRM introduces a noise-aware surrogate loss term that is provably equivalent to the primal loss under noise-free conditions by explicitly modeling the annotation error generation process. To tackle challenge (2), CausalRM uses propensity scores -- the probability of a user providing feedback for a given response -- to reweight training samples, yielding a loss function that eliminates user preference bias. Extensive experiments across diverse LLM backbones and benchmark datasets validate that CausalRM effectively learns accurate reward signals from noisy and biased observational feedback and delivers substantial performance improvements on downstream RLHF tasks -- including a 49.2% gain on WildGuardMix and a 32.7% improvement on HarmBench. Code is available on our project website.
Fonte: arXiv stat.ML
Privacy/Security/Fairness • Score 90
Beyond Passive Aggregation: Active Auditing and Topology-Aware Defense in Decentralized Federated Learning
arXiv:2603.18538v1 Announce Type: new
Abstract: Decentralized Federated Learning (DFL) remains highly vulnerable to adaptive backdoor attacks designed to bypass traditional passive defense metrics. To address this limitation, we shift the defensive paradigm toward a novel active, interventional auditing framework. First, we establish a dynamical model to characterize the spatiotemporal diffusion of adversarial updates across complex graph topologies. Second, we introduce a suite of proactive auditing metrics, stochastic entropy anomaly, randomized smoothing Kullback-Leibler divergence, and activation kurtosis. These metrics utilize private probes to stress-test local models, effectively exposing latent backdoors that remain invisible to conventional static detection. Furthermore, we implement a topology-aware defense placement strategy to maximize global aggregation resilience. We provide theoretical property for the system's convergence under co-evolving attack and defense dynamics. Numeric empirical evaluations across diverse architectures demonstrate that our active framework is highly competitive with state-of-the-art defenses in mitigating stealthy, adaptive backdoors while preserving primary task utility.
Fonte: arXiv cs.LG
RL • Score 85
R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation
arXiv:2603.18202v1 Announce Type: new
Abstract: A central challenge in image-based Model-Based Reinforcement Learning (MBRL) is to learn representations that distill essential information from irrelevant visual details. While promising, reconstruction-based methods often waste capacity on large task-irrelevant regions. Decoder-free methods instead learn robust representations by leveraging Data Augmentation (DA), but reliance on such external regularizers limits versatility. We propose R2-Dreamer, a decoder-free MBRL framework with a self-supervised objective that serves as an internal regularizer, preventing representation collapse without resorting to DA. The core of our method is a redundancy-reduction objective inspired by Barlow Twins, which can be easily integrated into existing frameworks. On DeepMind Control Suite and Meta-World, R2-Dreamer is competitive with strong baselines such as DreamerV3 and TD-MPC2 while training 1.59x faster than DreamerV3, and yields substantial gains on DMC-Subtle with tiny task-relevant objects. These results suggest that an effective internal regularizer can enable versatile, high-performance decoder-free MBRL. Code is available at https://github.com/NM512/r2dreamer.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Don't Vibe Code, Do Skele-Code: Interactive No-Code Notebooks for Subject Matter Experts to Build Lower-Cost Agentic Workflows
arXiv:2603.18122v1 Announce Type: new
Abstract: Skele-Code is a natural-language and graph-based interface for building workflows with AI agents, designed especially for less or non-technical users. It supports incremental, interactive notebook-style development, and each step is converted to code with a required set of functions and behavior to enable incremental building of workflows. Agents are invoked only for code generation and error recovery, not orchestration or task execution. This agent-supported, but code-first approach to workflows, along with the context-engineering used in Skele-Code, can help reduce token costs compared to the multi-agent system approach to executing workflows. Skele-Code produces modular, easily extensible, and shareable workflows. The generated workflows can also be used as skills by agents, or as steps in other workflows.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution
arXiv:2603.18718v1 Announce Type: new
Abstract: Memory-augmented LLM agents maintain external memory banks to support long-horizon interaction, yet most existing systems treat construction, retrieval, and utilization as isolated subroutines. This creates two coupled challenges: strategic blindness on the forward path of the memory cycle, where construction and retrieval are driven by local heuristics rather than explicit strategic reasoning, and sparse, delayed supervision on the backward path, where downstream failures rarely translate into direct repairs of the memory bank. To address these challenges, we propose MemMA, a plug-and-play multi-agent framework that coordinates the memory cycle along both the forward and backward paths. On the forward path, a Meta-Thinker produces structured guidance that steers a Memory Manager during construction and directs a Query Reasoner during iterative retrieval. On the backward path, MemMA introduces in-situ self-evolving memory construction, which synthesizes probe QA pairs, verifies the current memory, and converts failures into repair actions before the memory is finalized. Extensive experiments on LoCoMo show that MemMA consistently outperforms existing baselines across multiple LLM backbones and improves three different storage backends in a plug-and-play manner. Our code is publicly available at https://github.com/ventr1c/memma.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
Adaptive Domain Models: Bayesian Evolution, Warm Rotation, and Principled Training for Geometric and Neuromorphic AI
arXiv:2603.18104v1 Announce Type: new
Abstract: Prevailing AI training infrastructure assumes reverse-mode automatic differentiation over IEEE-754 arithmetic. The memory overhead of training relative to inference, optimizer complexity, and structural degradation of geometric properties through training are consequences of this arithmetic substrate. This paper develops an alternative training architecture grounded in three prior results: the Dimensional Type System and Deterministic Memory Management framework [6], which establishes stack-eligible gradient allocation and exact quire accumulation as design-time verifiable properties; the Program Hypergraph [8], which establishes grade preservation through geometric algebra computations as a type-level invariant; and the b-posit 2026 standard [10], which makes posit arithmetic tractable across hardware targets conventionally considered inference-only. Their composition enables depth-independent training memory bounded to approximately twice the inference footprint, grade-preserving weight updates, and exact gradient accumulation, applicable uniformly to loss-function-optimized and spike-timing-dependent neuromorphic models. We introduce Bayesian distillation, a mechanism by which the latent prior structure of a general-purpose model is extracted through the ADM training regime, resolving the data-scarcity bootstrapping problem for domain-specific training. For deployment, we introduce warm rotation, an operational pattern in which an updated model transitions into an active inference pathway without service interruption, with structural correctness formalized through PHG certificates and signed version records. The result is a class of domain-specific AI systems that are smaller and more precise than general-purpose models, continuously adaptive, verifiably correct with respect to the physical structure of their domains, and initializable from existing models.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
EDM-ARS: A Domain-Specific Multi-Agent System for Automated Educational Data Mining Research
arXiv:2603.18273v1 Announce Type: new
Abstract: In this technical report, we present the Educational Data Mining Automated Research System (EDM-ARS), a domain-specific multi-agent pipeline that automates end-to-end educational data mining (EDM) research. We conceptualize EDM-ARS as a general framework for domain-aware automated research pipelines, where educational expertise is embedded into each stage of the research lifecycle. As a first instantiation of this framework, we focus on predictive modeling tasks. Within this scope, EDM-ARS orchestrates five specialized LLM-powered agents (ProblemFormulator, DataEngineer, Analyst, Critic, and Writer) through a state-machine coordinator that supports revision loops, checkpoint-based recovery, and sandboxed code execution. Given a research prompt and a dataset, EDM-ARS produces a complete LaTeX manuscript with real Semantic Scholar citations, validated machine learning analyses, and automated methodological peer review. We also provide a detailed description of the system architecture, the three-tier data registry design that encodes educational domain expertise, the specification of each agent, the inter-agent communication protocol, and mechanisms for error-handling and self-correction. Finally, we discuss current limitations, including single-dataset scope and formulaic paper output, and outline a phased roadmap toward causal inference, transfer learning, psychometric, and multi-dataset generalization. EDM-ARS is released as an open-source project to support the educational research community.
Fonte: arXiv cs.AI
RL • Score 95
AcceRL: A Distributed Asynchronous Reinforcement Learning and World Model Framework for Vision-Language-Action Models
arXiv:2603.18464v1 Announce Type: new
Abstract: Reinforcement learning (RL) for large-scale Vision-Language-Action (VLA) models faces significant challenges in computational efficiency and data acquisition. We propose AcceRL, a fully asynchronous and decoupled RL framework designed to eliminate synchronization barriers by physically isolating training, inference, and rollouts. Crucially, AcceRL is the first to integrate a plug-and-play, trainable world model into a distributed asynchronous RL pipeline to generate virtual experiences. Experiments on the LIBERO benchmark demonstrate that AcceRL achieves state-of-the-art (SOTA) performance. Systematically, it exhibits super-linear scaling in throughput and highly efficient hardware utilization. Algorithmically, the world-model-augmented variant delivers unprecedented sample efficiency and robust training stability in complex control tasks.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
AIMER: Calibration-Free Task-Agnostic MoE Pruning
arXiv:2603.18492v1 Announce Type: new
Abstract: Mixture-of-Experts (MoE) language models increase parameter capacity without proportional per-token compute, but the deployment still requires storing all experts, making expert pruning important for reducing memory and serving overhead. Existing task-agnostic expert pruning methods are typically calibration-dependent: they estimate expert importance from routing or activation statistics on a calibration set, which makes pruning outcomes sensitive to the choice of calibration set and adds substantial preprocessing cost. We introduce AIMER (\textbf{A}bsolute mean over root mean square \textbf{IM}portance for \textbf{E}xpert \textbf{R}anking), a simple calibration-free criterion that yields clear within-layer score separation and distinct expert stratification. Across 7B to 30B MoE language models at 25\% and 50\% pruning ratios over 16 benchmarks, AIMER consistently delivers competitive or stronger overall performance against state-of-the-art calibration-based expert pruning baselines with only 0.22--1.27 seconds for scoring the experts.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
D-Mem: A Dual-Process Memory System for LLM Agents
arXiv:2603.18631v1 Announce Type: new
Abstract: Driven by the development of persistent, self-adapting autonomous agents, equipping these systems with high-fidelity memory access for long-horizon reasoning has emerged as a critical requirement. However, prevalent retrieval-based memory frameworks often follow an incremental processing paradigm that continuously extracts and updates conversational memories into vector databases, relying on semantic retrieval when queried. While this approach is fast, it inherently relies on lossy abstraction, frequently missing contextually critical information and struggling to resolve queries that rely on fine-grained contextual understanding. To address this, we introduce D-Mem, a dual-process memory system. It retains lightweight vector retrieval for routine queries while establishing an exhaustive Full Deliberation module as a high-fidelity fallback. To achieve cognitive economy without sacrificing accuracy, D-Mem employs a Multi-dimensional Quality Gating policy to dynamically bridge these two processes. Experiments on the LoCoMo and RealTalk benchmarks using GPT-4o-mini and Qwen3-235B-Instruct demonstrate the efficacy of our approach. Notably, our Multi-dimensional Quality Gating policy achieves an F1 score of 53.5 on LoCoMo with GPT-4o-mini. This outperforms our static retrieval baseline, Mem0$^\ast$ (51.2), and recovers 96.7\% of the Full Deliberation's performance (55.3), while incurring significantly lower computational costs.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
Towards Differentiating Between Failures and Domain Shifts in Industrial Data Streams
arXiv:2603.18032v1 Announce Type: new
Abstract: Anomaly and failure detection methods are crucial in identifying deviations from normal system operational conditions, which allows for actions to be taken in advance, usually preventing more serious damages. Long-lasting deviations indicate failures, while sudden, isolated changes in the data indicate anomalies. However, in many practical applications, changes in the data do not always represent abnormal system states. Such changes may be recognized incorrectly as failures, while being a normal evolution of the system, e.g. referring to characteristics of starting the processing of a new product, i.e. realizing a domain shift. Therefore, distinguishing between failures and such ''healthy'' changes in data distribution is critical to ensure the practical robustness of the system. In this paper, we propose a method that not only detects changes in the data distribution and anomalies but also allows us to distinguish between failures and normal domain shifts inherent to a given process. The proposed method consists of a modified Page-Hinkley changepoint detector for identification of the domain shift and possible failures and supervised domain-adaptation-based algorithms for fast, online anomaly detection. These two are coupled with an explainable artificial intelligence (XAI) component that aims at helping the human operator to finally differentiate between domain shifts and failures. The method is illustrated by an experiment on a data stream from the steel factory.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Prune-then-Quantize or Quantize-then-Prune? Understanding the Impact of Compression Order in Joint Model Compression
arXiv:2603.18426v1 Announce Type: new
Abstract: What happens when multiple compression methods are combined-does the order in which they are applied matter? Joint model compression has emerged as a powerful strategy to achieve higher efficiency by combining multiple methods such as pruning and quantization. A central but underexplored factor in joint model compression is the compression order, or the sequence of different methods within the compression pipeline. Most prior studies have either sidestepped the issue by assuming orthogonality between techniques, while a few have examined them only in highly constrained cases. Consequently, the broader role of compression order in shaping model performance remains poorly understood. In this paper, we address the overlooked problem of compression order and provide both theoretical and empirical analysis. We formulate the problem of optimizing the compression order and introduce the Progressive Intensity Hypothesis, which states that weaker perturbations should precede stronger ones. We provide theoretical guarantees showing that the relative benefit of one order increases with the underlying performance gap. Extensive experiments on both language and vision models validate the hypothesis, and further show its generality to broader setups such as multi-stage compression and mixed-precision quantization.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
A Concept is More Than a Word: Diversified Unlearning in Text-to-Image Diffusion Models
arXiv:2603.18767v1 Announce Type: new
Abstract: Concept unlearning has emerged as a promising direction for reducing the risks of harmful content generation in text-to-image diffusion models by selectively erasing undesirable concepts from a model's parameters. Existing approaches typically rely on keywords to identify the target concept to be unlearned. However, we show that this keyword-based formulation is inherently limited: a visual concept is multi-dimensional, can be expressed in diverse textual forms, and often overlap with related concepts in the latent space, making keyword-only unlearning, which imprecisely indicate the target concept is brittle and prone to over-forgetting. This occurs because a single keyword represents only a narrow point estimate of the concept, failing to cover its full semantic distribution and entangled variations in the latent space. To address this limitation, we propose Diversified Unlearning, a distributional framework that represents a concept through a set of contextually diverse prompts rather than a single keyword. This richer representation enables more precise and robust unlearning. Through extensive experiments across multiple benchmarks and state-of-the-art baselines, we demonstrate that integrating Diversified Unlearning as an add-on component into existing unlearning pipelines consistently achieves stronger erasure, better retention of unrelated concepts, and improved robustness against adversarial recovery attacks.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Probabilistic Federated Learning on Uncertain and Heterogeneous Data with Model Personalization
arXiv:2603.18083v1 Announce Type: new
Abstract: Conventional federated learning (FL) frameworks often suffer from training degradation due to data uncertainty and heterogeneity across local clients. Probabilistic approaches such as Bayesian neural networks (BNNs) can mitigate this issue by explicitly modeling uncertainty, but they introduce additional runtime, latency, and bandwidth overhead that has rarely been studied in federated settings. To address these challenges, we propose Meta-BayFL, a personalized probabilistic FL method that combines meta-learning with BNNs to improve training under uncertain and heterogeneous data. The framework is characterized by three main features: (1) BNN-based client models incorporate uncertainty across hidden layers to stabilize training on small and noisy datasets, (2) meta-learning with adaptive learning rates enables personalized updates that enhance local training under non-IID conditions, and (3) a unified probabilistic and personalized design improves the robustness of global model aggregation. We provide a theoretical convergence analysis and characterize the upper bound of the global model over communication rounds. In addition, we evaluate computational costs (runtime, latency, and communication) and discuss the feasibility of deployment on resource-constrained devices such as edge nodes and IoT systems. Extensive experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet show that Meta-BayFL consistently outperforms state-of-the-art methods, including both standard and personalized FL approaches (e.g., pFedMe, Ditto, FedFomo), with up to 7.42\% higher test accuracy.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
InfoMamba: An Attention-Free Hybrid Mamba-Transformer Model
arXiv:2603.18031v1 Announce Type: new
Abstract: Balancing fine-grained local modeling with long-range dependency capture under computational constraints remains a central challenge in sequence modeling. While Transformers provide strong token mixing, they suffer from quadratic complexity, whereas Mamba-style selective state-space models (SSMs) scale linearly but often struggle to capture high-rank and synchronous global interactions. We present a consistency boundary analysis that characterizes when diagonal short-memory SSMs can approximate causal attention and identifies structural gaps that remain. Motivated by this analysis, we propose InfoMamba, an attention-free hybrid architecture. InfoMamba replaces token-level self-attention with a concept bottleneck linear filtering layer that serves as a minimal-bandwidth global interface and integrates it with a selective recurrent stream through information-maximizing fusion (IMF). IMF dynamically injects global context into the SSM dynamics and encourages complementary information usage through a mutual-information-inspired objective. Extensive experiments on classification, dense prediction, and non-vision tasks show that InfoMamba consistently outperforms strong Transformer and SSM baselines, achieving competitive accuracy-efficiency trade-offs while maintaining near-linear scaling.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Adapting Methods for Domain-Specific Japanese Small LMs: Scale, Architecture, and Quantization
arXiv:2603.18037v1 Announce Type: new
Abstract: This paper presents a systematic methodology for building domain-specific Japanese small language models using QLoRA fine-tuning. We address three core questions: optimal training scale, base-model selection, and architecture-aware quantization. Stage 1 (Training scale): Scale-learning experiments (1k--5k samples) identify n=4,000 as optimal, where test-set NLL reaches minimum (1.127) before overfitting at 5k samples. Stage 2 (Compare finetuned SLMs): Comparing four Japanese LLMs shows that Llama-3 models with Japanese continual pre-training (Swallow-8B, ELYZA-JP-8B) outperform multilingual models (Qwen2.5-7B). Stage 3 (Quantization): Llama-3 architectures improve under Q4_K_M quantization, while GQA architectures degrade severely (Qwen2.5: -0.280 points). Production recommendation: Swallow-8B Q4_K_M achieves 2.830/3 score, 8.9 s/question, 4.9 GB size. The methodology generalizes to low-resource technical domains and provides actionable guidance for compact Japanese specialist LMs on consumer hardware.
Fonte: arXiv cs.LG
Multimodal • Score 92
Edge-Efficient Two-Stream Multimodal Architecture for Non-Intrusive Bathroom Fall Detection
arXiv:2603.17069v1 Announce Type: new
Abstract: Falls in wet bathroom environments are a major safety risk for seniors living alone. Recent work has shown that mmWave-only, vibration-only, and existing multimodal schemes, such as vibration-triggered radar activation, early feature concatenation, and decision-level score fusion, can support privacy-preserving, non-intrusive fall detection. However, these designs still treat motion and impact as loosely coupled streams, depending on coarse temporal alignment and amplitude thresholds, and do not explicitly encode the causal link between radar-observed collapse and floor impact or address timing drift, object drop confounders, and latency and energy constraints on low-power edge devices. To this end, we propose a two-stream architecture that encodes radar signals with a Motion--Mamba branch for long-range motion patterns and processes floor vibration with an Impact--Griffin branch that emphasizes impact transients and cross-axis coupling. Cross-conditioned fusion uses low-rank bilinear interaction and a Switch--MoE head to align motion and impact tokens and suppress object-drop confounders. The model keeps inference cost suitable for real-time execution on a Raspberry Pi 4B gateway. We construct a bathroom fall detection benchmark dataset with frame-level annotations, comprising more than 3~h of synchronized mmWave radar and triaxial vibration recordings across eight scenarios under running water, together with subject-independent training, validation, and test splits. On the test split, our model attains 96.1% accuracy, 94.8% precision, 88.0% recall, a 91.1% macro F1 score, and an AUC of 0.968. Compared with the strongest baseline, it improves accuracy by 2.0 percentage points and fall recall by 1.3 percentage points, while reducing latency from 35.9 ms to 15.8 ms and lowering energy per 2.56 s window from 14200 mJ to 10750 mJ on the Raspberry Pi 4B gateway.
Fonte: arXiv cs.CV
Vision • Score 85
Leveraging Large Vision Model for Multi-UAV Co-perception in Low-Altitude Wireless Networks
arXiv:2603.16927v1 Announce Type: new
Abstract: Multi-uncrewed aerial vehicle (UAV) cooperative perception has emerged as a promising paradigm for diverse low-altitude economy applications, where complementary multi-view observations are leveraged to enhance perception performance via wireless communications. However, the massive visual data generated by multiple UAVs poses significant challenges in terms of communication latency and resource efficiency. To address these challenges, this paper proposes a communication-efficient cooperative perception framework, termed Base-Station-Helped UAV (BHU), which reduces communication overhead while enhancing perception performance. Specifically, we employ a Top-K selection mechanism to identify the most informative pixels from UAV-captured RGB images, enabling sparsified visual transmission with reduced data volume and latency. The sparsified images are transmitted to a ground server via multi-user MIMO (MU-MIMO), where a Swin-large-based MaskDINO encoder extracts bird's-eye-view (BEV) features and performs cooperative feature fusion for ground vehicle perception. Furthermore, we develop a diffusion model-based deep reinforcement learning (DRL) algorithm to jointly select cooperative UAVs, sparsification ratios, and precoding matrices, achieving a balance between communication efficiency and perception utility. Simulation results on the Air-Co-Pred dataset demonstrate that, compared with traditional CNN-based BEV fusion baselines, the proposed BHU framework improves perception performance by over 5% while reducing communication overhead by 85%, providing an effective solution for multi-UAV cooperative perception under resource-constrained wireless environments.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild
arXiv:2603.17187v1 Announce Type: new
Abstract: Large language model (LLM) agents are increasingly used for complex tasks, yet deployed agents often remain static, failing to adapt as user needs evolve. This creates a tension between the need for continuous service and the necessity of updating capabilities to match shifting task distributions. On platforms like OpenClaw, which handle diverse workloads across 20+ channels, existing methods either store raw trajectories without distilling knowledge, maintain static skill libraries, or require disruptive downtime for retraining. We present MetaClaw, a continual meta-learning framework that jointly evolves a base LLM policy and a library of reusable behavioral skills. MetaClaw employs two complementary mechanisms. Skill-driven fast adaptation analyzes failure trajectories via an LLM evolver to synthesize new skills, enabling immediate improvement with zero downtime. Opportunistic policy optimization performs gradient-based updates via cloud LoRA fine-tuning and Reinforcement Learning with a Process Reward Model (RL-PRM). This is triggered during user-inactive windows by the Opportunistic Meta-Learning Scheduler (OMLS), which monitors system inactivity and calendar data. These mechanisms are mutually reinforcing: a refined policy generates better trajectories for skill synthesis, while richer skills provide higher-quality data for policy optimization. To prevent data contamination, a versioning mechanism separates support and query data. Built on a proxy-based architecture, MetaClaw scales to production-size LLMs without local GPUs. Experiments on MetaClaw-Bench and AutoResearchClaw show that skill-driven adaptation improves accuracy by up to 32% relative. The full pipeline advances Kimi-K2.5 accuracy from 21.4% to 40.6% and increases composite robustness by 18.3%. Code is available at https://github.com/aiming-lab/MetaClaw.
Fonte: arXiv cs.LG
RL • Score 85
Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models
arXiv:2603.17051v1 Announce Type: new
Abstract: Distilled autoregressive (AR) video models enable efficient streaming generation but frequently misalign with human visual preferences. Existing reinforcement learning (RL) frameworks are not naturally suited to these architectures, typically requiring either expensive re-distillation or solver-coupled reverse-process optimization that introduces considerable memory and computational overhead. We present Astrolabe, an efficient online RL framework tailored for distilled AR models. To overcome existing bottlenecks, we introduce a forward-process RL formulation based on negative-aware fine-tuning. By contrasting positive and negative samples directly at inference endpoints, this approach establishes an implicit policy improvement direction without requiring reverse-process unrolling. To scale this alignment to long videos, we propose a streaming training scheme that generates sequences progressively via a rolling KV-cache, applying RL updates exclusively to local clip windows while conditioning on prior context to ensure long-range coherence. Finally, to mitigate reward hacking, we integrate a multi-reward objective stabilized by uncertainty-aware selective regularization and dynamic reference updates. Extensive experiments demonstrate that our method consistently enhances generation quality across multiple distilled AR video models, serving as a robust and scalable alignment solution.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Auto-Unrolled Proximal Gradient Descent: An AutoML Approach to Interpretable Waveform Optimization
arXiv:2603.17478v1 Announce Type: new
Abstract: This study explores the combination of automated machine learning (AutoML) with model-based deep unfolding (DU) for optimizing wireless beamforming and waveforms. We convert the iterative proximal gradient descent (PGD) algorithm into a deep neural network, wherein the parameters of each layer are learned instead of being predetermined. Additionally, we enhance the architecture by incorporating a hybrid layer that performs a learnable linear gradient transformation prior to the proximal projection. By utilizing AutoGluon with a tree-structured parzen estimator (TPE) for hyperparameter optimization (HPO) across an expanded search space, which includes network depth, step-size initialization, optimizer, learning rate scheduler, layer type, and post-gradient activation, the proposed auto-unrolled PGD (Auto-PGD) achieves 98.8% of the spectral efficiency of a traditional 200-iteration PGD solver using only five unrolled layers, while requiring only 100 training samples. We also address a gradient normalization issue to ensure consistent performance during training and evaluation, and we illustrate per-layer sum-rate logging as a tool for transparency. These contributions highlight a notable reduction in the amount of training data and inference cost required, while maintaining high interpretability compared to conventional black-box architectures.
Fonte: arXiv cs.LG
Vision • Score 85
From Virtual Environments to Real-World Trials: Emerging Trends in Autonomous Driving
arXiv:2603.17714v1 Announce Type: new
Abstract: Autonomous driving technologies have achieved significant advances in recent years, yet their real-world deployment remains constrained by data scarcity, safety requirements, and the need for generalization across diverse environments. In response, synthetic data and virtual environments have emerged as powerful enablers, offering scalable, controllable, and richly annotated scenarios for training and evaluation. This survey presents a comprehensive review of recent developments at the intersection of autonomous driving, simulation technologies, and synthetic datasets. We organize the landscape across three core dimensions: (i) the use of synthetic data for perception and planning, (ii) digital twin-based simulation for system validation, and (iii) domain adaptation strategies bridging synthetic and real-world data. We also highlight the role of vision-language models and simulation realism in enhancing scene understanding and generalization. A detailed taxonomy of datasets, tools, and simulation platforms is provided, alongside an analysis of trends in benchmark design. Finally, we discuss critical challenges and open research directions, including Sim2Real transfer, scalable safety validation, cooperative autonomy, and simulation-driven policy learning, that must be addressed to accelerate the path toward safe, generalizable, and globally deployable autonomous driving systems.
Fonte: arXiv cs.AI
Vision • Score 85
Empirical Recipes for Efficient and Compact Vision-Language Models
arXiv:2603.16987v1 Announce Type: new
Abstract: Deploying vision-language models (VLMs) in resource-constrained settings demands low latency and high throughput, yet existing compact VLMs often fall short of the inference speedups their smaller parameter counts suggest. To explain this discrepancy, we conduct an empirical end-to-end efficiency analysis and systematically profile inference to identify the dominant bottlenecks. Based on these findings, we develop optimization recipes tailored to compact VLMs that substantially reduce latency while preserving accuracy. These techniques cut time to first token (TTFT) by 53% on InternVL3-2B and by 93% on SmolVLM-256M. Our recipes are broadly applicable across both VLM architectures and common serving frameworks, providing practical guidance for building efficient VLM systems. Beyond efficiency, we study how to extend compact VLMs with structured perception outputs and introduce the resulting model family, ArgusVLM. Across diverse benchmarks, ArgusVLM achieves strong performance while maintaining a compact and efficient design.
Fonte: arXiv cs.CV
RL • Score 90
GigaWorld-Policy: An Efficient Action-Centered World--Action Model
arXiv:2603.17240v1 Announce Type: new
Abstract: World-Action Models (WAM) initialized from pre-trained video generation backbones have demonstrated remarkable potential for robot policy learning. However, existing approaches face two critical bottlenecks that hinder performance and deployment. First, jointly reasoning over future visual dynamics and corresponding actions incurs substantial inference overhead. Second, joint modeling often entangles visual and motion representations, making motion prediction accuracy heavily dependent on the quality of future video forecasts. To address these issues, we introduce GigaWorld-Policy, an action-centered WAM that learns 2D pixel-action dynamics while enabling efficient action decoding, with optional video generation. Specifically, we formulate policy training into two coupled components: the model predicts future action sequences conditioned on the current observation, and simultaneously generates future videos conditioned on the predicted actions and the same observation. The policy is supervised by both action prediction and video generation, providing richer learning signals and encouraging physically plausible actions through visual-dynamics constraints. With a causal design that prevents future-video tokens from influencing action tokens, explicit future-video generation is optional at inference time, allowing faster action prediction during deployment. To support this paradigm, we curate a diverse, large-scale robot dataset to pre-train an action-centered video generation model, which is then adapted as the backbone for robot policy learning. Experimental results on real-world robotic platforms show that GigaWorld-Policy runs 9x faster than the leading WAM baseline, Motus, while improving task success rates by 7%. Moreover, compared with pi-0.5, GigaWorld-Policy improves performance by 95% on RoboTwin 2.0.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
Governed Memory: A Production Architecture for Multi-Agent Workflows
arXiv:2603.17787v1 Announce Type: new
Abstract: Enterprise AI deploys dozens of autonomous agent nodes across workflows, each acting on the same entities with no shared memory and no common governance. We identify five structural challenges arising from this memory governance gap: memory silos across agent workflows; governance fragmentation across teams and tools; unstructured memories unusable by downstream systems; redundant context delivery in autonomous multi-step executions; and silent quality degradation without feedback loops. We present Governed Memory, a shared memory and governance layer addressing this gap through four mechanisms: a dual memory model combining open-set atomic facts with schema-enforced typed properties; tiered governance routing with progressive context delivery; reflection-bounded retrieval with entity-scoped isolation; and a closed-loop schema lifecycle with AI-assisted authoring and automated per-property refinement. We validate each mechanism through controlled experiments (N=250, five content types): 99.6% fact recall with complementary dual-modality coverage; 92% governance routing precision; 50% token reduction from progressive delivery; zero cross-entity leakage across 500 adversarial queries; 100% adversarial governance compliance; and output quality saturation at approximately seven governed memories per entity. On the LoCoMo benchmark, the architecture achieves 74.8% overall accuracy, confirming that governance and schema enforcement impose no retrieval quality penalty. The system is in production at Personize.ai.
Fonte: arXiv cs.AI
Vision • Score 85
Joint Optimization of Storage and Loading for High-Performance 3D Point Cloud Data Processing
arXiv:2603.16945v1 Announce Type: new
Abstract: With the rapid development of computer vision and deep learning, significant advancements have been made in 3D vision, partic- ularly in autonomous driving, robotic perception, and augmented reality. 3D point cloud data, as a crucial representation of 3D information, has gained widespread attention. However, the vast scale and complexity of point cloud data present significant chal- lenges for loading and processing and traditional algorithms struggle to handle large-scale datasets.The diversity of storage formats for point cloud datasets (e.g., PLY, XYZ, BIN) adds complexity to data handling and results in inefficiencies in data preparation. Al- though binary formats like BIN and NPY have been used to speed up data access, they still do not fully address the time-consuming data loading and processing phase. To overcome these challenges, we propose the .PcRecord format, a unified data storage solution designed to reduce the storage occupation and accelerate the processing of point cloud data. We also introduce a high-performance data processing pipeline equipped with multiple modules. By leveraging a multi-stage parallel pipeline architecture, our system optimizes the use of computational resources, significantly improving processing speed and efficiency. This paper details the im- plementation of this system and demonstrates its effectiveness in addressing the challenges of handling large-scale point cloud datasets.On average, our system achieves performance improvements of 6.61x (ModelNet40), 2.69x (S3DIS), 2.23x (ShapeNet), 3.09x (Kitti), 8.07x (SUN RGB-D), and 5.67x (ScanNet) with GPU and 6.9x, 1.88x, 1.29x, 2.28x, 25.4x, and 19.3x with Ascend.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
Behavior-Centric Extraction of Scenarios from Highway Traffic Data and their Domain-Knowledge-Guided Clustering using CVQ-VAE
arXiv:2603.16964v1 Announce Type: new
Abstract: Approval of ADS depends on evaluating its behavior within representative real-world traffic scenarios. A common way to obtain such scenarios is to extract them from real-world data recordings. These can then be grouped and serve as basis on which the ADS is subsequently tested. This poses two central challenges: how scenarios are extracted and how they are grouped. Existing extraction methods rely on heterogeneous definitions, hindering scenario comparability. For the grouping of scenarios, rule-based or ML-based methods can be utilized. However, while modern ML-based approaches can handle the complexity of traffic scenarios, unlike rule-based approaches, they lack interpretability and may not align with domain-knowledge. This work contributes to a standardized scenario extraction based on the Scenario-as-Specification concept, as well as a domain-knowledge-guided scenario clustering process. Experiments on the highD dataset demonstrate that scenarios can be extracted reliably and that domain-knowledge can be effectively integrated into the clustering process. As a result, the proposed methodology supports a more standardized process for deriving scenario categories from highway data recordings and thus enables a more efficient validation process of automated vehicles.
Fonte: arXiv cs.CV
Vision • Score 85
PaAgent: Portrait-Aware Image Restoration Agent via Subjective-Objective Reinforcement Learning
arXiv:2603.17055v1 Announce Type: new
Abstract: Image Restoration (IR) agents, leveraging multimodal large language models to perceive degradation and invoke restoration tools, have shown promise in automating IR tasks. However, existing IR agents typically lack an insight summarization mechanism for past interactions, which results in an exhaustive search for the optimal IR tool. To address this limitation, we propose a portrait-aware IR agent, dubbed PaAgent, which incorporates a self-evolving portrait bank for IR tools and Retrieval-Augmented Generation (RAG) to select a suitable IR tool for input. Specifically, to construct and evolve the portrait bank, the PaAgent continuously enriches it by summarizing the characteristics of various IR tools with restored images, selected IR tools, and degraded images. In addition, the RAG is employed to select the optimal IR tool for the input image by retrieving relevant insights from the portrait bank. Furthermore, to enhance PaAgent's ability to perceive degradation in complex scenes, we propose a subjective-objective reinforcement learning strategy that considers both image quality scores and semantic insights in reward generation, which accurately provides the degradation information even under partial and non-uniform degradation. Extensive experiments across 8 IR benchmarks, covering six single-degradation and eight mixed-degradation scenarios, validate PaAgent's superiority in addressing complex IR tasks. Our project page is \href{https://wyjgr.github.io/PaAgent.html}{PaAgent}.
Fonte: arXiv cs.CV
Applications • Score 85
A Novel end-to-end Digital Health System Using Deep Learning-based ECG Analysis
arXiv:2603.16891v1 Announce Type: cross
Abstract: This study presents AI-HEART, a cloud-based information system for managing and analysing long-duration ambulatory electrocardiogram (ECG) recordings and supporting clinician decision-making. The platform operationalises an end-to-end pipeline that ingests multi-day three-lead ECGs, normalises inputs, performs signal preprocessing, and applies dedicated deep neural networks for wave delineation, noise/quality detection, and beat- and rhythm-level multi-class arrhythmia classification. To address class imbalance and real-world signal variability, model development combines large clinically annotated datasets with expert-in-the-loop curation and generative augmentation for under-represented rhythms. Empirical evaluation on three-lead ambulatory ECG data shows that delineation accuracy is sufficient for automated interval measurement, noise detection reliably flags poor-quality segments, and arrhythmia classification achieves high specificity with clinically useful macro-averaged performance across common and rarer rhythms. Beyond predictive accuracy, AI-HEART provides a scalable deployment approach for integrating AI into routine ECG services, enabling traceable outputs, audit-friendly storage of recordings and derived annotations, and clinician review/editing that captures feedback for controlled model improvement. The findings demonstrate the technical feasibility and operational value of a noise-aware AI-ECG platform as a digital health information system.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Sensi: Learn One Thing at a Time -- Curriculum-Based Test-Time Learning for LLM Game Agents
arXiv:2603.17683v1 Announce Type: new
Abstract: Large language model (LLM) agents deployed in unknown environments must learn task structure at test time, but current approaches require thousands of interactions to form useful hypotheses. We present Sensi, an LLM agent architecture for the ARC-AGI-3 game-playing challenge that introduces structured test-time learning through three mechanisms: (1) a two-player architecture separating perception from action, (2) a curriculum-based learning system managed by an external state machine, and (3) a database-as-control-plane that makes the agents context window programmatically steerable. We further introduce an LLM-as-judge component with dynamically generated evaluation rubrics to determine when the agent has learned enough about one topic to advance to the next. We report results across two iterations: Sensi v1 solves 2 game levels using the two-player architecture alone, while Sensi v2 adds curriculum learning and solves 0 levels - but completes its entire learning curriculum in approximately 32 action attempts, achieving 50-94x greater sample efficiency than comparable systems that require 1600-3000 attempts. We precisely diagnose the failure mode as a self-consistent hallucination cascade originating in the perception layer, demonstrating that the architectural bottleneck has shifted from learning efficiency to perceptual grounding - a more tractable problem.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Variational Kernel Design for Internal Noise: Gaussian Chaos Noise, Representation Compatibility, and Reliable Deep Learning
arXiv:2603.17365v1 Announce Type: new
Abstract: Internal noise in deep networks is usually inherited from heuristics such as dropout, hard masking, or additive perturbation. We ask two questions: what correlation geometry should internal noise have, and is the implemented perturbation compatible with the representations it acts on? We answer these questions through Variational Kernel Design (VKD), a framework in which a noise mechanism is specified by a law family, a correlation kernel, and an injection operator, and is derived from learning desiderata. In a solved spatial subfamily, a quadratic maximum-entropy principle over latent log-fields yields a Gaussian optimizer with precision given by the Dirichlet Laplacian, so the induced geometry is the Dirichlet Green kernel. Wick normalization then gives a canonical positive mean-one gate, Gaussian Chaos Noise (GCh). For the sample-wise gate used in practice, we prove exact Gaussian control of pairwise log-ratio deformation, margin-sensitive ranking stability, and an exact expected intrinsic roughness budget; hard binary masks instead induce singular or coherence-amplified distortions on positive coherent representations. On ImageNet and ImageNet-C, GCh consistently improves calibration and under shift also improves NLL at competitive accuracy.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Cascade-Aware Multi-Agent Routing: Spatio-Temporal Sidecars and Geometry-Switching
arXiv:2603.17112v1 Announce Type: new
Abstract: A common architectural pattern in advanced AI reasoning systems is the symbolic graph network: specialized agents or modules connected by delegation edges, routing tasks through a dynamic execution graph. Current schedulers optimize load and fitness but are geometry-blind: they do not model how failures propagate differently in tree-like versus cyclic regimes. In tree-like delegation, a single failure can cascade exponentially; in dense cyclic graphs, failures tend to self-limit. We identify this observability gap, quantify its system-level cost, and propose a lightweight mitigation.
We formulate online geometry control for route-risk estimation on time-indexed execution graphs with route-local failure history. Our approach combines (i) a Euclidean spatio-temporal propagation baseline, (ii) a hyperbolic route-risk model with temporal decay (and optional burst excitation), and (iii) a learned geometry selector over structural features. The selector is a compact MLP (9->12->1) using six topology statistics plus three geometry-aware signals: BFS shell-growth slope, cycle-rank norm, and fitted Poincare curvature. On the Genesis 3 benchmark distribution, adaptive switching improves win rate in the hardest non_tree regime from 64-72% (fixed hyperbolic variants) to 92%, and achieves 87.2% overall win rate.
To measure total system value, we compare against Genesis 3 routing without any spatio-temporal sidecar, using only native bandit/LinUCB signals (team fitness and mean node load). This baseline achieves 50.4% win rate overall and 20% in tree-like regimes; the full sidecar recovers 87.2% overall (+36.8 pp), with +48 to +68 pp gains in tree-like settings, consistent with a cascade-sensitivity analysis. Overall, a 133-parameter sidecar substantially mitigates geometry-blind failure propagation in one high-capability execution-graph system.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
Learning Permutation Distributions via Reflected Diffusion on Ranks
arXiv:2603.17353v1 Announce Type: new
Abstract: The finite symmetric group S_n provides a natural domain for permutations, yet learning probability distributions on S_n is challenging due to its factorially growing size and discrete, non-Euclidean structure. Recent permutation diffusion methods define forward noising via shuffle-based random walks (e.g., riffle shuffles) and learn reverse transitions with Plackett-Luce (PL) variants, but the resulting trajectories can be abrupt and increasingly hard to denoise as n grows. We propose Soft-Rank Diffusion, a discrete diffusion framework that replaces shuffle-based corruption with a structured soft-rank forward process: we lift permutations to a continuous latent representation of order by relaxing discrete ranks into soft ranks, yielding smoother and more tractable trajectories. For the reverse process, we introduce contextualized generalized Plackett-Luce (cGPL) denoisers that generalize prior PL-style parameterizations and improve expressivity for sequential decision structures. Experiments on sorting and combinatorial optimization benchmarks show that Soft-Rank Diffusion consistently outperforms prior diffusion baselines, with particularly strong gains in long-sequence and intrinsically sequential settings.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Federated Multi Agent Deep Learning and Neural Networks for Advanced Distributed Sensing in Wireless Networks
arXiv:2603.16881v1 Announce Type: new
Abstract: Multi-agent deep learning (MADL), including multi-agent deep reinforcement learning (MADRL), distributed/federated training, and graph-structured neural networks, is becoming a unifying framework for decision-making and inference in wireless systems where sensing, communication, and computing are tightly coupled. Recent 5G-Advanced and 6G visions strengthen this coupling through integrated sensing and communication, edge intelligence, open programmable RAN, and non-terrestrial/UAV networking, which create decentralized, partially observed, time-varying, and resource-constrained control problems. This survey synthesizes the state of the art, with emphasis on 2021-2025 research, on MADL for distributed sensing and wireless communications. We present a task-driven taxonomy across (i) learning formulations (Markov games, Dec-POMDPs, CTDE), (ii) neural architectures (GNN-based radio resource management, attention-based policies, hierarchical learning, and over-the-air aggregation), (iii) advanced techniques (federated reinforcement learning, communication-efficient federated deep RL, and serverless edge learning orchestration), and (iv) application domains (MEC offloading with slicing, UAV-enabled heterogeneous networks with power-domain NOMA, intrusion detection in sensor networks, and ISAC-driven perceptive mobile networks). We also provide comparative tables of algorithms, training topologies, and system-level trade-offs in latency, spectral efficiency, energy, privacy, and robustness. Finally, we identify open issues including scalability, non-stationarity, security against poisoning and backdoors, communication overhead, and real-time safety, and outline research directions toward 6G-native sense-communicate-compute-learn systems.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
QuantFL: Sustainable Federated Learning for Edge IoT via Pre-Trained Model Quantisation
arXiv:2603.17507v1 Announce Type: new
Abstract: Federated Learning (FL) enables privacy-preserving intelligence on Internet of Things (IoT) devices but incurs a significant carbon footprint due to the high energy cost of frequent uplink transmission. While pre-trained models are increasingly available on edge devices, their potential to reduce the energy overhead of fine-tuning remains underexplored. In this work, we propose QuantFL, a sustainable FL framework that leverages pre-trained initialisation to enable aggressive, computationally lightweight quantisation. We demonstrate that pre-training naturally concentrates update statistics, allowing us to use memory-efficient bucket quantisation without the energy-intensive overhead of complex error-feedback mechanisms. On MNIST and CIFAR-100, QuantFL reduces total communication by 40\% ($\simeq40\%$ total-bit reduction with full-precision downlink; $\geq80\%$ on uplink or when downlink is quantised) while matching or exceeding uncompressed baselines under strict bandwidth budgets; BU attains 89.00\% (MNIST) and 66.89\% (CIFAR-100) test accuracy with orders of magnitude fewer bits. We also account for uplink and downlink costs and provide ablations on quantisation levels and initialisation. QuantFL delivers a practical, "green" recipe for scalable training on battery-constrained IoT networks.
Fonte: arXiv cs.LG
Vision • Score 85
Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs
arXiv:2603.16932v1 Announce Type: cross
Abstract: Vision-language models (VLMs) typically process images at a native high-resolution, forcing a trade-off between accuracy and computational efficiency: high-resolution inputs capture fine details but incur significant computational costs, while low-resolution inputs advocate for efficiency, they potentially miss critical visual information, like small text. We present AwaRes, a spatial-on-demand framework that resolves this accuracy-efficiency trade-off by operating on a low-resolution global view and using tool-calling to retrieve only high-resolution segments needed for a given query. We construct supervised data automatically: a judge compares low- vs.\ high-resolution answers to label whether cropping is needed, and an oracle grounding model localizes the evidence for the correct answer, which we map to a discrete crop set to form multi-turn tool-use trajectories. We train our framework with cold-start SFT followed by multi-turn GRPO with a composite reward that combines semantic answer correctness with explicit crop-cost penalties. Project page: https://nimrodshabtay.github.io/AwaRes
Fonte: arXiv cs.AI
Multimodal • Score 85
OpenQlaw: An Agentic AI Assistant for Analysis of 2D Quantum Materials
arXiv:2603.17043v1 Announce Type: new
Abstract: The transition from optical identification of 2D quantum materials to practical device fabrication requires dynamic reasoning beyond the detection accuracy. While recent domain-specific Multimodal Large Language Models (MLLMs) successfully ground visual features using physics-informed reasoning, their outputs are optimized for step-by-step cognitive transparency. This yields verbose candidate enumerations followed by dense reasoning that, while accurate, may induce cognitive overload and lack immediate utility for real-world interaction with researchers. To address this challenge, we introduce OpenQlaw, an agentic orchestration system for analyzing 2D materials. The architecture is built upon NanoBot, a lightweight agentic framework inspired by OpenClaw, and QuPAINT, one of the first Physics-Aware Instruction Multi-modal platforms for Quantum Material Discovery. This allows accessibility to the lab floor via a variety of messaging channels. OpenQlaw allows the core Large Language Model (LLM) agent to orchestrate a domain-expert MLLM,with QuPAINT, as a specialized node, successfully decoupling visual identification from reasoning and deterministic image rendering. By parsing spatial data from the expert, the agent can dynamically process user queries, such as performing scale-aware physical computation or generating isolated visual annotations, and answer in a naturalistic manner. Crucially, the system features a persistent memory that enables the agent to save physical scale ratios (e.g., 1 pixel = 0.25 {\mu}m) for area computations and store sample preparation methods for efficacy comparison. The application of an agentic architecture, together with the extension that uses the core agent as an orchestrator for domain-specific experts, transforms isolated inferences into a context-aware assistant capable of accelerating high-throughput device fabrication.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
Beyond Outliers: A Data-Free Layer-wise Mixed-Precision Quantization Approach Driven by Numerical and Structural Dual-Sensitivity
arXiv:2603.17354v1 Announce Type: new
Abstract: Layer-wise mixed-precision quantization (LMPQ) enables effective compression under extreme low-bit settings by allocating higher precision to sensitive layers. However, existing methods typically treat all intra-layer weight modules uniformly and rely on a single numerical property when estimating sensitivity, overlooking their distinct operational roles and structural characteristics. To address this, we propose NSDS, a novel calibration-free LMPQ framework driven by Numerical and Structural Dual-Sensitivity. Specifically, it first mechanistically decomposes each layer into distinct operational roles and quantifies their sensitivity from both numerical and structural perspectives. These dual-aspect scores are then aggregated into a unified layer-wise metric through a robust aggregation scheme based on MAD-Sigmoid and Soft-OR to guide bit allocation. Extensive experiments demonstrate that NSDS consistently achieves superior performance compared to various baselines across diverse models and downstream tasks, without relying on any calibration data.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Graph-Native Cognitive Memory for AI Agents: Formal Belief Revision Semantics for Versioned Memory Architectures
arXiv:2603.17244v1 Announce Type: new
Abstract: While individual components for AI agent memory exist in prior systems, their architectural synthesis and formal grounding remain underexplored. We present Kumiho, a graph-native cognitive memory architecture grounded in formal belief revision semantics. The structural primitives required for cognitive memory -- immutable revisions, mutable tag pointers, typed dependency edges, URI-based addressing -- are identical to those required for managing agent-produced work as versionable assets, enabling a unified graph-native architecture that serves both purposes. The central formal contribution is a correspondence between the AGM belief revision framework and the operational semantics of a property graph memory system, proving satisfaction of the basic AGM postulates (K*2--K*6) and Hansson's belief base postulates (Relevance, Core-Retainment). The architecture implements a dual-store model (Redis working memory, Neo4j long-term graph) with hybrid fulltext and vector retrieval. On LoCoMo (token-level F1), Kumiho achieves 0.565 overall F1 (n=1,986) including 97.5% adversarial refusal accuracy. On LoCoMo-Plus, a Level-2 cognitive memory benchmark testing implicit constraint recall, Kumiho achieves 93.3% judge accuracy (n=401); independent reproduction by the benchmark authors yielded results in the mid-80% range, still substantially outperforming all published baselines (best: Gemini 2.5 Pro, 45.7%). Three architectural innovations drive the results: prospective indexing (LLM-generated future-scenario implications indexed at write time), event extraction (structured causal events preserved in summaries), and client-side LLM reranking. The architecture is model-decoupled: switching the answer model from GPT-4o-mini (~88%) to GPT-4o (93.3%) improves end-to-end accuracy without pipeline changes, at a total evaluation cost of ~$14 for 401 entries.
Fonte: arXiv cs.AI
RL • Score 85
Multi-Modal Multi-Agent Reinforcement Learning for Radiology Report Generation: Radiologist-Like Workflow with Clinically Verifiable Rewards
arXiv:2603.16876v1 Announce Type: cross
Abstract: We propose MARL-Rad, a novel multi-modal multi-agent reinforcement learning framework for radiology report generation that coordinates region-specific agents and a global integrating agent, optimized via clinically verifiable rewards. Unlike prior single-model reinforcement learning or post-hoc agentization of independently trained models, our method jointly trains multiple agents and optimizes the entire agent system through reinforcement learning. Experiments on the MIMIC-CXR and IU X-ray datasets show that MARL-Rad consistently improves clinically efficacy (CE) metrics such as RadGraph, CheXbert, and GREEN scores, achieving state-of-the-art CE performance. Further analyses confirm that MARL-Rad enhances laterality consistency and produces more accurate, detail-informed reports.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
MosaicMem: Hybrid Spatial Memory for Controllable Video World Models
arXiv:2603.17117v1 Announce Type: new
Abstract: Video diffusion models are moving beyond short, plausible clips toward world simulators that must remain consistent under camera motion, revisits, and intervention. Yet spatial memory remains a key bottleneck: explicit 3D structures can improve reprojection-based consistency but struggle to depict moving objects, while implicit memory often produces inaccurate camera motion even with correct poses. We propose Mosaic Memory (MosaicMem), a hybrid spatial memory that lifts patches into 3D for reliable localization and targeted retrieval, while exploiting the model's native conditioning to preserve prompt-following generation. MosaicMem composes spatially aligned patches in the queried view via a patch-and-compose interface, preserving what should persist while allowing the model to inpaint what should evolve. With PRoPE camera conditioning and two new memory alignment methods, experiments show improved pose adherence compared to implicit memory and stronger dynamic modeling than explicit baselines. MosaicMem further enables minute-level navigation, memory-based scene editing, and autoregressive rollout.
Fonte: arXiv cs.CV
NLP/LLMs • Score 92
A Progressive Visual-Logic-Aligned Framework for Ride-Hailing Adjudication
arXiv:2603.17328v1 Announce Type: new
Abstract: The efficient adjudication of responsibility disputes is pivotal for maintaining marketplace fairness. However, the exponential surge in ride-hailing volume renders manual review intractable, while conventional automated methods lack the reasoning transparency required for quasi-judicial decisions. Although Multimodal LLMs offer a promising paradigm, they fundamentally struggle to bridge the gap between general visual semantics and rigorous evidentiary protocols, often leading to perceptual hallucinations and logical looseness. To address these systemic misalignments, we introduce RideJudge, a Progressive Visual-Logic-Aligned Framework. Instead of relying on generic pre-training, we bridge the semantic gap via SynTraj, a synthesis engine that grounds abstract liability concepts into concrete trajectory patterns. To resolve the conflict between massive regulation volume and limited context windows, we propose an Adaptive Context Optimization strategy that distills expert knowledge, coupled with a Chain-of-Adjudication mechanism to enforce active evidentiary inquiry. Furthermore, addressing the inadequacy of sparse binary feedback for complex liability assessment, we implement a novel Ordinal-Sensitive Reinforcement Learning mechanism that calibrates decision boundaries against hierarchical severity. Extensive experiments show that our RideJudge-8B achieves 88.41\% accuracy, surpassing 32B-scale baselines and establishing a new standard for interpretable adjudication.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
SCALE:Scalable Conditional Atlas-Level Endpoint transport for virtual cell perturbation prediction
arXiv:2603.17380v1 Announce Type: new
Abstract: Virtual cell models aim to enable in silico experimentation by predicting how cells respond to genetic, chemical, or cytokine perturbations from single-cell measurements. In practice, however, large-scale perturbation prediction remains constrained by three coupled bottlenecks: inefficient training and inference pipelines, unstable modeling in high-dimensional sparse expression space, and evaluation protocols that overemphasize reconstruction-like accuracy while underestimating biological fidelity. In this work we present a specialized large-scale foundation model SCALE for virtual cell perturbation prediction that addresses the above limitations jointly. First, we build a BioNeMo-based training and inference framework that substantially improves data throughput, distributed scalability, and deployment efficiency, yielding 12.51* speedup on pretrain and 1.29* on inference over the prior SOTA pipeline under matched system settings. Second, we formulate perturbation prediction as conditional transport and implement it with a set-aware flow architecture that couples LLaMA-based cellular encoding with endpoint-oriented supervision. This design yields more stable training and stronger recovery of perturbation effects. Third, we evaluate the model on Tahoe-100M using a rigorous cell-level protocol centered on biologically meaningful metrics rather than reconstruction alone. On this benchmark, our model improves PDCorr by 12.02% and DE Overlap by 10.66% over STATE. Together, these results suggest that advancing virtual cells requires not only better generative objectives, but also the co-design of scalable infrastructure, stable transport modeling, and biologically faithful evaluation.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
AI Scientist via Synthetic Task Scaling
arXiv:2603.17216v1 Announce Type: new
Abstract: With the advent of AI agents, automatic scientific discovery has become a tenable goal. Many recent works scaffold agentic systems that can perform machine learning research, but don't offer a principled way to train such agents -- and current LLMs often generate plausible-looking but ineffective ideas. To make progress on training agents that can learn from doing, we provide a novel synthetic environment generation pipeline targeting machine learning agents. Our pipeline automatically synthesizes machine learning challenges compatible with the SWE-agent framework, covering topic sampling, dataset proposal, and code generation. The resulting synthetic tasks are 1) grounded in real machine learning datasets, because the proposed datasets are verified against the Huggingface API and are 2) verified for higher quality with a self-debugging loop. To validate the effectiveness of our synthetic tasks, we tackle MLGym, a benchmark for machine learning tasks. From the synthetic tasks, we sample trajectories from a teacher model (GPT-5), then use the trajectories to train a student model (Qwen3-4B and Qwen3-8B). The student models trained with our synthetic tasks achieve improved performance on MLGym, raising the AUP metric by 9% for Qwen3-4B and 12% for Qwen3-8B.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse
arXiv:2603.18000v1 Announce Type: new
Abstract: Building LLM-based agents has become increasingly important. Recent works on LLM-based agent self-evolution primarily record successful experiences as textual prompts or reflections, which cannot reliably guarantee efficient task re-execution in complex scenarios. We propose AgentFactory, a new self-evolution paradigm that preserves successful task solutions as executable subagent code rather than textual experience. Crucially, these subagents are continuously refined based on execution feedback, becoming increasingly robust and efficient as more tasks are encountered. Saved subagents are pure Python code with standardized documentation, enabling portability across any Python-capable system. We demonstrate that AgentFactory enables continuous capability accumulation: its library of executable subagents grows and improves over time, progressively reducing the effort required for similar tasks without manual intervention. Our implementation is open-sourced at https://github.com/zzatpku/AgentFactory, and our demonstration video is available at https://youtu.be/iKSsuAXJHW0.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
From Digital Twins to World Models:Opportunities, Challenges, and Applications for Mobile Edge General Intelligence
arXiv:2603.17420v1 Announce Type: new
Abstract: The rapid evolution toward 6G and beyond communication systems is accelerating the convergence of digital twins and world models at the network edge. Traditional digital twins provide high-fidelity representations of physical systems and support monitoring, analysis, and offline optimization. However, in highly dynamic edge environments, they face limitations in autonomy, adaptability, and scalability. This paper presents a systematic survey of the transition from digital twins to world models and discusses its role in enabling edge general intelligence (EGI). First, the paper clarifies the conceptual differences between digital twins and world models and highlights the shift from physics-based, centralized, and system-centric replicas to data-driven, decentralized, and agent-centric internal models. This discussion helps readers gain a clear understanding of how this transition enables more adaptive, autonomous, and resource-efficient intelligence at the network edge. The paper reviews the design principles, architectures, and key components of world models, including perception, latent state representation, dynamics learning, imagination-based planning, and memory. In addition, it examines the integration of world models and digital twins in wireless EGI systems and surveys emerging applications in integrated sensing and communications, semantic communication, air-ground networks, and low-altitude wireless networks. Finally, this survey provides a systematic roadmap and practical insights for designing world-model-driven edge intelligence systems in wireless and edge computing environments. It also outlines key research challenges and future directions toward scalable, reliable, and interoperable world models for edge-native agentic AI.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
SENSE: Efficient EEG-to-Text via Privacy-Preserving Semantic Retrieval
arXiv:2603.17109v1 Announce Type: new
Abstract: Decoding brain activity into natural language is a major challenge in AI with important applications in assistive communication, neurotechnology, and human-computer interaction. Most existing Brain-Computer Interface (BCI) approaches rely on memory-intensive fine-tuning of Large Language Models (LLMs) or encoder-decoder models on raw EEG signals, resulting in expensive training pipelines, limited accessibility, and potential exposure of sensitive neural data. We introduce SENSE (SEmantic Neural Sparse Extraction), a lightweight and privacy-preserving framework that translates non-invasive electroencephalography (EEG) into text without LLM fine-tuning. SENSE decouples decoding into two stages: on-device semantic retrieval and prompt-based language generation. EEG signals are locally mapped to a discrete textual space to extract a non-sensitive Bag-of-Words (BoW), which conditions an off-the-shelf LLM to synthesize fluent text in a zero-shot manner. The EEG-to-keyword module contains only ~6M parameters and runs fully on-device, ensuring raw neural signals remain local while only abstract semantic cues interact with language models. Evaluated on a 128-channel EEG dataset across six subjects, SENSE matches or surpasses the generative quality of fully fine-tuned baselines such as Thought2Text while substantially reducing computational overhead. By localizing neural decoding and sharing only derived textual cues, SENSE provides a scalable and privacy-aware retrieval-augmented architecture for next-generation BCIs.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
DANCE: Dynamic 3D CNN Pruning: Joint Frame, Channel, and Feature Adaptation for Energy Efficiency on the Edge
arXiv:2603.17275v1 Announce Type: new
Abstract: Modern convolutional neural networks (CNNs) are workhorses for video and image processing, but fail to adapt to the computational complexity of input samples in a dynamic manner to minimize energy consumption. In this research, we propose DANCE, a fine-grained, input-aware, dynamic pruning framework for 3D CNNs to maximize power efficiency with negligible to zero impact on performance. In the proposed two-step approach, the first step is called activation variability amplification (AVA), and the 3D CNN model is retrained to increase the variance of the magnitude of neuron activations across the network in this step, facilitating pruning decisions across diverse CNN input scenarios. In the second step, called adaptive activation pruning (AAP), a lightweight activation controller network is trained to dynamically prune frames, channels, and features of 3D convolutional layers of the network (different for each layer), based on statistics of the outputs of the first layer of the network. Our method achieves substantial savings in multiply-accumulate (MAC) operations and memory accesses by introducing sparsity within convolutional layers. Hardware validation on the NVIDIA Jetson Nano GPU and the Qualcomm Snapdragon 8 Gen 1 platform demonstrates respective speedups of 1.37X and 2.22X, achieving up to 1.47X higher energy efficiency compared to the state of the art.
Fonte: arXiv cs.CV
NLP/LLMs • Score 90
Prose2Policy (P2P): A Practical LLM Pipeline for Translating Natural-Language Access Policies into Executable Rego
arXiv:2603.15799v1 Announce Type: new
Abstract: Prose2Policy (P2P) is a LLM-based practical tool that translates natural-language access control policies (NLACPs) into executable Rego code (the policy language of Open Policy Agent, OPA). It provides a modular, end-to-end pipeline that performs policy detection, component extraction, schema validation, linting, compilation, automatic test generation and execution. Prose2Policy is designed to bridge the gap between human-readable access requirements and machine-enforceable policy-as-code (PaC) while emphasizing deployment reliability and auditability. We evaluated Prose2Policy on the ACRE dataset and demonstrated a 95.3\% compile rate for accepted policies, with automated testing achieving a 82.2\% positive-test pass rate and a 98.9\% negative-test pass rate. These results indicate that Prose2Policy produces syntactically robust and behaviorally consistent Rego policies suitable for Zero Trust and compliance-driven environments.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
CraniMem: Cranial Inspired Gated and Bounded Memory for Agentic Systems
arXiv:2603.15642v1 Announce Type: new
Abstract: Large language model (LLM) agents are increasingly deployed in long running workflows, where they must preserve user and task state across many turns. Many existing agent memory systems behave like external databases with ad hoc read/write rules, which can yield unstable retention, limited consolidation, and vulnerability to distractor content. We present CraniMem, a neurocognitively motivated, gated and bounded multi-stage memory design for agentic systems. CraniMem couples goal conditioned gating and utility tagging with a bounded episodic buffer for near term continuity and a structured long-term knowledge graph for durable semantic recall. A scheduled consolidation loop replays high utility traces into the graph while pruning low utility items, keeping memory growth in check and reducing interference. On long horizon benchmarks evaluated under both clean inputs and injected noise, CraniMem is more robust than a Vanilla RAG and Mem0 baseline and exhibits smaller performance drops under distraction. Our code is available at https://github.com/PearlMody05/Cranimem and the accompanying PyPI package at https://pypi.org/project/cranimem.
Fonte: arXiv cs.AI
RL • Score 85
Beyond Reward Suppression: Reshaping Steganographic Communication Protocols in MARL via Dynamic Representational Circuit Breaking
arXiv:2603.15655v1 Announce Type: new
Abstract: In decentralized Multi-Agent Reinforcement Learning (MARL), steganographic collusion -- where agents develop private protocols to evade monitoring -- presents a critical AI safety threat. Existing defenses, limited to behavioral or reward layers, fail to detect coordination in latent communication channels. We introduce the Dynamic Representational Circuit Breaker (DRCB), an architectural defense operating at the optimization substrate.
Building on the AI Mother Tongue (AIM) framework, DRCB utilizes a Vector Quantized Variational Autoencoder (VQ-VAE) bottleneck to convert unobservable messages into auditable statistical objects. DRCB monitors signals including Jensen-Shannon Divergence drift, L2-norm codebook displacement, and Randomized Observer Pool accuracy to compute an EMA-based Collusion Score. Threshold breaches trigger four escalating interventions: dynamic adaptation, gradient-space penalty injection into the Advantage function A^pi, temporal reward suppression, and full substrate circuit breaking via codebook shuffling and optimizer state reset.
Experiments on a Contextual Prisoner's Dilemma with MNIST labels show that while static monitoring fails (p = 0.3517), DRCB improves observer mean accuracy from 0.858 to 0.938 (+9.3 percent) and reduces volatility by 43 percent, while preserving mean joint reward (p = 0.854). Analysis of 214,298 symbol samples confirms "Semantic Degradation," where high-frequency sequences converge to zero entropy, foreclosing complex steganographic encodings. We identify a "Transparency Paradox" where agents achieve surface-level determinism while preserving residual capacity in long-tail distributions, reflecting Goodhart's Law. This task-agnostic methodology provides a technical path toward MICA-compliant (Multi-Agent Internal Coupling Audit) pre-deployment auditing for autonomous systems.
Fonte: arXiv cs.LG
MLOps/Systems • Score 90
Determinism in the Undetermined: Deterministic Output in Charge-Conserving Continuous-Time Neuromorphic Systems with Temporal Stochasticity
arXiv:2603.15987v1 Announce Type: new
Abstract: Achieving deterministic computation results in asynchronous neuromorphic systems remains a fundamental challenge due to the inherent temporal stochasticity of continuous-time hardware. To address this, we develop a unified continuous-time framework for spiking neural networks (SNNs) that couples the Law of Charge Conservation with minimal neuron-level constraints. This integration ensures that the terminal state depends solely on the aggregate input charge, providing a unique cumulated output invariant to temporal stochasticity. We prove that this mapping is strictly invariant to spike timing in acyclic networks, whereas recurrent connectivity can introduce temporal sensitivity. Furthermore, we establish an exact representational correspondence between these charge-conserving SNNs and quantized artificial neural networks, bridging the gap between static deep learning and event-driven dynamics without approximation errors. These results establish a rigorous theoretical basis for designing continuous-time neuromorphic systems that harness the efficiency of asynchronous processing while maintaining algorithmic determinism.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
From Workflow Automation to Capability Closure: A Formal Framework for Safe and Revenue-Aware Customer Service AI
arXiv:2603.15978v1 Announce Type: new
Abstract: Customer service automation is undergoing a structural transformation. The dominant paradigm is shifting from scripted chatbots and single-agent responders toward networks of specialised AI agents that compose capabilities dynamically across billing, service provision, payments, and fulfilment. This shift introduces a safety gap that no current platform has closed: two agents individually verified as safe can, when combined, reach a forbidden goal through an emergent conjunctive dependency that neither possesses alone.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
NextMem: Towards Latent Factual Memory for LLM-based Agents
arXiv:2603.15634v1 Announce Type: new
Abstract: Memory is critical for LLM-based agents to preserve past observations for future decision-making, where factual memory serves as its foundational part. However, existing approaches to constructing factual memory face several limitations. Textual methods impose heavy context and indexing burdens, while parametric methods suffer from catastrophic forgetting and high costs. To address these challenges, we introduce NextMem, a latent factual memory framework that utilizes an autoregressive autoencoder to efficiently construct latent memory while ensuring accurate reconstruction. For better optimization, we propose a two-stage training process, including autoregressive reconstruction alignment and progressive latent substitution. We also incorporate quantization to reduce storage overhead. Extensive experiments demonstrate that NextMem achieves superior performance, and excels in retrieval, robustness, and extensibility properties. We release our code and model checkpoints at https://github.com/nuster1128/NextMem.
Fonte: arXiv cs.AI
Applications • Score 85
AI-Generated Figures in Academic Publishing: Policies, Tools, and Practical Guidelines
arXiv:2603.16159v1 Announce Type: new
Abstract: The rapid advancement of generative AI has introduced a new class of tools capable of producing publication-quality scientific figures, graphical abstracts, and data visualizations. However, academic publishers have responded with inconsistent and often ambiguous policies regarding AI-generated imagery. This paper surveys the current stance of major journals and publishers -- including Nature, Science, Cell Press, Elsevier, and PLOS -- on the use of AI-generated figures. We identify key concerns raised by publishers, including reproducibility, authorship attribution, and potential for visual misinformation. Drawing on practical examples from tools such as SciDraw, an AI-powered platform designed specifically for scientific illustration, we propose a set of best-practice guidelines for researchers seeking to use AI figure-generation tools in a compliant and transparent manner. Our findings suggest that, with appropriate disclosure and quality control, AI-generated figures can meaningfully accelerate scientific communication without compromising integrity.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
Flow Matching for Tabular Data Synthesis
arXiv:2512.00698v3 Announce Type: replace-cross
Abstract: Synthetic data generation is an important tool for privacy-preserving data sharing. Although diffusion models have set recent benchmarks, flow matching (FM) offers a promising alternative. This paper presents different ways to implement FM for tabular data synthesis. We provide a comprehensive empirical study that compares flow matching (FM and variational FM) with a state-of-the-art diffusion method (TabDDPM and TabSyn) in tabular data synthesis. We evaluate both the standard Optimal Transport (OT) and the Variance Preserving (VP) probability paths, and also compare deterministic and stochastic samplers -- something possible when learning to generate using \textit{variational} FM -- characterising the empirical relationship between data utility and privacy risk. Our key findings reveal that FM, particularly TabbyFlow, outperforms diffusion baselines. Flow matching methods also achieve better performance with remarkably low function evaluations ($\leq$ 100 steps), offering a substantial computational advantage. The choice of probability path is also crucial, as using the OT is a strong default and more robust to early stopping on average, while VP has potential to produce synthetic data with lower privacy risk. Lastly, our results show that making flows stochastic not only preserves marginal distributions but, in some instances, enables the generation of high utility synthetic data with reduced disclosure risk. The implementation code associated with this paper is publicly available at https://github.com/rulnasution/tabular-flow-matching.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale
arXiv:2603.15954v1 Announce Type: new
Abstract: Real-time AI experiences call for on-device large language models (OD-LLMs) optimized for efficient deployment on resource-constrained hardware. The most useful OD-LLMs produce near-real-time responses and exhibit broad hardware compatibility, maximizing user reach. We present a methodology for designing such models using hardware-in-the-loop architecture search under mobile latency constraints. This system is amenable to industry-scale deployment: it generates models deployable without custom kernels and compatible with standard mobile runtimes like Executorch. Our methodology avoids specialized attention mechanisms and instead uses attention skipping for long-context acceleration.
Our approach jointly optimizes model architecture (layers, dimensions) and attention pattern. To efficiently evaluate candidates, we treat each as a pruned version of a pretrained backbone with inherited weights, thereby achieving high accuracy with minimal continued pretraining. We leverage the low cost of latency evaluation in a staged process: learning an accurate latency model first, then searching for the Pareto-frontier across latency and quality.
This yields MobileLLM-Flash, a family of foundation models (350M, 650M, 1.4B) for efficient on-device use with strong capabilities, supporting up to 8k context length. MobileLLM-Flash delivers up to 1.8x and 1.6x faster prefill and decode on mobile CPUs with comparable or superior quality. Our analysis of Pareto-frontier design choices offers actionable principles for OD-LLM design.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Discovery of interaction and diffusion kernels in particle-to-mean-field multi-agent systems
arXiv:2603.15927v1 Announce Type: new
Abstract: We propose a data-driven framework to learn interaction kernels in stochastic multi-agent systems. Our approach aims at identifying the functional form of nonlocal interaction and diffusion terms directly from trajectory data, without any a priori knowledge of the underlying interaction structure. Starting from a discrete stochastic binary-interaction model, we formulate the inverse problem as a sequence of sparse regression tasks in structured finite-dimensional spaces spanned by compactly supported basis functions, such as piecewise linear polynomials. In particular, we assume that pairwise interactions between agents are not directly observed and that only limited trajectory data are available. To address these challenges, we propose two complementary identification strategies. The first based on random-batch sampling, which compensates for latent interactions while preserving the statistical structure of the full dynamics in expectation. The second based on a mean-field approximation, where the empirical particle density reconstructed from the data defines a continuous nonlocal regression problem. Numerical experiments demonstrate the effectiveness and robustness of the proposed framework, showing accurate reconstruction of both interaction and diffusion kernels even from partially observed. The method is validated on benchmark models, including bounded-confidence and attraction-repulsion dynamics, where the two proposed strategies achieve comparable levels of accuracy.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Parallelised Differentiable Straightest Geodesics for 3D Meshes
arXiv:2603.15780v1 Announce Type: new
Abstract: Machine learning has been progressively generalised to operate within non-Euclidean domains, but geometrically accurate methods for learning on surfaces are still falling behind. The lack of closed-form Riemannian operators, the non-differentiability of their discrete counterparts, and poor parallelisation capabilities have been the main obstacles to the development of the field on meshes. A principled framework to compute the exponential map on Riemannian surfaces discretised as meshes is straightest geodesics, which also allows to trace geodesics and parallel-transport vectors as a by-product. We provide a parallel GPU implementation and derive two different methods for differentiating through the straightest geodesics, one leveraging an extrinsic proxy function and one based upon a geodesic finite differences scheme. After proving our parallelisation performance and accuracy, we demonstrate how our differentiable exponential map can improve learning and optimisation pipelines on general geometries. In particular, to showcase the versatility of our method, we propose a new geodesic convolutional layer, a new flow matching method for learning on meshes, and a second-order optimiser that we apply to centroidal Voronoi tessellation. Our code, models, and pip-installable library (digeo) are available at: circle-group.github.io/research/DSG.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
FlashSampling: Fast and Memory-Efficient Exact Sampling
arXiv:2603.15854v1 Announce Type: new
Abstract: Sampling from a categorical distribution is mathematically simple, but in large-vocabulary decoding, it often triggers extra memory traffic and extra kernels after the LM head. We present FlashSampling, an exact sampling primitive that fuses sampling into the LM-head matmul and never materializes the logits tensor in HBM. The method is simple: compute logits tile-by-tile on chip, add Gumbel noise, keep only one maximizer per row and per vocabulary tile, and finish with a small reduction over tiles. The fused tiled kernel is exact because $\argmax$ decomposes over a partition; grouped variants for online and tensor-parallel settings are exact by hierarchical factorization of the categorical distribution. Across H100, H200, B200, and B300 GPUs, FlashSampling speeds up kernel-level decode workloads, and in end-to-end vLLM experiments, it reduces time per output token by up to $19%$ on the models we test. These results show that exact sampling, with no approximation, can be integrated into the matmul itself, turning a bandwidth-bound postprocessing step into a lightweight epilogue. Project Page: https://github.com/FlashSampling/FlashSampling.
Fonte: arXiv cs.LG
Privacy/Security/Fairness • Score 92
Federated Learning for Privacy-Preserving Medical AI
arXiv:2603.15901v1 Announce Type: new
Abstract: This dissertation investigates privacy-preserving federated learning for Alzheimer's disease classification using three-dimensional MRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Existing methodologies often suffer from unrealistic data partitioning, inadequate privacy guarantees, and insufficient benchmarking, limiting their practical deployment in healthcare. To address these gaps, this research proposes a novel site-aware data partitioning strategy that preserves institutional boundaries, reflecting real-world multi-institutional collaborations and data heterogeneity. Furthermore, an Adaptive Local Differential Privacy (ALDP) mechanism is introduced, dynamically adjusting privacy parameters based on training progression and parameter characteristics, thereby significantly improving the privacy-utility trade-off over traditional fixed-noise approaches. Systematic empirical evaluation across multiple client federations and privacy budgets demonstrated that advanced federated optimisation algorithms, particularly FedProx, could equal or surpass centralised training performance while ensuring rigorous privacy protection. Notably, ALDP achieved up to 80.4% accuracy in a two-client configuration, surpassing fixed-noise Local DP by 5-7 percentage points and demonstrating substantially greater training stability. The comprehensive ablation studies and benchmarking establish quantitative standards for privacy-preserving collaborative medical AI, providing practical guidelines for real-world deployment. This work thereby advances the state-of-the-art in federated learning for medical imaging, establishing both methodological foundations and empirical evidence necessary for future privacy-compliant AI adoption in healthcare.
Fonte: arXiv cs.LG
Vision • Score 85
Domain Adaptation Without the Compute Burden for Efficient Whole Slide Image Analysis
arXiv:2603.15774v1 Announce Type: new
Abstract: Computational methods on analyzing Whole Slide Images (WSIs) enable early diagnosis and treatments by supporting pathologists in detection and classification of tumors. However, the extremely high resolution of WSIs makes end-to-end training impractical compared to typical image analysis tasks. To address this, most approaches use pre-trained feature extractors to obtain fixed representations of whole slides, which are then combined with Multiple Instance Learning (MIL) for downstream tasks. These feature extractors are typically pre-trained on natural image datasets such as ImageNet, which fail to capture domain-specific characteristics. Although domain-specific pre-training on histopathology data yields more relevant feature representations, it remains computationally expensive and fail to capture task-specific characteristics within the domain. To address the computational cost and lack of task-specificity in domain-specific pre-training, we propose EfficientWSI (eWSI), a careful integration of Parameter-Efficient-Fine-Tuning (PEFT) and Multiple Instance Learning (MIL) that enables end-to-end training on WSI tasks. We evaluate eWSI on seven WSI-level tasks over Camelyon16, TCGA and BRACS datasets. Our results show that eWSI when applied with ImageNet feature extractors yields strong classification performance, matching or outperforming MILs with in-domain feature extractors, alleviating the need for extensive in-domain pre-training. Furthermore, when eWSI is applied with in-domain feature extractors, it further improves classification performance in most cases, demonstrating its ability to capture task-specific information where beneficial. Our findings suggest that eWSI provides a task-targeted, computationally efficient path for WSI tasks, offering a promising direction for task-specific learning in computational pathology.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
VIGIL: Towards Edge-Extended Agentic AI for Enterprise IT Support
arXiv:2603.16110v1 Announce Type: new
Abstract: Enterprise IT support is constrained by heterogeneous devices, evolving policies, and long-tail failure modes that are difficult to resolve centrally. We present VIGIL, an edge-extended agentic AI system that deploys desktop-resident agents to perform situated diagnosis, retrieval over enterprise knowledge, and policy-governed remediation directly on user devices with explicit consent and end-to-end observability. In a 10-week pilot of VIGIL's operational loop on 100 resource-constrained endpoints, VIGIL reduces interaction rounds by 39%, achieves at least 4 times faster diagnosis, and supports self-service resolution in 82% of matched cases. Users report excellent usability, high trust, and low cognitive workload across four validated instruments, with qualitative feedback highlighting transparency as critical for trust. Notably, users rated the system higher when no historical matches were available, suggesting on-device diagnosis provides value independent of knowledge base coverage. This pilot establishes safety and observability foundations for fleet-wide continuous improvement.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
DualPrim: Compact 3D Reconstruction with Positive and Negative Primitives
arXiv:2603.16133v1 Announce Type: new
Abstract: Neural reconstructions often trade structure for fidelity, yielding dense and unstructured meshes with irregular topology and weak part boundaries that hinder editing, animation, and downstream asset reuse. We present DualPrim, a compact and structured 3D reconstruction framework. Unlike additive-only implicit or primitive methods, DualPrim represents shapes with positive and negative superquadrics: the former builds the bases while the latter carves local volumes through a differentiable operator, enabling topology-aware modeling of holes and concavities. This additive-subtractive design increases the representational power without sacrificing compactness or differentiability. We embed DualPrim in a volumetric differentiable renderer, enabling end-to-end learning from multi-view images and seamless mesh export via closed-form boolean difference. Empirically, DualPrim delivers state-of-the-art accuracy and produces compact, structured, and interpretable outputs that better satisfy downstream needs than additive-only alternatives.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors
arXiv:2603.15656v1 Announce Type: new
Abstract: The performance of neural network models deteriorates due to their unreliable behavior on non-robust features of corrupted samples. Owing to their opaque nature, rectifying models to address this problem often necessitates arduous data cleaning and model retraining, resulting in huge computational and manual overhead. In this work, we leverage rank-one model editing to establish an attribution-guided model rectification framework that effectively locates and corrects model unreliable behaviors. We first distinguish our rectification setting from existing model editing, yielding a formulation that corrects unreliable behavior while preserving model performance and reducing reliance on large budgets of cleansed samples. We further reveal a bottleneck of model rectifying arising from heterogeneous editability across layers. To target the primary source of misbehavior, we introduce an attribution-guided layer localization method that quantifies layer-wise editability and identifies the layer most responsible for unreliabilities. Extensive experiments demonstrate the effectiveness of our method in correcting unreliabilities observed for neural Trojans, spurious correlations and feature leakage. Our method shows remarkable performance by achieving its editing objective with as few as a single cleansed sample, which makes it appealing for practice.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Convergence Bounds for Sequential Monte Carlo on Multimodal Distributions using Soft Decomposition
arXiv:2405.19553v2 Announce Type: replace-cross
Abstract: We prove bounds on the variance of a function $f$ under the empirical measure of the samples obtained by the Sequential Monte Carlo (SMC) algorithm, with time complexity depending on local rather than global Markov chain mixing dynamics. SMC is a Markov Chain Monte Carlo (MCMC) method, which starts by drawing $N$ particles from a known distribution, and then, through a sequence of distributions, re-weights and re-samples the particles, at each instance applying a Markov chain for smoothing. In principle, SMC tries to alleviate problems from multi-modality. However, most theoretical guarantees for SMC are obtained by assuming global mixing time bounds, which are only efficient in the uni-modal setting. We show that bounds can be obtained in the truly multi-modal setting, with mixing times that depend only on local MCMC dynamics.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
Semi-Autonomous Formalization of the Vlasov-Maxwell-Landau Equilibrium
arXiv:2603.15929v1 Announce Type: new
Abstract: We present a complete Lean 4 formalization of the equilibrium characterization in the Vlasov-Maxwell-Landau (VML) system, which describes the motion of charged plasma. The project demonstrates the full AI-assisted mathematical research loop: an AI reasoning model (Gemini DeepThink) generated the proof from a conjecture, an agentic coding tool (Claude Code) translated it into Lean from natural-language prompts, a specialized prover (Aristotle) closed 111 lemmas, and the Lean kernel verified the result. A single mathematician supervised the process over 10 days at a cost of \$200, writing zero lines of code.
The entire development process is public: all 229 human prompts, and 213 git commits are archived in the repository. We report detailed lessons on AI failure modes -- hypothesis creep, definition-alignment bugs, agent avoidance behaviors -- and on what worked: the abstract/concrete proof split, adversarial self-review, and the critical role of human review of key definitions and theorem statements. Notably, the formalization was completed before the final draft of the corresponding math paper was finished.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
MoLoRA: Composable Specialization via Per-Token Adapter Routing
arXiv:2603.15965v1 Announce Type: new
Abstract: Multi-adapter serving systems route entire sequences to a single adapter, forcing a choice when requests span multiple domains. This assumption fails in two important settings: (1) multimodal generation, where text and image tokens require different adapters within the same sequence, and (2) mixed-capability requests like "write code to solve this equation," which need expertise from multiple specialized adapters. We introduce per-token routing, which routes individual tokens to adapters based on either vocabulary structure (for multimodal models) or learned gating (for semantic specialization). Per-token routing is provably optimal, achieving work N for N tokens versus K \cdot N for per-sequence routing with K adapter types. Our key contribution is MoLoRA (Mixture of LoRA), which enables composable specialization: load multiple domain-specific adapters and let a learned router select the appropriate adapter per-token. We demonstrate that specialization dramatically beats scale: MoLoRA enables Qwen3-1.7B to exceed Qwen3-8B across four reasoning benchmarks while being 4.7x smaller. This enables modular expertise at inference time: train focused LoRAs independently, combine them without retraining, and add new capabilities by simply loading new adapters.
Fonte: arXiv cs.CL
NLP/LLMs • Score 90
A federated learning framework with knowledge graph and temporal transformer for early sepsis prediction in multi-center ICUs
arXiv:2603.15651v1 Announce Type: new
Abstract: The early prediction of sepsis in intensive care unit (ICU) patients is crucial for improving survival rates. However, the development of accurate predictive models is hampered by data fragmentation across healthcare institutions and the complex, temporal nature of medical data, all under stringent privacy constraints. To address these challenges, we propose a novel framework that uniquely integrates federated learning (FL) with a medical knowledge graph and a temporal transformer model, enhanced by meta-learning capabilities. Our approach enables collaborative model training across multiple hospitals without sharing raw patient data, thereby preserving privacy. The model leverages a knowledge graph to incorporate structured medical relationships and employs a temporal transformer to capture long-range dependencies in clinical time-series data. A model-agnostic meta-learning (MAML) strategy is further incorporated to facilitate rapid adaptation of the global model to local data distributions. Evaluated on the MIMIC-IV and eICU datasets, our method achieves an area under the curve (AUC) of 0.956, which represents a 22.4% improvement over conventional centralized models and a 12.7% improvement over standard federated learning, demonstrating strong predictive capability for sepsis. This work presents a reliable and privacy-preserving solution for multi-center collaborative early warning of sepsis.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
The Comprehension-Gated Agent Economy: A Robustness-First Architecture for AI Economic Agency
arXiv:2603.15639v1 Announce Type: new
Abstract: AI agents are increasingly granted economic agency (executing trades, managing budgets, negotiating contracts, and spawning sub-agents), yet current frameworks gate this agency on capability benchmarks that are empirically uncorrelated with operational robustness. We introduce the Comprehension-Gated Agent Economy (CGAE), a formal architecture in which an agent's economic permissions are upper-bounded by a verified comprehension function derived from adversarial robustness audits. The gating mechanism operates over three orthogonal robustness dimensions: constraint compliance (measured by CDCT), epistemic integrity (measured by DDFT), and behavioral alignment (measured by AGT), with intrinsic hallucination rates serving as a cross-cutting diagnostic. We define a weakest-link gate function that maps robustness vectors to discrete economic tiers, and prove three properties of the resulting system: (1) bounded economic exposure, ensuring maximum financial liability is a function of verified robustness; (2) incentive-compatible robustness investment, showing rational agents maximize profit by improving robustness rather than scaling capability alone; and (3) monotonic safety scaling, demonstrating that aggregate system safety does not decrease as the economy grows. The architecture includes temporal decay and stochastic re-auditing mechanisms that prevent post-certification drift. CGAE provides the first formal bridge between empirical AI robustness evaluation and economic governance, transforming safety from a regulatory burden into a competitive advantage.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
Interpretable Context Methodology: Folder Structure as Agentic Architecture
arXiv:2603.16021v1 Announce Type: new
Abstract: Current approaches to AI agent orchestration typically involve building multi-agent frameworks that manage context passing, memory, error handling, and step coordination through code. These frameworks work well for complex, concurrent systems. But for sequential workflows where a human reviews output at each step, they introduce engineering overhead that the problem does not require. This paper presents Model Workspace Protocol (MWP), a method that replaces framework-level orchestration with filesystem structure. Numbered folders represent stages. Plain markdown files carry the prompts and context that tell a single AI agent what role to play at each step. Local scripts handle the mechanical work that does not need AI at all. The result is a system where one agent, reading the right files at the right moment, does the work that would otherwise require a multi-agent framework. This approach applies ideas from Unix pipeline design, modular decomposition, multi-pass compilation, and literate programming to the specific problem of structuring context for AI agents. The protocol is open source under the MIT license.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
DynaTrust: Defending Multi-Agent Systems Against Sleeper Agents via Dynamic Trust Graphs
arXiv:2603.15661v1 Announce Type: new
Abstract: Large Language Model-based Multi-Agent Systems (MAS) have demonstrated remarkable collaborative reasoning capabilities but introduce new attack surfaces, such as the sleeper agent, which behave benignly during routine operation and gradually accumulate trust, only revealing malicious behaviors when specific conditions or triggers are met. Existing defense works primarily focus on static graph optimization or hierarchical data management, often failing to adapt to evolving adversarial strategies or suffering from high false-positive rates (FPR) due to rigid blocking policies. To address this, we propose DynaTrust, a novel defense method against sleeper agents. DynaTrust models MAS as a dynamic trust graph~(DTG), and treats trust as a continuous, evolving process rather than a static attribute. It dynamically updates the trust of each agent based on its historical behaviors and the confidence of selected expert agents. Instead of simply blocking, DynaTrust autonomously restructures the graph to isolate compromised agents and restore task connectivity to ensure the usability of MAS. To assess the effectiveness of DynaTrust, we evaluate it on mixed benchmarks derived from AdvBench and HumanEval. The results demonstrate that DynaTrust outperforms the state-of-the-art method AgentShield by increasing the defense success rate by 41.7%, achieving rates exceeding 86% under adversarial conditions. Furthermore, it effectively balances security with utility by significantly reducing FPR, ensuring uninterrupted system operations through graph adaptation.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Frequency Matters: Fast Model-Agnostic Data Curation for Pruning and Quantization
arXiv:2603.16105v1 Announce Type: new
Abstract: Post-training model compression is essential for enhancing the portability of Large Language Models (LLMs) while preserving their performance. While several compression approaches have been proposed, less emphasis has been placed on selecting the most suitable set of data (the so-called \emph{calibration data}) for finding the compressed model configuration. The choice of calibration data is a critical step in preserving model capabilities both intra- and inter-tasks. In this work, we address the challenge of identifying high-performance calibration sets for both pruning and quantization by analyzing intrinsic data properties rather than model-specific signals. We introduce \texttt{\textbf{ZipCal}}, a model-agnostic data curation strategy that maximizes lexical diversity based on Zipfian power laws. Experiments demonstrate that our method consistently outperforms standard uniform random sampling across various pruning benchmarks. Notably, it also performs on par, in terms of downstream performance, with a state-of-the-art method that relies on model perplexity. The latter becomes prohibitively expensive at large-scale models and datasets, while \texttt{\textbf{ZipCal}} is on average $\sim$240$\times$ faster due to its tractable linear complexity\footnote{We make the code and the experiments available at https://anonymous.4open.science/r/zipcal-71CD/.}.
Fonte: arXiv cs.CL
MLOps/Systems • Score 85
Quantum-Secure-By-Construction (QSC): A Paradigm Shift For Post-Quantum Agentic Intelligence
arXiv:2603.15668v1 Announce Type: new
Abstract: As agentic artificial intelligence systems scale across globally distributed and long lived infrastructures, secure and policy compliant communication becomes a fundamental systems challenge. This challenge grows more serious in the quantum era, where the cryptographic assumptions built into today's AI deployments may not remain valid over their operational lifetime. Here, we introduce quantum secure by construction, or QSC, as a design paradigm that treats quantum secure communication as a core architectural property of agentic AI systems rather than an upgrade added later. We realize QSC through a runtime adaptive security model that combines post quantum cryptography, quantum random number generation, and quantum key distribution to secure interactions among autonomous agents operating across heterogeneous cloud, edge, and inter organizational environments. The approach is cryptographically pluggable and guided by policy, allowing the system to adjust its security posture according to infrastructure availability, regulatory constraints, and performance needs. QSC contributes a governance aware orchestration layer that selects and combines link specific cryptographic protections across the full agent lifecycle, including session bootstrap, inter agent coordination, tool invocation, and memory access. Through system level analysis and empirical evaluation, we examine the trade offs between classical and quantum secure mechanisms and show that QSC can reduce the operational complexity and cost of introducing quantum security into deployed agentic AI systems. These results position QSC as a foundational paradigm for post quantum agentic intelligence and establish a principled pathway for designing globally interoperable, resilient, and future ready intelligent systems.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
IRAM-Omega-Q: A Computational Architecture for Uncertainty Regulation in Artificial Agents
arXiv:2603.16020v1 Announce Type: new
Abstract: Artificial agents can achieve strong task performance while remaining opaque with respect to internal regulation, uncertainty management, and stability under stochastic perturbation. We present IRAM-Omega-Q, a computational architecture that models internal regulation as closed-loop control over a quantum-like state representation. The framework uses density matrices instrumentally as abstract state descriptors, enabling direct computation of entropy, purity, and coherence-related metrics without invoking physical quantum processes. A central adaptive gain is updated continuously to maintain a target uncertainty regime under noise. Using systematic parameter sweeps, fixed-seed publication-mode simulations, and susceptibility-based phase-diagram analysis, we identify reproducible critical boundaries in regulation-noise space. We further show that alternative control update orderings, interpreted as perception-first and action-first architectures, induce distinct stability regimes under identical external conditions. These results support uncertainty regulation as a concrete architectural principle for artificial agents and provide a formal setting for studying stability, control, and order effects in cognitively inspired AI systems. The framework is presented as a technical model of adaptive regulation dynamics in artificial agents. It makes no claims regarding phenomenological consciousness, and the quantum-like formalism is used strictly as a mathematical representation for structured uncertainty and state evolution.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
An Agentic Evaluation Framework for AI-Generated Scientific Code in PETSc
arXiv:2603.15976v1 Announce Type: new
Abstract: While large language models have significantly accelerated scientific code generation, comprehensively evaluating the generated code remains a major challenge. Traditional benchmarks reduce evaluation to test-case matching, an approach insufficient for library code in HPC where solver selection, API conventions, memory management, and performance are just as critical as functional correctness. To address this gap, we introduce petscagent-bench, an agentic framework built on an agents-evaluating-agents paradigm. Instead of relying on static scripts, petscagent-bench deploys a tool-augmented evaluator agent that compiles, executes, and measures code produced by a separate model-under-test agent, orchestrating a 14-evaluator pipeline across five scoring categories: correctness, performance, code quality, algorithmic appropriateness, and library-specific conventions. Because the agents communicate through standardized protocols (A2A and MCP), the framework enables black-box evaluation of any coding agent without requiring access to its source code. We demonstrate the framework on a benchmark suite of realistic problems using the PETSc library for HPC. Our empirical analysis of frontier models reveals that while current models generate readable, well-structured code, they consistently struggle with library-specific conventions that traditional pass/fail metrics completely miss.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
POaaS: Minimal-Edit Prompt Optimization as a Service to Lift Accuracy and Cut Hallucinations on On-Device sLLMs
arXiv:2603.16045v1 Announce Type: new
Abstract: Small language models (sLLMs) are increasingly deployed on-device, where imperfect user prompts--typos, unclear intent, or missing context--can trigger factual errors and hallucinations. Existing automatic prompt optimization (APO) methods were designed for large cloud LLMs and rely on search that often produces long, structured instructions; when executed under an on-device constraint where the same small model must act as optimizer and solver, these pipelines can waste context and even hurt accuracy. We propose POaaS, a minimal-edit prompt optimization layer that routes each query to lightweight specialists (Cleaner, Paraphraser, Fact-Adder) and merges their outputs under strict drift and length constraints, with a conservative skip policy for well-formed prompts. Under a strict fixed-model setting with Llama-3.2-3B-Instruct and Llama-3.1-8B-Instruct, POaaS improves both task accuracy and factuality while representative APO baselines degrade them, and POaaS recovers up to +7.4% under token deletion and mixup. Overall, per-query conservative optimization is a practical alternative to search-heavy APO for on-device sLLMs.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning
arXiv:2603.15914v1 Announce Type: new
Abstract: AI tools and agents are reshaping how researchers work, from proving theorems to training neural networks. Yet for many, it remains unclear how these tools fit into everyday research practice. This paper is a practical guide to AI-assisted research in mathematics and machine learning: We discuss how researchers can use modern AI systems productively, where these systems help most, and what kinds of guardrails are needed to use them responsibly. It is organized into three parts: (I) a five-level taxonomy of AI integration, (II) an open-source framework that, through a set of methodological rules formulated as agent prompts, turns CLI coding agents (e.g., Claude Code, Codex CLI, OpenCode) into autonomous research assistants, and (III) case studies from deep learning and mathematics. The framework runs inside a sandboxed container, works with any frontier LLM through existing CLI agents, is simple enough to install and use within minutes, and scales from personal-laptop prototyping to multi-node, multi-GPU experimentation across compute clusters. In practice, our longest autonomous session ran for over 20 hours, dispatching independent experiments across multiple nodes without human intervention. We stress that our framework is not intended to replace the researcher in the loop, but to augment them. Our code is publicly available at https://github.com/ZIB-IOL/The-Agentic-Researcher.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
VQKV: High-Fidelity and High-Ratio Cache Compression via Vector-Quantization
arXiv:2603.16435v1 Announce Type: new
Abstract: The growing context length of Large Language Models (LLMs) enlarges the Key-Value (KV) cache, limiting deployment in resource-limited environments. Prior training-free approaches for KV cache compression typically rely on low-rank approximation or scalar quantization, which fail to simultaneously achieve high compression ratios and high reconstruction fidelity. We propose VQKV, a novel, training-free method introducing vector quantization (VQ) to obtain highly compressed KV representations while preserving high model fidelity, allowing for the representation of thousands of floating-point values with just a few integer indices. As a result, VQKV achieves an 82.8\% compression ratio on LLaMA3.1-8B while retaining 98.6\% of the baseline performance on LongBench and enabling 4.3x longer generation length on the same memory footprint.
Fonte: arXiv cs.CL
MLOps/Systems • Score 85
Data-driven configuration tuning of glmnet for balancing accuracy and computational efficiency
arXiv:2602.17922v2 Announce Type: replace-cross
Abstract: The glmnet package in R is widely used for lasso estimation because of its computational efficiency. Despite its popularity, glmnet occasionally yields solutions that deviate substantially from the true ones because of the inappropriate default configuration of the algorithm. The accuracy of the obtained solutions can be improved by appropriately tuning the configuration. However, such improvements typically increase computational time, resulting in a tradeoff between accuracy and computational efficiency. Therefore, a systematic approach is required to determine the appropriate configuration. To address this need, we propose a unified data-driven framework specifically designed to optimize the configuration by balancing solution path accuracy and computational cost. Specifically, we generate a large-scale training dataset by measuring the accuracy and computation time of glmnet. Using this dataset, we construct neural networks to predict accuracy and computation time from data characteristics and configuration. For a new dataset, the proposed framework uses the trained networks to explore the configuration space and derive a Pareto front that represents the tradeoff between accuracy and computational cost. This front enables automatic selection of the configuration that maximizes accuracy under a user-specified time constraint. The proposed method is implemented in the R package glmnetconf, available at https://github.com/Shuhei-Muroya/glmnetconf.git.
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
Adaptive regularization parameter selection for high-dimensional inverse problems: A Bayesian approach with Tucker low-rank constraints
arXiv:2603.16066v1 Announce Type: new
Abstract: This paper introduces a novel variational Bayesian method that integrates Tucker decomposition for efficient high-dimensional inverse problem solving. The method reduces computational complexity by transforming variational inference from a high-dimensional space to a lower-dimensional core tensor space via Tucker decomposition. A key innovation is the introduction of per-mode precision parameters, enabling adaptive regularization for anisotropic structures. For instance, in directional image deblurring, learned parameters align with physical anisotropy, applying stronger regularization to critical directions (e.g., row vs. column axes). The method further estimates noise levels from data, eliminating reliance on prior knowledge of noise parameters (unlike conventional benchmarks such as the discrepancy principle (DP)). Experimental evaluations across 2D deblurring, 3D heat conduction, and Fredholm integral equations demonstrate consistent improvements in quantitative metrics (PSNR, SSIM) and qualitative visualizations (error maps, precision parameter trends) compared to L-curve criterion, generalized cross-validation (GCV), unbiased predictive risk estimator (UPRE), and DP. The approach scales to problems with 110,000 variables and outperforms existing methods by 0.73-2.09 dB in deblurring tasks and 6.75 dB in 3D heat conduction. Limitations include sensitivity to rank selection in Tucker decomposition and the need for theoretical analysis. Future work will explore automated rank selection and theoretical guarantees. This method bridges Bayesian theory and scalable computation, offering practical solutions for large-scale inverse problems in imaging, remote sensing, and scientific computing.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Exact and general decoupled solutions of the LMC Multitask Gaussian Process model
arXiv:2310.12032v3 Announce Type: replace-cross
Abstract: The Linear Model of Co-regionalization (LMC) is a very general multitask gaussian process model for regression or classification. While its expressiveness and conceptual simplicity are appealing, naive implementations have cubic complexity in the product (number of datapoints $\times$ number of tasks), making approximations mandatory for most applications. However, recent work has shown that in some settings the latent processes of the model can be decoupled, leading to a complexity that is only linear in the number of said processes. We here extend these results, showing from the most general assumptions that the only condition necessary to an efficient exact computation of the LMC is a mild hypothesis on the noise model. We introduce a full parametrization of the resulting \emph{projected LMC} model, enabling its efficient optimization. The effectiveness of this approach is assessed through synthetic and real-data experiments, testing in particular the behavior of its underlying noise model restriction.\\ Overall, the projected LMC appears as a competitive and simpler alternative to state-of-the art multitask gaussian process models. It greatly facilitates some computations such as training data updates or leave-one-out cross-validation, and is more interpretable, for it gives access to its low-dimensional quantities and to their explicit relation with the full-dimensional data. These qualities could facilitate the adoption by various industries of entire classes of methodologies, notably multitask bayesian optimization.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
Tackling Over-smoothing on Hypergraphs: A Ricci Flow-guided Neural Diffusion Approach
arXiv:2603.15696v1 Announce Type: new
Abstract: Hypergraph neural networks (HGNNs) have demonstrated strong capabilities in modeling complex higher-order relationships. However, existing HGNNs often suffer from over-smoothing as the number of layers increases and lack effective control over message passing among nodes. Inspired by the theory of Ricci flow in differential geometry, we theoretically establish that introducing discrete Ricci flow into hypergraph structures can effectively regulate node feature evolution and thereby alleviate over-smoothing. Building on this insight, we propose Ricci Flow-guided Hypergraph Neural Diffusion(RFHND), a novel message passing paradigm for hypergraphs guided by discrete Ricci flow. Specifically, RFHND is based on a PDE system that describes the continuous evolution of node features on hypergraphs and adaptively regulates the rate of information diffusion at the geometric level, preventing feature homogenization and producing high-quality node representations. Experimental results show that RFHND significantly outperforms existing methods across multiple benchmark datasets and demonstrates strong robustness, while also effectively mitigating over-smoothing.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Deriving Hyperparameter Scaling Laws via Modern Optimization Theory
arXiv:2603.15958v1 Announce Type: new
Abstract: Hyperparameter transfer has become an important component of modern large-scale training recipes. Existing methods, such as muP, primarily focus on transfer between model sizes, with transfer across batch sizes and training horizons often relying on empirical scaling rules informed by insights from timescale preservation, quadratic proxies, and continuous-time approximations. We study hyperparameter scaling laws for modern first-order optimizers through the lens of recent convergence bounds for methods based on the Linear Minimization Oracle (LMO), a framework that includes normalized SGD, signSGD (approximating Adam), and Muon. Treating bounds in recent literature as a proxy and minimizing them across different tuning regimes yields closed-form power-law schedules for learning rate, momentum, and batch size as functions of the iteration or token budget. Our analysis, holding model size fixed, recovers most insights and observations from the literature under a unified and principled perspective, with clear directions open for future research. Our results draw particular attention to the interaction between momentum and batch-size scaling, suggesting that optimal performance may be achieved with several scaling strategies.
Fonte: arXiv cs.LG
Evaluation/Benchmarks • Score 85
CUBE: A Standard for Unifying Agent Benchmarks
arXiv:2603.15798v1 Announce Type: new
Abstract: The proliferation of agent benchmarks has created critical fragmentation that threatens research productivity. Each new benchmark requires substantial custom integration, creating an "integration tax" that limits comprehensive evaluation. We propose CUBE (Common Unified Benchmark Environments), a universal protocol standard built on MCP and Gym that allows benchmarks to be wrapped once and used everywhere. By separating task, benchmark, package, and registry concerns into distinct API layers, CUBE enables any compliant platform to access any compliant benchmark for evaluation, RL training, or data generation without custom integration. We call on the community to contribute to the development of this standard before platform-specific implementations deepen fragmentation as benchmark production accelerates through 2026.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
EngGPT2: Sovereign, Efficient and Open Intelligence
arXiv:2603.16430v1 Announce Type: new
Abstract: EngGPT2-16B-A3B is the latest iteration of Engineering Group's Italian LLM and it's built to be a Sovereign, Efficient and Open model. EngGPT2 is trained on 2.5 trillion tokens - less than Qwen3's 36T or Llama3's 15T - and delivers performance on key benchmarks, including MMLU-Pro, GSM8K, IFEval and HumanEval, comparable to dense models in the 8B-16B range, while requiring one-fifth to half of the inference power, and between one-tenth to one-sixth of the training data and consequent needed training power. Designed as a trained-from-scratch Mixture-of-Experts (MoE) architecture, EngGPT2 features 16 billion parameters with 3 billion active per inference, with expert sizes positioned between those used in GPT-OSS and Qwen3. Approximately 25% of its training corpus consists of Italian-language data, to deliver strong capabilities for European and Italian NLP tasks among models of similar scale. This efficiency aims to position EngGPT2 as a key contributor to the growing portfolio of open-weight European models, combining performance and efficiency with full alignment to the EU AI Act. EngGPT2 is also a single model capable of multiple reasoning modes: non-reasoning, reasoning in Italian or English, and turbo-reasoning (a concise, bullet-point style reasoning available in both languages designed for real-time reasoning use cases). EngGPT2 aims to set a new standard for resource-conscious, high-performance LLMs tailored to European and Italian contexts.
Fonte: arXiv cs.CL
MLOps/Systems • Score 85
Resilience Meets Autonomy: Governing Embodied AI in Critical Infrastructure
arXiv:2603.15885v1 Announce Type: new
Abstract: Critical infrastructure increasingly incorporates embodied AI for monitoring, predictive maintenance, and decision support. However, AI systems designed to handle statistically representable uncertainty struggle with cascading failures and crisis dynamics that exceed their training assumptions. This paper argues that Embodied AIs resilience depends on bounded autonomy within a hybrid governance architecture. We outline four oversight modes and map them to critical infrastructure sectors based on task complexity, risk level, and consequence severity. Drawing on the EU AI Act, ISO safety standards, and crisis management research, we argue that effective governance requires a structured allocation of machine capability and human judgement.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
Holographic Invariant Storage: Design-Time Safety Contracts via Vector Symbolic Architectures
arXiv:2603.13558v1 Announce Type: new
Abstract: We introduce Holographic Invariant Storage (HIS), a protocol that assembles known properties of bipolar Vector Symbolic Architectures into a design-time safety contract for LLM context-drift mitigation. The contract provides three closed-form guarantees evaluable before deployment: single-signal recovery fidelity converging to $1/\sqrt{2} \approx 0.707$ (regardless of noise depth or content), continuous-noise robustness $2\Phi(1/\sigma) - 1$, and multi-signal capacity degradation $\approx\sqrt{1/(K+1)}$. These bounds, validated by Monte Carlo simulation ($n = 1{,}000$), enable a systems engineer to budget recovery fidelity and codebook capacity at design time -- a property no timer or embedding-distance metric provides. A pilot behavioral experiment (four LLMs, 2B--7B, 720 trials) confirms that safety re-injection improves adherence at the 2B scale; full results are in an appendix.
Fonte: arXiv stat.ML
Multimodal • Score 85
Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs
arXiv:2603.13292v1 Announce Type: new
Abstract: Multimodal Large Language Models (MLLMs) pose critical safety challenges, as they are susceptible not only to adversarial attacks such as jailbreaking but also to inadvertently generating harmful content for benign users. While internal safety alignment via Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) is a primary mitigation strategy, current methods often face a safety-utility trade-off: they either refuse benign queries out of excessive caution or overlook latent risks in cross-modal interactions. To resolve this, we introduce Pragma-VL, an end-to-end alignment algorithm that enables MLLMs to pragmatically arbitrate between safety and helpfulness. First, we enhance visual risk perception with a novel cold-start SFT stage. This is achieved by applying risk-aware clustering to the visual encoder and using an interleaved dataset of risk descriptions and high-quality data. Second, we introduce a theoretically-guaranteed reward model that leverages synergistic learning. We train it with a novel data augmentation method that assigns dynamic weights based on the queries, enabling contextual arbitration between safety and helpfulness. Extensive experiments show that Pragma-VL effectively balances safety and helpfulness, outperforming baselines by 5% to 20% on most multimodal safety benchmarks while preserving its general capabilities in areas such as mathematics and knowledge reasoning.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
Your Code Agent Can Grow Alongside You with Structured Memory
arXiv:2603.13258v1 Announce Type: new
Abstract: While "Intent-oriented programming" (or "Vibe Coding") redefines software engineering, existing code agents remain tethered to static code snapshots. Consequently, they struggle to model the critical information embedded in the temporal evolution of projects, failing to leverage the "reasoning trajectories" implicit in past successful practices. This limitation results in rigid behavioral logic and a lack of autonomous adaptability, ultimately hindering their ability to tackle complex, repository-level problems. To bridge this static-dynamic mismatch, we propose MemCoder, a framework designed to enable continual human-AI co-evolution. MemCoder first structures historical human experience to distill latent intent-to-code mappings from past commits. It then employs a self-refinement mechanism driven by verification feedback to correct agent behavior in real-time. Crucially, an experience self-internalization mechanism is introduced to crystallize human-validated solutions into long-term knowledge, thereby supporting sustained evolution. Experimental results on SWE-bench Verified demonstrate that MemCoder not only achieves State-of-the-Art (SOTA) performance but also delivers a 9.4% improvement in resolved rate over the general foundation model DeepSeek-V3.2. These findings indicate that equipping agents with the capability to co-evolve with humans via project history and real-time feedback effectively unlocks the potential of general models in complex software engineering tasks.
Fonte: arXiv cs.LG
MLOps/Systems • Score 90
A Robust Framework for Secure Cardiovascular Risk Prediction: An Architectural Case Study of Differentially Private Federated Learning
arXiv:2603.13293v1 Announce Type: new
Abstract: Accurate cardiovascular risk prediction is crucial for preventive healthcare; however, the development of robust Artificial Intelligence (AI) models is hindered by the fragmentation of clinical data across institutions due to stringent privacy regulations. This paper presents a comprehensive architectural case study validating the engineering robustness of FedCVR, a privacy-preserving Federated Learning framework applied to heterogeneous clinical networks. Rather than proposing a new theoretical optimizer, this work focuses on a systems engineering analysis to quantify the operational trade-offs of server-side adaptive optimization under utility-prioritized Differential Privacy (DP). By conducting a rigorous stress test in a high-fidelity synthetic environment calibrated against real-world datasets (Framingham, Cleveland), we systematically evaluate the system's resilience to statistical noise. The validation results demonstrate that integrating server-side momentum as a temporal denoiser allows the architecture to achieve a stable F1-score of 0.84 and an Area Under the Curve (AUC) of 0.96, statistically outperforming standard stateless baselines. Our findings confirm that server-side adaptivity is a structural prerequisite for recovering clinical utility under realistic privacy budgets, providing a validated engineering blueprint for secure multi-institutional collaboration.
Fonte: arXiv cs.LG
Applications • Score 85
MS2MetGAN: Latent-space adversarial training for metabolite-spectrum matching in MS/MS database search
arXiv:2603.13342v1 Announce Type: new
Abstract: Database search is a widely used approach for identifying metabolites from tandem mass spectra (MS/MS). In this strategy, an experimental spectrum is matched against a user-specified database of candidate metabolites, and candidates are ranked such that true metabolite-spectrum matches receive the highest scores. Machine-learning methods have been widely incorporated into database-search-based identification tools and have substantially improved performance. To further improve identification accuracy, we propose a new framework for generating negative training samples. The framework first uses autoencoders to learn latent representations of metabolite structures and MS/MS spectra, thereby recasting metabolite-spectrum matching as matching between latent vectors. It then uses a GAN to generate latent vectors of decoy metabolites and constructs decoy metabolite-spectrum matches as negative samples for training. Experimental results show that our tool, MS2MetGAN, achieves better overall performance than existing metabolite identification methods.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Language-Guided Token Compression with Reinforcement Learning in Large Vision-Language Models
arXiv:2603.13394v1 Announce Type: new
Abstract: Large Vision-Language Models (LVLMs) incur substantial inference costs due to the processing of a vast number of visual tokens. Existing methods typically struggle to model progressive visual token reduction as a multi-step decision process with sequential dependencies and often rely on hand-engineered scoring rules that lack adaptive optimization for complex reasoning trajectories. To overcome these limitations, we propose TPRL, a reinforcement learning framework that learns adaptive pruning trajectories through language-guided sequential optimization tied directly to end-task performance. We formulate visual token pruning as a sequential decision process with explicit state transitions and employ a self-supervised autoencoder to compress visual tokens into a compact state representation for efficient policy learning. The pruning policy is initialized through learning from demonstrations and subsequently fine-tuned using Proximal Policy Optimization (PPO) to jointly optimize task accuracy and computational efficiency. Our experimental results demonstrate that TPRL removes up to 66.7\% of visual tokens and achieves up to a 54.2\% reduction in FLOPs during inference while maintaining a near-lossless average accuracy drop of only 0.7\%. Code is released at \href{https://github.com/MagicVicCoder/TPRL}{\textcolor{mypink}{https://github.com/MagicVicCoder/TPRL}}.
Fonte: arXiv cs.CV
RL • Score 85
FastODT: A tree-based framework for efficient continual learning
arXiv:2603.13276v1 Announce Type: new
Abstract: Machine learning models deployed in real-world settings must operate under evolving data distributions and constrained computational resources. This challenge is particularly acute in non-stationary domains such as energy time series, weather monitoring, and environmental sensing. To remain effective, models must support adaptability, continuous learning, and long-term knowledge retention. This paper introduces a oblivious tree-based model with Hoeffding bound controlling its growth. It seamlessly integrates rapid learning and inference with efficient memory management and robust knowledge preservation, thus allowing for online learning. Extensive experiments across energy and environmental sensing time-series benchmarks demonstrate that the proposed framework achieves performance competitive with, and in several cases surpassing, existing online and batch learning methods, while maintaining superior computational efficiency. Collectively, these results demonstrate that the proposed approach fulfills the core objectives of adaptability, continual updating, and efficient retraining without full model retraining. The framework provides a scalable and resource-aware foundation for deployment in real-world non-stationary environments where resources are constrained and sustained adaptation is essential.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
COT-FM: Cluster-wise Optimal Transport Flow Matching
arXiv:2603.13395v1 Announce Type: new
Abstract: We introduce COT-FM, a general framework that reshapes the probability path in Flow Matching (FM) to achieve faster and more reliable generation. FM models often produce curved trajectories due to random or batchwise couplings, which increase discretization error and reduce sample quality. COT-FM fixes this by clustering target samples and assigning each cluster a dedicated source distribution obtained by reversing pretrained FM models. This divide-and-conquer strategy yields more accurate local transport and significantly straighter vector fields, all without changing the model architecture. As a plug-and-play approach, COT-FM consistently accelerates sampling and improves generation quality across 2D datasets, image generation benchmarks, and robotic manipulation tasks.
Fonte: arXiv cs.CV
Vision • Score 85
DDS-UDA: Dual-Domain Synergy for Unsupervised Domain Adaptation in Joint Segmentation of Optic Disc and Optic Cup
arXiv:2603.13345v1 Announce Type: new
Abstract: Convolutional neural networks (CNNs) have achieved exciting performance in joint segmentation of optic disc and optic cup on single-institution datasets. However, their clinical translation is hindered by two major challenges: limited availability of large-scale, high-quality annotations and performance degradation caused by domain shift during deployment across heterogeneous imaging protocols and acquisition platforms. While unsupervised domain adaptation (UDA) provides a way to mitigate these limitations, most existing approaches do not address cross-domain interference and intra-domain generalization within a unified framework. In this paper, we present the Dual-Domain Synergy UDA (DDS-UDA), a novel UDA framework that comprises two key modules. First, a bi-directional cross-domain consistency regularization module is enforced to mitigate cross-domain interference through feature-level semantic information exchange guided by a coarse-to-fine dynamic mask generator, suppressing noise propagation while preserving structural coherence. Second, a frequency-driven intra-domain pseudo label learning module is used to enhance intra-domain generalization by synthesizing spectral amplitude-mixed supervision signals, which ensures high-fidelity feature alignment across domains. Implemented within a teacher-student architecture, DDS-UDA disentangles domain-specific biases from domain-invariant feature-level representations, thereby achieving robust adaptation to heterogeneous imaging environments. We conduct a comprehensive evaluation of our proposed method on two multi-domain fundus image datasets, demonstrating that it outperforms several existing UDA based methods and therefore providing an effective way for optic disc and optic cup segmentation.
Fonte: arXiv cs.CV
Vision • Score 85
Taming Vision Priors for Data Efficient mmWave Channel Modeling
arXiv:2603.13383v1 Announce Type: new
Abstract: Accurately modeling millimeter-wave (mmWave) propagation is essential for real-time AR and autonomous systems. Differentiable ray tracing offers a physics-grounded solution but still facing deployment challenges due to its over-reliance on exhaustive channel measurements or brittle, hand-tuned scene models for material properties. We present VisRFTwin, a scalable and data-efficient digital-twin framework that integrates vision-derived material priors with differentiable ray tracing. Multi-view images from commodity cameras are processed by a frozen Vision-Language Model to extract dense semantic embeddings, which are translated into initial estimates of permittivity and conductivity for scene surfaces. These priors initialize a Sionna-based differentiable ray tracer, which rapidly calibrates material parameters via gradient descent with only a few dozen sparse channel soundings. Once calibrated, the association between vision features and material parameters is retained, enabling fast transfer to new scenarios without repeated calibration. Evaluations across three real-world scenarios, including office interiors, urban canyons, and dynamic public spaces show that VisRFTwin reduces channel measurement needs by up to 10$\times$ while achieving a 59% lower median delay spread error than pure data-driven deep learning methods.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Can We Trust LLMs on Memristors? Diving into Reasoning Ability under Non-Ideality
arXiv:2603.13725v1 Announce Type: new
Abstract: Memristor-based analog compute-in-memory (CIM) architectures provide a promising substrate for the efficient deployment of Large Language Models (LLMs), owing to superior energy efficiency and computational density. However, these architectures suffer from precision issues caused by intrinsic non-idealities of memristors. In this paper, we first conduct a comprehensive investigation into the impact of such typical non-idealities on LLM reasoning. Empirical results indicate that reasoning capability decreases significantly but varies for distinct benchmarks. Subsequently, we systematically appraise three training-free strategies, including thinking mode, in-context learning, and module redundancy. We thus summarize valuable guidelines, i.e., shallow layer redundancy is particularly effective for improving robustness, thinking mode performs better under low noise levels but degrades at higher noise, and in-context learning reduces output length with a slight performance trade-off. Our findings offer new insights into LLM reasoning under non-ideality and practical strategies to improve robustness.
Fonte: arXiv cs.CL
RecSys • Score 85
EmDT: Embedding Diffusion Transformer for Tabular Data Generation in Fraud Detection
arXiv:2603.13566v1 Announce Type: new
Abstract: Imbalanced datasets pose a difficulty in fraud detection, as classifiers are often biased toward the majority class and perform poorly on rare fraudulent transactions. Synthetic data generation is therefore commonly used to mitigate this problem. In this work, we propose the Clustered Embedding Diffusion-Transformer (EmDT), a diffusion model designed to generate fraudulent samples. Our key innovation is to leverage UMAP clustering to identify distinct fraudulent patterns, and train a Transformer denoising network with sinusoidal positional embeddings to capture feature relationships throughout the diffusion process. Once the synthetic data has been generated, we employ a standard decision-tree-based classifier (e.g., XGBoost) for classification, as this type of model remains better suited to tabular datasets. Experiments on a credit card fraud detection dataset demonstrate that EmDT significantly improves downstream classification performance compared to existing oversampling and generative methods, while maintaining comparable privacy protection and preserving feature correlations present in the original data.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
Orla: A Library for Serving LLM-Based Multi-Agent Systems
arXiv:2603.13605v1 Announce Type: new
Abstract: We introduce Orla, a library for constructing and running LLM-based agentic systems. Modern agentic applications consist of workflows that combine multiple LLM inference steps, tool calls, and heterogeneous infrastructure. Today, developers typically build these systems by manually composing orchestration code with LLM serving engines and tool execution logic. Orla provides a general abstraction that separates request execution from workflow-level policy. It acts as a serving layer above existing LLM inference engines: developers define workflows composed of stages, while Orla manages how those stages are mapped, executed, and coordinated across models and backends. It provides agent-level control through three mechanisms: a stage mapper, which assigns each stage to an appropriate model and backend; a workflow orchestrator, which schedules stages and manages their resources and context; and a memory manager, which manages inference state such as the KV cache across workflow boundaries. We demonstrate Orla with a customer support workflow that exercises many of its capabilities. We evaluate Orla on two datasets, showing that stage mapping improves latency and cost compared to a single-model vLLM baseline, while workflow-level cache management reduces time-to-first-token.
Fonte: arXiv cs.AI
Privacy/Security/Fairness • Score 85
GroupGuard: A Framework for Modeling and Defending Collusive Attacks in Multi-Agent Systems
arXiv:2603.13940v1 Announce Type: new
Abstract: While large language model-based agents demonstrate great potential in collaborative tasks, their interactivity also introduces security vulnerabilities. In this paper, we propose and model group collusive attacks, a highly destructive threat in which multiple agents coordinate via sociological strategies to mislead the system. To address this challenge, we introduce GroupGuard, a training-free defense framework that employs a multi-layered defense strategy, including continuous graph-based monitoring, active honeypot inducement, and structural pruning, to identify and isolate collusive agents. Experimental results across five datasets and four topologies demonstrate that group collusive attacks increase the attack success rate by up to 15\% compared to individual attacks. GroupGuard consistently achieves high detection accuracy (up to 88\%) and effectively restores collaborative performance, providing a robust solution for securing multi-agent systems.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
High-Probability Bounds for SGD under the Polyak-Lojasiewicz Condition with Markovian Noise
arXiv:2603.14514v1 Announce Type: cross
Abstract: We present the first uniform-in-time high-probability bound for SGD under the PL condition, where the gradient noise contains both Markovian and martingale difference components. This significantly broadens the scope of finite-time guarantees, as the PL condition arises in many machine learning and deep learning models while Markovian noise naturally arises in decentralized optimization and online system identification problems. We further allow the magnitude of noise to grow with the function value, enabling the analysis of many practical sampling strategies. In addition to the high-probability guarantee, we establish a matching $1/k$ decay rate for the expected suboptimality. Our proof technique relies on the Poisson equation to handle the Markovian noise and a probabilistic induction argument to address the lack of almost-sure bounds on the objective. Finally, we demonstrate the applicability of our framework by analyzing three practical optimization problems: token-based decentralized linear regression, supervised learning with subsampling for privacy amplification, and online system identification.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
Selective Fine-Tuning of GPT Architectures for Parameter-Efficient Clinical Text Classification
arXiv:2603.14183v1 Announce Type: new
Abstract: The rapid expansion of electronic health record (EHR) systems has generated large volumes of unstructured clinical narratives that contain valuable information for disease identification, patient cohort discovery, and clinical decision support. Extracting structured knowledge from these free-text documents remains challenging because clinical language is highly specialized, labeled datasets are limited, and full fine-tuning of large pretrained language models can require substantial computational resources. Efficient adaptation strategies are therefore essential for practical clinical natural language processing applications. This study proposes a parameter-efficient selective fine-tuning framework for adapting GPT-2 to clinical text classification tasks. Instead of updating the entire pretrained model, the majority of network parameters are frozen, and only the final Transformer block, the final layer normalization module, and a lightweight classification head are updated during training. This design substantially reduces the number of trainable parameters while preserving the contextual representation capabilities learned during pretraining. The proposed approach is evaluated using radiology reports from the MIMIC-IV-Note dataset with automatically derived CheXpert-style labels. Experiments on 50,000 radiology reports demonstrate that selective fine-tuning achieves approximately 91% classification accuracy while updating fewer than 6% of the model parameters. Comparative experiments with head-only training and full-model fine-tuning show that the proposed method provides a favorable balance between predictive performance and computational efficiency. These results indicate that selective fine-tuning offers an efficient and scalable framework for clinical text classification.
Fonte: arXiv cs.CL
MLOps/Systems • Score 85
Automating Document Intelligence in Statutory City Planning
arXiv:2603.13245v1 Announce Type: new
Abstract: UK planning authorities face a legislative conflict between the Planning Act, which mandates public access to application documents, and the Data Protection Act, which requires protection of personal information. This situation creates a manually intensive workload for processing large document volumes, diverting planning officers to administrative tasks and creating legal compliance risks. This paper presents an integrated AI system designed to address these challenges. The system automates the identification and redaction of personal information, extracts key metadata from planning documents, and analyzes architectural drawings for specified features. It operates with an AI-in-the-Loop (AI2L) design, presenting all suggestions for review and confirmation by planning officers directly within their existing software; no action is committed without explicit human approval. The system is designed to improve its performance over time by learning from this human oversight through active learning prioritization rather than autoapproval. The system is currently being piloted at four diverse UK local authorities. The paper details the system design, the AI2L workflow, and the evaluation framework used in the pilot. Additionally, it describes a preliminary Return on Investment (ROI) model developed to quantify potential savings and secure partner participation. This work provides a case study on deploying AI to reduce administrative burden and manage compliance risk in a public sector environment.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Linear Predictability of Attention Heads in Large Language Models
arXiv:2603.13314v1 Announce Type: new
Abstract: Large language model (LLM) inference is increasingly bottlenecked by the Key-Value (KV) cache, yet the fine-grained structure of attention-head activations remains poorly understood. We show that pretrained Transformers exhibit a pervasive inter-head linear structure: for a given token, the Query, Key, and Value (QKV) vectors of an attention head can often be reconstructed as a linear combination of a small number of peer heads, typically within the same layer. Across Llama-3.1-8B, Falcon3-10B, OLMo-2-7B, and Qwen3-32B, just 2-5 reference heads recover many target heads with high fidelity (e.g., mean R^2 approx 0.76 for Keys on C4 with five references, and frequently R^2 > 0.85 on GSM8K). This predictability is learned rather than architectural: it is largely absent at random initialization, rises rapidly during pretraining as we track through OLMo-2 checkpoints, and is supported by a theoretical lower bound showing high mean-squared error for linear prediction at initialization. We further connect this emergence to increasing intra-layer alignment of Key projection subspaces. Finally, we exploit this redundancy for efficiency by caching only reference-head KV states and reconstructing the remaining heads on the fly via lightweight linear maps, achieving 2x KV-cache reduction with model-dependent accuracy trade-offs (4.5-5.5 percentage point average drop on Falcon3-10B and Qwen3-32B across five benchmarks, and larger drops on Llama-3.1-8B), and we find that reconstructing Keys is substantially less harmful than reconstructing Values.
Fonte: arXiv cs.LG
Applications • Score 85
Artificial intelligence-driven improvement of hospital logistics management resilience: a practical exploration based on H Hospital
arXiv:2603.13816v1 Announce Type: new
Abstract: Hospital logistics management faces growing pressure from internal operations and external emergencies, with artificial intelligence (AI) holding untapped potential to boost its resilience. This study explores AI's role in enhancing logistics resilience via a mixed-methods case study of H Hospital, combining 12 key informant interviews and a full survey of 151 logistics staff, with the PDCA cycle as the analytical framework. Thematic and quantitative analyses (hierarchical regression, structural equation modeling) were adopted for data analysis. Results showed 94.7% staff perceived AI application, with the strongest improvements in equipment maintenance (41.1%) and resource allocation (33.1%), but limited effects in emergency response (18.54%) and risk management (15.23%). AI integration positively correlated with logistics resilience (\b{eta}=0.642, p<0.001), with management system adaptability as a positive moderator (\b{eta}=0.208, p<0.01). The PDCA cycle fully mediated the AI-resilience relationship. We conclude AI effectively enhances logistics resilience, dependent on adaptive management systems and structured continuous improvement mechanisms. Targeted strategies are proposed to form an AI-driven closed-loop resilience mechanism, offering empirical guidance for AI-hospital logistics integration and resilient health system construction.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
SemantiCache: Efficient KV Cache Compression via Semantic Chunking and Clustered Merging
arXiv:2603.14303v1 Announce Type: new
Abstract: Existing KV cache compression methods generally operate on discrete tokens or non-semantic chunks. However, such approaches often lead to semantic fragmentation, where linguistically coherent units are disrupted, causing irreversible information loss and degradation in model performance. To address this, we introduce SemantiCache, a novel compression framework that preserves semantic integrity by aligning the compression process with the semantic hierarchical nature of language. Specifically, we first partition the cache into semantically coherent chunks by delimiters, which are natural semantic boundaries. Within each chunk, we introduce a computationally efficient Greedy Seed-Based Clustering (GSC) algorithm to group tokens into semantic clusters. These clusters are further merged into semantic cores, enhanced by a Proportional Attention mechanism that rebalances the reduced attention contributions of the merged tokens. Extensive experiments across diverse benchmarks and models demonstrate that SemantiCache accelerates the decoding stage of inference by up to 2.61 times and substantially reduces memory footprint, while maintaining performance comparable to the original model.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
RelayCaching: Accelerating LLM Collaboration via Decoding KV Cache Reuse
arXiv:2603.13289v1 Announce Type: new
Abstract: The increasing complexity of AI tasks has shifted the paradigm from monolithic models toward multi-agent large language model (LLM) systems. However, these collaborative architectures introduce a critical bottleneck: redundant prefill computation for shared content generated by previous agents, which significantly increases KV cache memory usage and time-to-first-token (TTFT). While various KV cache methods have been proposed to mitigate prefill redundancy, they either fail to maintain accuracy on agent-generated outputs or exhibit low reuse rates due to rigid constraints. We present RelayCaching, a training-free inference method that directly reuses decoding phase KV caches from previous agents in subsequent prefill phases. Our key insight is that KV caches for identical content are highly consistent across phases, while prefix-induced deviations are sparse and localized within a limited range of layers and token positions. By selectively recomputing KV caches at these positions, RelayCaching preserves model accuracy with minimal overhead, yielding a superior accuracy-efficiency trade-off over existing methods. Experiments on diverse collaborative LLM tasks spanning mathematical reasoning, general knowledge, and code generation demonstrate that RelayCaching achieves over 80% KV cache reuse, reduces TTFT by up to $4.7\times$ compared to the standard pipeline, all with negligible accuracy degradation.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
FineRMoE: Dimension Expansion for Finer-Grained Expert with Its Upcycling Approach
arXiv:2603.13364v1 Announce Type: new
Abstract: As revealed by the scaling law of fine-grained MoE, model performance ceases to be improved once the granularity of the intermediate dimension exceeds the optimal threshold, limiting further gains from single-dimension fine-grained design. To address this bottleneck, we propose FineRMoE (FineR-Grained MoE), an architecture that extends fine-grained expert design to both intermediate and output dimensions, aiming to enhance expert specialization beyond the single-dimension limit. We further introduce a bi-level sparse forward computation paradigm and a specialized routing mechanism to govern the activation. In addition, to obviate the prohibitive cost of training FineRMoE from scratch, we devise a generalized upcycling method to build FineRMoE in a cost-effective manner. Extensive experiments demonstrate the superior performance achieved by FineRMoE across ten standard benchmarks. Compared with the strongest baseline, FineRMoE achieves 6 times higher parameter efficiency, 281 times lower prefill latency, and 136 timese higher decoding throughput during inference.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
FedTreeLoRA: Reconciling Statistical and Functional Heterogeneity in Federated LoRA Fine-Tuning
arXiv:2603.13282v1 Announce Type: new
Abstract: Federated Learning (FL) with Low-Rank Adaptation (LoRA) has become a standard for privacy-preserving LLM fine-tuning. However, existing personalized methods predominantly operated under a restrictive Flat-Model Assumption: they addressed client-side \textit{statistical heterogeneity} but treated the model as a monolithic block, ignoring the \textit{functional heterogeneity} across LLM layers. We argue that these two statistical (horizontal) and functional (vertical) dimensions, are \textit{orthogonal in source yet coupled in interaction}, implying that the optimal depth of parameter sharing is functionally dependent on client similarity. To address this, we propose \textbf{FedTreeLoRA}, a framework employing tree-structured aggregation for fine-grained, layer-wise alignment. By dynamically constructing an aggregation hierarchy, FedTreeLoRA allows clients to share broad consensus on shallow `trunks' while progressively specializing on deep `branches'. Experiments on NLU and NLG benchmarks demonstrate that FedTreeLoRA significantly outperforms state-of-the-art methods by effectively reconciling generalization and personalization.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
Traffic and weather driven hybrid digital twin for bridge monitoring
arXiv:2603.14028v1 Announce Type: new
Abstract: A hybrid digital twin framework is presented for bridge condition monitoring using existing traffic cameras and weather APIs, reducing reliance on dedicated sensor installations. The approach is demonstrated on the Peace Bridge (99 years in service) under high traffic demand and harsh winter exposure. The framework fuses three near-real-time streams: YOLOv8 computer vision from a bridge-deck camera estimates vehicle counts, traffic density, and load proxies; a Lighthill--Whitham--Richards (LWR) model propagates density $\rho(x,t)$ and detects deceleration-driven shockwaves linked to repetitive loading and fatigue accumulation; and weather APIs provide deterioration drivers including temperature cycling, freeze-thaw activity, precipitation-related corrosion potential, and wind effects. Monte Carlo simulation quantifies uncertainty across traffic-environment scenarios, while Random Forest models map fused features to fatigue indicators and maintenance classification. The framework demonstrates utilizing existing infrastructure for cost-effective predictive maintenance of aging, high-traffic bridges in harsh climates.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks
arXiv:2603.14830v1 Announce Type: cross
Abstract: Dataset distillation, a training-aware data compression technique, has recently attracted increasing attention as an effective tool for mitigating costs of optimization and data storage. However, progress remains largely empirical. Mechanisms underlying the extraction of task-relevant information from the training process and the efficient encoding of such information into synthetic data points remain elusive. In this paper, we theoretically analyze practical algorithms of dataset distillation applied to the gradient-based training of two-layer neural networks with width $L$. By focusing on a non-linear task structure called multi-index model, we prove that the low-dimensional structure of the problem is efficiently encoded into the resulting distilled data. This dataset reproduces a model with high generalization ability for a required memory complexity of $\tilde{\Theta}$$(r^2d+L)$, where $d$ and $r$ are the input and intrinsic dimensions of the task. To the best of our knowledge, this is one of the first theoretical works that include a specific task structure, leverage its intrinsic dimensionality to quantify the compression rate and study dataset distillation implemented solely via gradient-based algorithms.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
StatePlane: A Cognitive State Plane for Long-Horizon AI Systems Under Bounded Context
arXiv:2603.13644v1 Announce Type: new
Abstract: Large language models (LLMs) and small language models (SLMs) operate under strict context window and key-value (KV) cache constraints, fundamentally limiting their ability to reason coherently over long interaction horizons. Existing approaches -- extended context windows, retrieval-augmented generation, summarization, or static documentation -- treat memory as static storage and fail to preserve decision-relevant state under long-running, multi-session tasks. We introduce StatePlane, a model-agnostic cognitive state plane that governs the formation, evolution, retrieval, and decay of episodic, semantic, and procedural state for AI systems operating under bounded context. Grounded in cognitive psychology and systems design, StatePlane formalizes episodic segmentation, selective encoding via information-theoretic constraints, goal-conditioned retrieval with intent routing, reconstructive state synthesis, and adaptive forgetting. We present a formal state model, KV-aware algorithms, security and governance mechanisms including write-path anti-poisoning, enterprise integration pathways, and an evaluation framework with six domain-specific benchmarks. StatePlane demonstrates that long-horizon intelligence can be achieved without expanding context windows or retraining models.
Fonte: arXiv cs.AI
RecSys • Score 88
Federated Personal Knowledge Graph Completion with Lightweight Large Language Models for Personalized Recommendations
arXiv:2603.13264v1 Announce Type: new
Abstract: Personalized recommendation increasingly relies on private user data, motivating approaches that can adapt to individuals without centralizing their information. We present Federated Targeted Recommendations with Evolving Knowledge graphs and Language Models (FedTREK-LM), a framework that unifies lightweight large language models (LLMs), evolving personal knowledge graphs (PKGs), federated learning (FL), and Kahneman-Tversky Optimization to enable scalable, decentralized personalization. By prompting LLMs with structured PKGs, FedTREK-LM performs context-aware reasoning for personalized recommendation tasks such as movie and recipe suggestions. Across three lightweight Qwen3 models (0.6B, 1.7B, 4B), FedTREK-LM consistently and substantially outperforms state-of-the-art KG completion and federated recommendation baselines (HAKE, KBGAT, and FedKGRec), achieving more than a 4x improvement in F1-score on the movie and food benchmarks. Our results further show that real user data is critical for effective personalization, as synthetic data degrades performance by up to 46%. Overall, FedTREK-LM offers a practical paradigm for adaptive, LLM-powered personalization that generalizes across decentralized, evolving user PKGs.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
ICaRus: Identical Cache Reuse for Efficient Multi Model Inference
arXiv:2603.13281v1 Announce Type: new
Abstract: Multi model inference has recently emerged as a prominent paradigm, particularly in the development of agentic AI systems. However, in such scenarios, each model must maintain its own Key-Value (KV) cache for the identical prompt, leading to substantial memory consumption. This explosive growth of KV caches forces LLM serving systems to evict previously stored caches, which in turn introduces significant recomputation overhead whenever the evicted caches are required again. Moreover, prefix caching is inherently infeasible across different models, forcing each model to recompute KV cache for the identical prompt, which leads to significant overhead. To alleviate these issues, we propose Identical Cache Reuse (ICaRus), a novel architecture that allows multiple models to share identical KV caches across all layers. ICaRus is based on the key observation that a decoder-only Transformer can be conceptually decomposed into a logical encoder, which generates KV caches, and a logical decoder, which predicts output tokens from the KV caches. ICaRus fine-tunes only the logical decoder while freezing the logical encoder, enabling multiple models to share an identical KV cache. This eliminates cache memory explosion and unexpected evictions while also allowing cross-model reuse of KV caches for new input tokens, thereby removing redundant recomputation in multi model inference achieving both efficiency and scalability. Moreover, by incorporating lightweight adapters such as LoRA, ICaRus parallelizes KV cache generation and next-token prediction during decoding. ICaRus achieves comparable accuracy to task-specific fine-tuned model across a diverse set of tasks, while allowing multiple specialized models to fully share KV caches. ICaRus achieves up to 11.1x lower P95 latency and 3.8x higher throughput in multi agent workflow with 8 different models, compared to conventional multi model system.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
PA-Net: Precipitation-Adaptive Mixture-of-Experts for Long-Tail Rainfall Nowcasting
arXiv:2603.13818v1 Announce Type: new
Abstract: Precipitation nowcasting is vital for flood warning, agricultural management, and emergency response, yet two bottlenecks persist: the prohibitive cost of modeling million-scale spatiotemporal tokens from multi-variate atmospheric fields, and the extreme long-tailed rainfall distribution where heavy-to-torrential events -- those of greatest societal impact -- constitute fewer than 0.1% of all samples. We propose the Precipitation-Adaptive Network (PA-Net), a Transformer framework whose computational budget is explicitly governed by rainfall intensity. Its core component, Precipitation-Adaptive MoE (PA-MoE), dynamically scales the number of activated experts per token according to local precipitation magnitude, channeling richer representational capacity toward the rare yet critical heavy-rainfall tail. A Dual-Axis Compressed Latent Attention mechanism factorizes spatiotemporal attention with convolutional reduction to manage massive context lengths, while an intensity-aware training protocol progressively amplifies learning signals from extreme-rainfall samples. Experiment on ERA5 demonstrate consistent improvements over state-of-the-art baselines, with particularly significant gains in heavy-rain and rainstorm regimes.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
DOVA: Deliberation-First Multi-Agent Orchestration for Autonomous Research Automation
arXiv:2603.13327v1 Announce Type: new
Abstract: Large language model (LLM) agents have demonstrated remarkable capabilities in tool use, reasoning, and code generation, yet single-agent systems exhibit fundamental limitations when confronted with complex research tasks demanding multi-source synthesis, adversarial verification, and personalized delivery. We present DOVA (Deep Orchestrated Versatile Agent), a multi-agent platform introducing three key innovations: (1) deliberation-first orchestration, where explicit meta-reasoning precedes tool invocation, informed by a persistent user model and entity-aware conversation context; (2) hybrid collaborative reasoning, a composable three-phase pipeline unifying ensemble diversity, blackboard transparency, and iterative refinement; and (3) adaptive multi-tiered thinking, a six-level token-budget allocation scheme that reduces inference cost by 40-60% on simple tasks while preserving deep reasoning capacity. We formalize the core algorithms, present an architectural ablation study across seven system configurations, and analyze the contribution of each component to answer confidence, source coverage, and token efficiency.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
Fundamental Limits of CSI Compression in FDD Massive MIMO
arXiv:2603.14325v1 Announce Type: cross
Abstract: Channel state information (CSI) feedback in frequency-division duplex (FDD) massive multiple-input multiple-output (MIMO) systems is fundamentally limited by the high dimensionality of wideband channels. In this paper, we model the stacked wideband CSI vector as a Gaussian-mixture source with a latent geometry state that represents different propagation environments. Each component corresponds to a locally stationary regime characterized by a correlated proper complex Gaussian distribution with its own covariance matrix. This representation captures the multimodal nature of practical CSI datasets while preserving the analytical tractability of Gaussian models. Motivated by this structure, we propose Gaussian-mixture transform coding (GMTC), a practical CSI feedback architecture that combines state inference with state-adaptive TC. The mixture parameters are learned offline from channel samples and stored as a shared statistical dictionary at both the user equipment (UE) and the base station. For each CSI realization, the UE identifies the most likely geometry state, encodes the corresponding label using a lossless source code, and compresses the CSI using the Karhunen-Loeve transform matched to that state. We further characterize the fundamental limits of CSI compression under this model by deriving analytical converse and achievability bounds on the rate-distortion (RD) function. A key structural result is that the optimal bit allocation across all mixture components is governed by a single global reverse-waterfilling level. Simulations on the COST2100 dataset show that GMTC significantly improves the RD tradeoff relative to neural transform coding approaches while requiring substantially smaller model memory and lower inference complexity. These results indicate that near-optimal CSI compression can be achieved through state-adaptive TC without relying on large neural encoders.
Fonte: arXiv stat.ML
MLOps/Systems • Score 85
Do Diffusion Models Dream of Electric Planes? Discrete and Continuous Simulation-Based Inference for Aircraft Design
arXiv:2603.13284v1 Announce Type: new
Abstract: In this paper, we generate conceptual engineering designs of electric vertical take-off and landing (eVTOL) aircraft. We follow the paradigm of simulation-based inference (SBI), whereby we look to learn a posterior distribution over the full eVTOL design space. To learn this distribution, we sample over discrete aircraft configurations (topologies) and their corresponding set of continuous parameters. Therefore, we introduce a hierarchical probabilistic model consisting of two diffusion models. The first model leverages recent work on Riemannian Diffusion Language Modeling (RDLM) and Unified World Models (UWMs) to enable us to sample topologies from a discrete and continuous space. For the second model we introduce a masked diffusion approach to sample the corresponding parameters conditioned on the topology. Our approach rediscovers known trends and governing physical laws in aircraft design, while significantly accelerating design generation.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Learning Retrieval Models with Sparse Autoencoders
arXiv:2603.13277v1 Announce Type: new
Abstract: Sparse autoencoders (SAEs) provide a powerful mechanism for decomposing the dense representations produced by Large Language Models (LLMs) into interpretable latent features. We posit that SAEs constitute a natural foundation for Learned Sparse Retrieval (LSR), whose objective is to encode queries and documents into high-dimensional sparse representations optimized for efficient retrieval. In contrast to existing LSR approaches that project input sequences into the vocabulary space, SAE-based representations offer the potential to produce more semantically structured, expressive, and language-agnostic features. Building on this insight, we introduce SPLARE, a method to train SAE-based LSR models. Our experiments, relying on recently released open-source SAEs, demonstrate that this technique consistently outperforms vocabulary-based LSR in multilingual and out-of-domain settings. SPLARE-7B, a multilingual retrieval model capable of producing generalizable sparse latent embeddings for a wide range of languages and domains, achieves top results on MMTEB's multilingual and English retrieval tasks. We also developed a 2B-parameter variant with a significantly lighter footprint.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
RFX-Fuse: Breiman and Cutler's Unified ML Engine + Native Explainable Similarity
arXiv:2603.13234v1 Announce Type: new
Abstract: Breiman and Cutler's original Random Forest was designed as a unified ML engine -- not merely an ensemble predictor. Their implementation included classification, regression, unsupervised learning, proximity-based similarity, outlier
detection, missing value imputation, and visualization -- capabilities that modern libraries like scikit-learn never implemented. RFX-Fuse (Random Forests X [X=compression] -- Forest Unified Learning and Similarity Engine) delivers
Breiman and Cutler's complete vision with native GPU/CPU support. Modern ML pipelines require 5+ separate tools -- XGBoost for prediction, FAISS for similarity, SHAP for explanations, Isolation Forest for outliers, custom code for
importance. RFX-Fuse provides a 1 to 2 model object alternative -- a single set of trees grown once. Novel Contributions: (1) Proximity Importance -- native explainable similarity: proximity measures that samples are similar;
proximity importance explains why. (2) Dataset-specific imputation validation for general tabular data -- ranking imputation methods by how real the imputed data looks, without ground truth labels.
Fonte: arXiv cs.LG
Vision • Score 85
Real-Time Monocular Scene Analysis for UAV in Outdoor Environments
arXiv:2603.13368v1 Announce Type: new
Abstract: In this thesis, we leverage monocular cameras on aerial robots to predict depth and semantic maps in low-altitude unstructured environments. We propose a joint deep-learning architecture, named Co-SemDepth, that can perform the two tasks accurately and rapidly, and validate its effectiveness on a variety of datasets. The training of neural networks requires an abundance of annotated data, and in the UAV field, the availability of such data is limited. We introduce a new synthetic dataset in this thesis, TopAir that contains images captured with a nadir view in outdoor environments at different altitudes, helping to fill the gap.
While using synthetic data for the training is convenient, it raises issues when shifting to the real domain for testing. We conduct an extensive analytical study to assess the effect of several factors on the synthetic-to-real generalization. Co-SemDepth and TaskPrompter models are used for comparison in this study. The results reveal a superior generalization performance for Co-SemDepth in depth estimation and for TaskPrompter in semantic segmentation. Also, our analysis allows us to determine which training datasets lead to a better generalization. Moreover, to help attenuate the gap between the synthetic and real domains, image style transfer techniques are explored on aerial images to convert from the synthetic to the realistic style. Cycle-GAN and Diffusion models are employed. The results reveal that diffusion models are better in the synthetic to real style transfer.
In the end, we focus on the marine domain and address its challenges. Co-SemDepth is trained on a collected synthetic marine data, called MidSea, and tested on both synthetic and real data. The results reveal good generalization performance of Co-SemDepth when tested on real data from the SMD dataset while further enhancement is needed on the MIT dataset.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
Efficient Federated Conformal Prediction with Group-Conditional Guarantee
arXiv:2603.14198v1 Announce Type: cross
Abstract: Deploying trustworthy AI systems requires principled uncertainty quantification. Conformal prediction (CP) is a widely used framework for constructing prediction sets with distribution-free coverage guarantees. In many practical settings, including healthcare, finance, and mobile sensing, the calibration data required for CP are distributed across multiple clients, each with its own local data distribution. In this federated setting, data can often be partitioned into, potentially overlapping, groups, which may reflect client-specific strata or cross-cutting attributes such as demographic or semantic categories. We propose group-conditional federated conformal prediction (GC-FCP), a novel protocol that provides group-conditional coverage guarantees. GC-FCP constructs mergeable, group-stratified coresets from local calibration scores, enabling clients to communicate compact weighted summaries that support efficient aggregation and calibration at the server. Experiments on synthetic and real-world datasets validate the performance of GC-FCP compared to centralized calibration baselines.
Fonte: arXiv stat.ML
NLP/LLMs • Score 95
FLUX: Data Worth Training On
arXiv:2603.13972v1 Announce Type: new
Abstract: Modern large language model training is no longer limited by data availability, but by the inability of existing preprocessing pipelines to simultaneously achieve massive scale and high data quality. Current approaches are forced to sacrifice one for the other: either aggressively filtering to improve quality at the cost of severe token loss, or retaining large volumes of data while introducing substantial noise. In this work, we introduce FLUX, a preprocessing pipeline specifically designed to break this long-standing trade-off by maximizing token retention while enforcing rigorous quality control. Models trained on FLUX-curated data consistently outperform prior methods. A 3B-parameter model trained on 60B tokens with FLUX achieves 32.14% MMLU accuracy, surpassing the previous state-of-the-art pipeline DCLM (31.98%) and significantly outperforming FineWeb (29.88%). FLUX achieves the same aggregate score as a model trained on DCLM data using only 39B tokens, resulting in a 34.4% reduction in training compute. At the data level, FLUX extracts 50B usable tokens from a single dump (CC-MAIN-2025-51), compared to 40B from DCLM (+25% retention). FLUX-Base yields 192B tokens, exceeding FineWeb's 170B while still maintaining superior quality. Overall, FLUX establishes a new state of the art in web-scale data preprocessing by demonstrating that high retention, strong quality control, and computational efficiency can be achieved simultaneously, redefining the limits of scalable dataset construction for modern language models.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
A Hierarchical End-of-Turn Model with Primary Speaker Segmentation for Real-Time Conversational AI
arXiv:2603.13379v1 Announce Type: new
Abstract: We present a real-time front-end for voice-based conversational AI to enable natural turn-taking in two-speaker scenarios by combining primary speaker segmentation with hierarchical End-of-Turn (EOT) detection. To operate robustly in multi-speaker environments, the system continuously identifies and tracks the primary user, ensuring that downstream EOT decisions are not confounded by background conversations. The tracked activity segments are fed to a hierarchical, causal EOT model that predicts the immediate conversational state by independently analyzing per-speaker speech features from both the primary speaker and the bot. Simultaneously, the model anticipates near-future states ($t{+}10/20/30$\,ms) through probabilistic predictions that are aware of the conversation partner's speech. Task-specific knowledge distillation compresses wav2vec~2.0 representations (768\,D) into a compact MFCC-based student (32\,D) for efficient deployment. The system achieves 82\% multi-class frame-level F1 and 70.6\% F1 on Backchannel detection, with 69.3\% F1 on a binary Final vs.\ Others task. On an end-to-end turn-detection benchmark, our model reaches 87.7\% recall vs.\ 58.9\% for Smart Turn~v3 while keeping a median detection latency of 36\,ms versus 800--1300\,ms. Despite using only 1.14\,M parameters, the proposed model matches or exceeds transformer-based baselines while substantially reducing latency and memory footprint, making it suitable for edge deployment.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Lipschitz-Based Robustness Certification Under Floating-Point Execution
arXiv:2603.13334v1 Announce Type: new
Abstract: Sensitivity-based robustness certification has emerged as a practical approach for certifying neural network robustness, including in settings that require verifiable guarantees. A key advantage of these methods is that certification is performed by concrete numerical computation (rather than symbolic reasoning) and scales efficiently with network size. However, as with the vast majority of prior work on robustness certification and verification, the soundness of these methods is typically proved with respect to a semantic model that assumes exact real arithmetic. In reality deployed neural network implementations execute using floating-point arithmetic. This mismatch creates a semantic gap between certified robustness properties and the behaviour of the executed system.
As motivating evidence, we exhibit concrete counterexamples showing that real arithmetic robustness guarantees can fail under floating-point execution, even for previously verified certifiers, with discrepancies becoming pronounced at lower-precision formats such as float16. We then develop a formal, compositional theory relating real arithmetic Lipschitz-based sensitivity bounds to the sensitivity of floating-point execution under standard rounding-error models, specialised to feed-forward neural networks with ReLU activations. We derive sound conditions for robustness under floating-point execution, including bounds on certificate degradation and sufficient conditions for the absence of overflow. We formalize the theory and its main soundness results, and implement an executable certifier based on these principles, which we empirically evaluate to demonstrate its practicality.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
APEX-Searcher: Augmenting LLMs' Search Capabilities through Agentic Planning and Execution
arXiv:2603.13853v1 Announce Type: new
Abstract: Retrieval-augmented generation (RAG), based on large language models (LLMs), serves as a vital approach to retrieving and leveraging external knowledge in various domain applications. When confronted with complex multi-hop questions, single-round retrieval is often insufficient for accurate reasoning and problem solving. To enhance search capabilities for complex tasks, most existing works integrate multi-round iterative retrieval with reasoning processes via end-to-end training. While these approaches significantly improve problem-solving performance, they are still faced with challenges in task reasoning and model training, especially ambiguous retrieval execution paths and sparse rewards in end-to-end reinforcement learning (RL) process, leading to inaccurate retrieval results and performance degradation. To address these issues, in this paper, we proposes APEX-Searcher, a novel Agentic Planning and Execution framework to augment LLM search capabilities. Specifically, we introduce a two-stage agentic framework that decouples the retrieval process into planning and execution: It first employs RL with decomposition-specific rewards to optimize strategic planning; Built on the sub-task decomposition, it then applies supervised fine-tuning on high-quality multi-hop trajectories to equip the model with robust iterative sub-task execution capabilities. Extensive experiments demonstrate that our proposed framework achieves significant improvements in both multi-hop RAG and task planning performances across multiple benchmarks.
Fonte: arXiv cs.CL
Multimodal • Score 85
FedUAF: Uncertainty-Aware Fusion with Reliability-Guided Aggregation for Multimodal Federated Sentiment Analysis
arXiv:2603.13291v1 Announce Type: new
Abstract: Multimodal sentiment analysis in federated learning environments faces significant challenges due to missing modalities, heterogeneous data distributions, and unreliable client updates. Existing federated approaches often struggle to maintain robust performance under these practical conditions. In this paper, we propose FedUAF, a unified multimodal federated learning framework that addresses these challenges through uncertainty-aware fusion and reliability-guided aggregation. FedUAF explicitly models modality-level uncertainty during local training and leverages client reliability to guide global aggregation, enabling effective learning under incomplete and noisy multimodal data. Extensive experiments on CMU-MOSI and CMU-MOSEI demonstrate that FedUAF consistently outperforms state-of-the-art federated baselines across various missing-modality patterns and Non-IID settings. Moreover, FedUAF exhibits superior robustness against noisy clients, highlighting its potential for real-world multimodal federated applications.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Enhanced Atrial Fibrillation Prediction in ESUS Patients with Hypergraph-based Pre-training
arXiv:2603.13297v1 Announce Type: new
Abstract: Atrial fibrillation (AF) is a major complication following embolic stroke of undetermined source (ESUS), elevating the risk of recurrent stroke and mortality. Early identification is clinically important, yet existing tools face limitations in accuracy, scalability, and cost. Machine learning (ML) offers promise but is hindered by small ESUS cohorts and high-dimensional medical features. To address these challenges, we introduce supervised and unsupervised hypergraph-based pre-training strategies to improve AF prediction in ESUS patients. We first pre-train hypergraph-based patient embedding models on a large stroke cohort (7,780 patients) to capture salient features and higher-order interactions. The resulting embeddings are transferred to a smaller ESUS cohort (510 patients), reducing feature dimensionality while preserving clinically meaningful information, enabling effective prediction with lightweight models. Experiments show that both pre-training approaches outperform traditional models trained on raw data, improving accuracy and robustness. This framework offers a scalable and efficient solution for AF risk prediction after stroke.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
Machine Learning Models to Identify Promising Nested Antiresonance Nodeless Fiber Designs
arXiv:2603.13302v1 Announce Type: new
Abstract: Hollow-core fibers offer superior loss and latency characteristics compared to solid-core alternatives, yet the geometric complexity of nested antiresonance nodeless fibers (NANFs) makes traditional optimization computationally prohibitive. We propose a high-efficiency, two-stage machine learning framework designed to identify high-performance NANF designs using minimal training data. The model employs a neural network (NN) classifier to filter for single-mode designs (suppression ratio $\ge$ 50 dB), followed by a regressor that predicts confinement loss (CL). By training on the common logarithm of the loss, the regressor overcomes the challenges of high dynamic range. Using a sparse data set of only 1,819 designs, all with CL greater or equal to 1 dB/km, the model successfully identified optimized designs with a confirmed CL of 0.25 dB/km. {This demonstrates the NN has captured underlying physical behavior and is able to extrapolate to regions of lower CL. We show that small data sets are sufficient for stable, high-accuracy performance prediction, enabling the exploration of design spaces as large as $14e6$ cases at a negligible computational cost compared to finite element methods.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Modular Neural Computer
arXiv:2603.13323v1 Announce Type: new
Abstract: This paper introduces the Modular Neural Computer (MNC), a memory-augmented neural architecture for exact algorithmic computation on variable-length inputs. The model combines an external associative memory of scalar cells, explicit read and write heads, a controller multi-layer perceptron (MLP), and a homogeneous set of functional MLP modules. Rather than learning an algorithm end to end from data, it realizes a given algorithm through analytically specified neural components with fixed interfaces and exact behavior. The control flow is represented inside the neural computation through one-hot module gates, where inactive modules are inhibited. Computation unfolds as a sequence of memory transformations generated by a fixed graph. The architecture is illustrated through three case studies: computing the minimum of an array, sorting an array in place, and executing A* search on a fixed problem instance. These examples show that algorithmic procedures can be compiled into modular neural components with external memory while preserving deterministic behavior and explicit intermediate state.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Knowledge Distillation for Large Language Models
arXiv:2603.13765v1 Announce Type: new
Abstract: We propose a resource-efficient framework for compressing large language models through knowledge distillation, combined with guided chain-of-thought reinforcement learning. Using Qwen 3B as the teacher and Qwen 0.5B as the student, we apply knowledge distillation across English Dolly-15k, Spanish Dolly-15k, and code BugNet and PyTorrent datasets, with hyperparameters tuned in the English setting to optimize student performance. Across tasks, the distilled student retains a substantial portion of the teacher's capability while remaining significantly smaller: 70% to 91% in English, up to 95% in Spanish, and up to 93.5% Rouge-L in code. For coding tasks, integrating chain-of-thought prompting with Group Relative Policy Optimization using CoT-annotated Codeforces data improves reasoning coherence and solution correctness compared to knowledge distillation alone. Post-training 4-bit weight quantization further reduces memory footprint and inference latency. These results show that knowledge distillation combined with chain-of-thought guided reinforcement learning can produce compact, efficient models suitable for deployment in resource-constrained settings.
Fonte: arXiv cs.CL
MLOps/Systems • Score 85
Post Training Quantization for Efficient Dataset Condensation
arXiv:2603.13346v1 Announce Type: new
Abstract: Dataset Condensation (DC) distills knowledge from large datasets into smaller ones, accelerating training and reducing storage requirements. However, despite notable progress, prior methods have largely overlooked the potential of quantization for further reducing storage costs. In this paper, we take the first step to explore post-training quantization in dataset condensation, demonstrating its effectiveness in reducing storage size while maintaining representation quality without requiring expensive training cost. However, we find that at extremely low bit-widths (e.g., 2-bit), conventional quantization leads to substantial degradation in representation quality, negatively impacting the networks trained on these data. To address this, we propose a novel \emph{patch-based post-training quantization} approach that ensures localized quantization with minimal loss of information. To reduce the overhead of quantization parameters, especially for small patch sizes, we employ quantization-aware clustering to identify similar patches and subsequently aggregate them for efficient quantization. Furthermore, we introduce a refinement module to align the distribution between original images and their dequantized counterparts, compensating for quantization errors. Our method is a plug-and-play framework that can be applied to synthetic images generated by various DC methods. Extensive experiments across diverse benchmarks including CIFAR-10/100, Tiny ImageNet, and ImageNet subsets demonstrate that our method consistently outperforms prior works under the same storage constraints. Notably, our method nearly \textbf{doubles the test accuracy} of existing methods at extreme compression regimes (e.g., 26.0\% $\rightarrow$ 54.1\% for DM at IPC=1), while operating directly on 2-bit images without additional distillation.
Fonte: arXiv cs.CV
Evaluation/Benchmarks • Score 85
When Your Model Stops Working: Anytime-Valid Calibration Monitoring
arXiv:2603.13156v1 Announce Type: cross
Abstract: Practitioners monitoring deployed probabilistic models face a fundamental trap: any fixed-sample test applied repeatedly over an unbounded stream will eventually raise a false alarm, even when the model remains perfectly stable. Existing methods typically lack formal error guarantees, conflate alarm time with changepoint location, and monitor indirect signals that do not fully characterize calibration. We present PITMonitor, an anytime-valid calibration-specific monitor that detects distributional shifts in probability integral transforms via a mixture e-process, providing Type I error control over an unbounded monitoring horizon as well as Bayesian changepoint estimation. On river's FriedmanDrift benchmark, PITMonitor achieves detection rates competitive with the strongest baselines across all three scenarios, although detection delay is substantially longer under local drift.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
Embedded Quantum Machine Learning in Embedded Systems: Feasibility, Hybrid Architectures, and Quantum Co-Processors
arXiv:2603.12540v1 Announce Type: new
Abstract: Embedded quantum machine learning (EQML) seeks to bring quantum machine learning (QML) capabilities to resource-constrained edge platforms such as IoT nodes, wearables, drones, and cyber-physical controllers. In 2026, EQML is technically feasible only in limited and highly experimental forms: (i) hybrid workflows where an embedded device performs sensing and classical processing while offloading a narrowly scoped quantum subroutine to a remote quantum processing unit (QPU) or nearby quantum appliance, and (ii) early-stage "embedded QPU" concepts in which a compact quantum co-processor is integrated with classical control hardware. A practical bridge is quantum-inspired machine learning and optimisation on classical embedded processors and FPGAs. This paper analyses feasibility from a circuits-and-systems perspective aligned with the academic community, formalises two implementation pathways, identifies the dominant barriers (latency, data encoding overhead, NISQ noise, tooling mismatch, and energy), and maps them to concrete engineering directions in interface design, control electronics, power management, verification, and security. We also argue that responsible deployment requires adversarial evaluation and governance practices that are increasingly necessary for edge AI systems.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Disentangled Latent Dynamics Manifold Fusion for Solving Parameterized PDEs
arXiv:2603.12676v1 Announce Type: new
Abstract: Generalizing neural surrogate models across different PDE parameters remains difficult because changes in PDE coefficients often make learning harder and optimization less stable. The problem becomes even more severe when the model must also predict beyond the training time range. Existing methods usually cannot handle parameter generalization and temporal extrapolation at the same time. Standard parameterized models treat time as just another input and therefore fail to capture intrinsic dynamics, while recent continuous-time latent methods often rely on expensive test-time auto-decoding for each instance, which is inefficient and can disrupt continuity across the parameterized solution space. To address this, we propose Disentangled Latent Dynamics Manifold Fusion (DLDMF), a physics-informed framework that explicitly separates space, time, and parameters. Instead of unstable auto-decoding, DLDMF maps PDE parameters directly to a continuous latent embedding through a feed-forward network. This embedding initializes and conditions a latent state whose evolution is governed by a parameter-conditioned Neural ODE. We further introduce a dynamic manifold fusion mechanism that uses a shared decoder to combine spatial coordinates, parameter embeddings, and time-evolving latent states to reconstruct the corresponding spatiotemporal solution. By modeling prediction as latent dynamic evolution rather than static coordinate fitting, DLDMF reduces interference between parameter variation and temporal evolution while preserving a smooth and coherent solution manifold. As a result, it performs well on unseen parameter settings and in long-term temporal extrapolation. Experiments on several benchmark problems show that DLDMF consistently outperforms state-of-the-art baselines in accuracy, parameter generalization, and extrapolation robustness.
Fonte: arXiv cs.LG
RL • Score 85
CALF: Communication-Aware Learning Framework for Distributed Reinforcement Learning
arXiv:2603.12543v1 Announce Type: new
Abstract: Distributed reinforcement learning policies face network delays, jitter, and packet loss when deployed across edge devices and cloud servers. Standard RL training assumes zero-latency interaction, causing severe performance degradation under realistic network conditions. We introduce CALF (Communication-Aware Learning Framework), which trains policies under realistic network models during simulation. Systematic experiments demonstrate that network-aware training substantially reduces deployment performance gaps compared to network-agnostic baselines. Distributed policy deployments across heterogeneous hardware validate that explicitly modelling communication constraints during training enables robust real-world execution. These findings establish network conditions as a major axis of sim-to-real transfer for Wi-Fi-like distributed deployments, complementing physics and visual domain randomisation.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Scaling Laws and Pathologies of Single-Layer PINNs: Network Width and PDE Nonlinearity
arXiv:2603.12556v1 Announce Type: new
Abstract: We establish empirical scaling laws for Single-Layer Physics-Informed Neural Networks on canonical nonlinear PDEs. We identify a dual optimization failure: (i) a baseline pathology, where the solution error fails to decrease with network width, even at fixed nonlinearity, falling short of theoretical approximation bounds, and (ii) a compounding pathology, where this failure is exacerbated by nonlinearity. We provide quantitative evidence that a simple separable power law is insufficient, and that the scaling behavior is governed by a more complex, non-separable relationship. This failure is consistent with the concept of spectral bias, where networks struggle to learn the high-frequency solution components that intensify with nonlinearity. We show that optimization, not approximation capacity, is the primary bottleneck, and propose a methodology to empirically measure these complex scaling effects.
Fonte: arXiv cs.LG
Applications • Score 85
Developing and evaluating a chatbot to support maternal health care
arXiv:2603.13168v1 Announce Type: new
Abstract: The ability to provide trustworthy maternal health information using phone-based chatbots can have a significant impact, particularly in low-resource settings where users have low health literacy and limited access to care. However, deploying such systems is technically challenging: user queries are short, underspecified, and code-mixed across languages, answers require regional context-specific grounding, and partial or missing symptom context makes safe routing decisions difficult.
We present a chatbot for maternal health in India developed through a partnership between academic researchers, a health tech company, a public health nonprofit, and a hospital. The system combines (1) stage-aware triage, routing high-risk queries to expert templates, (2) hybrid retrieval over curated maternal/newborn guidelines, and (3) evidence-conditioned generation from an LLM. Our core contribution is an evaluation workflow for high-stakes deployment under limited expert supervision. Targeting both component-level and end-to-end testing, we introduce: (i) a labeled triage benchmark (N=150) achieving 86.7% emergency recall, explicitly reporting the missed-emergency vs. over-escalation trade-off; (ii) a synthetic multi-evidence retrieval benchmark (N=100) with chunk-level evidence labels; (iii) LLM-as-judge comparison on real queries (N=781) using clinician-codesigned criteria; and (iv) expert validation. Our findings show that trustworthy medical assistants in multilingual, noisy settings require defense-in-depth design paired with multi-method evaluation, rather than any single model and evaluation method choice.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
AI Planning Framework for LLM-Based Web Agents
arXiv:2603.12710v1 Announce Type: new
Abstract: Developing autonomous agents for web-based tasks is a core challenge in AI. While Large Language Model (LLM) agents can interpret complex user requests, they often operate as black boxes, making it difficult to diagnose why they fail or how they plan. This paper addresses this gap by formally treating web tasks as sequential decision-making processes. We introduce a taxonomy that maps modern agent architectures to traditional planning paradigms: Step-by-Step agents to Breadth-First Search (BFS), Tree Search agents to Best-First Tree Search, and Full-Plan-in-Advance agents to Depth-First Search (DFS). This framework allows for a principled diagnosis of system failures like context drift and incoherent task decomposition. To evaluate these behaviors, we propose five novel evaluation metrics that assess trajectory quality beyond simple success rates. We support this analysis with a new dataset of 794 human-labeled trajectories from the WebArena benchmark. Finally, we validate our evaluation framework by comparing a baseline Step-by-Step agent against a novel Full-Plan-in-Advance implementation. Our results reveal that while the Step-by-Step agent aligns more closely with human gold trajectories (38% overall success), the Full-Plan-in-Advance agent excels in technical measures such as element accuracy (89%), demonstrating the necessity of our proposed metrics for selecting appropriate agent architectures based on specific application constraints.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
DART: Input-Difficulty-AwaRe Adaptive Threshold for Early-Exit DNNs
arXiv:2603.12269v1 Announce Type: cross
Abstract: Early-exit deep neural networks enable adaptive inference by terminating computation when sufficient confidence is achieved, reducing cost for edge AI accelerators in resource-constrained settings. Existing methods, however, rely on suboptimal exit policies, ignore input difficulty, and optimize thresholds independently. This paper introduces DART (Input-Difficulty-Aware Adaptive Threshold), a framework that overcomes these limitations. DART introduces three key innovations: (1) a lightweight difficulty estimation module that quantifies input complexity with minimal computational overhead, (2) a joint exit policy optimization algorithm based on dynamic programming, and (3) an adaptive coefficient management system. Experiments on diverse DNN benchmarks (AlexNet, ResNet-18, VGG-16) demonstrate that DART achieves up to \textbf{3.3$\times$} speedup, \textbf{5.1$\times$} lower energy, and up to \textbf{42\%} lower average power compared to static networks, while preserving competitive accuracy. Extending DART to Vision Transformers (LeViT) yields power (5.0$\times$) and execution-time (3.6$\times$) gains but also accuracy loss (up to 17 percent), underscoring the need for transformer-specific early-exit mechanisms. We further introduce the Difficulty-Aware Efficiency Score (DAES), a novel multi-objective metric, under which DART achieves up to a 14.8 improvement over baselines, highlighting superior accuracy, efficiency, and robustness trade-offs.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
On Using Machine Learning to Early Detect Catastrophic Failures in Marine Diesel Engines
arXiv:2603.12733v1 Announce Type: new
Abstract: Catastrophic failures of marine engines imply severe loss of functionality and destroy or damage the systems irreversibly. Being sudden and often unpredictable events, they pose a severe threat to navigation, crew, and passengers. The abrupt nature makes early detection the only effective countermeasure. However, research has concentrated on modeling the gradual degradation of components, with limited attention to sudden and anomalous phenomena. This work proposes a new method for early detection of catastrophic failures. Based on real data from a failed engine, the approach evaluates the derivatives of the deviation between actual sensor readings and expected values of engine variables. Predictions are obtained by a Random Forest, which is the most suitable Machine Learning algorithm among the tested ones. Traditional methods focus on deviations of monitored signals, whereas the proposed approach employs the derivatives of the deviations to provide earlier indications of abnormal dynamics, and to alert that a rapid and dangerous event is breaking out within the system. The method allows the detection of anomalies before measurements reach critical thresholds and alarms are triggered, which is the common method in industry. Consequently, operators can be warned in advance and shut down the engine, then prevent damage and unexpected power loss. Moreover, they have the time to safely change the ship route and avoid potential obstacles. Simulation results conf irm the effectiveness of the proposed approach in anticipating occurrence of catastrophic failures. Validation on real-world data further reinforces the robustness and practical applicability of the method. It is worth noting that data acquisition to train the predictive algorithm is not a problem, since a Deep Learning-based data augmentation procedure is used.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimization
arXiv:2603.12933v1 Announce Type: new
Abstract: Large Language Model (LLM)-driven Multi-Agent Systems (MAS) have demonstrated strong capability in complex reasoning and tool use, and heterogeneous agent pools further broaden the quality--cost trade-off space. Despite these advances, real-world deployment is often constrained by high inference cost, latency, and limited transparency, which hinders scalable and efficient routing. Existing routing strategies typically rely on expensive LLM-based selectors or static policies, and offer limited controllability for semantic-aware routing under dynamic loads and mixed intents, often resulting in unstable performance and inefficient resource utilization. To address these limitations, we propose AMRO-S, an efficient and interpretable routing framework for Multi-Agent Systems (MAS). AMRO-S models MAS routing as a semantic-conditioned path selection problem, enhancing routing performance through three key mechanisms: First, it leverages a supervised fine-tuned (SFT) small language model for intent inference, providing a low-overhead semantic interface for each query; second, it decomposes routing memory into task-specific pheromone specialists, reducing cross-task interference and optimizing path selection under mixed workloads; finally, it employs a quality-gated asynchronous update mechanism to decouple inference from learning, optimizing routing without increasing latency. Extensive experiments on five public benchmarks and high-concurrency stress tests demonstrate that AMRO-S consistently improves the quality--cost trade-off over strong routing baselines, while providing traceable routing evidence through structured pheromone patterns.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Structured Distillation for Personalized Agent Memory: 11x Token Reduction with Retrieval Preservation
arXiv:2603.13017v1 Announce Type: new
Abstract: Long conversations with an AI agent create a simple problem for one user: the history is useful, but carrying it verbatim is expensive. We study personalized agent memory: one user's conversation history with an agent, distilled into a compact retrieval layer for later search. Each exchange is compressed into a compound object with four fields (exchange_core, specific_context, thematic room_assignments, and regex-extracted files_touched). The searchable distilled text averages 38 tokens per exchange. Applied to 4,182 conversations (14,340 exchanges) from 6 software engineering projects, the method reduces average exchange length from 371 to 38 tokens, yielding 11x compression. We evaluate whether personalized recall survives that compression using 201 recall-oriented queries, 107 configurations spanning 5 pure and 5 cross-layer search modes, and 5 LLM graders (214,519 consensus-graded query-result pairs). The best pure distilled configuration reaches 96% of the best verbatim MRR (0.717 vs 0.745). Results are mechanism-dependent. All 20 vector search configurations remain non-significant after Bonferroni correction, while all 20 BM25 configurations degrade significantly (effect sizes |d|=0.031-0.756). The best cross-layer setup slightly exceeds the best pure verbatim baseline (MRR 0.759). Structured distillation compresses single-user agent memory without uniformly sacrificing retrieval quality. At 1/11 the context cost, thousands of exchanges fit within a single prompt while the verbatim source remains available for drill-down. We release the implementation and analysis pipeline as open-source software.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Detecting Miscitation on the Scholarly Web through LLM-Augmented Text-Rich Graph Learning
arXiv:2603.12290v1 Announce Type: cross
Abstract: Scholarly web is a vast network of knowledge connected by citations. However, this system is increasingly compromised by miscitation, where references do not support or even contradict the claims they are cited for. Current miscitation detection methods, which primarily rely on semantic similarity or network anomalies, struggle to capture the nuanced relationship between a citation's context and its place in the wider network. While large language models (LLMs) offer powerful capabilities in semantic reasoning for this task, their deployment is hindered by hallucination risks and high computational costs. In this work, we introduce LLM-Augmented Graph Learning-based Miscitation Detector (LAGMiD), a novel framework that leverages LLMs for deep semantic reasoning over citation graphs and distills this knowledge into graph neural networks (GNNs) for efficient and scalable miscitation detection. Specifically, LAGMiD introduces an evidence-chain reasoning mechanism, which uses chain-of-thought prompting, to perform multi-hop citation tracing and assess semantic fidelity. To reduce LLM inference costs, we design a knowledge distillation method aligning GNN embeddings with intermediate LLM reasoning states. A collaborative learning strategy further routes complex cases to the LLM while optimizing the GNN for structure-based generalization. Experiments on three real-world benchmarks show that LAGMiD achieves state-of-the-art miscitation detection with significantly reduced inference cost.
Fonte: arXiv cs.AI
NLP/LLMs • Score 95
98$\times$ Faster LLM Routing Without a Dedicated GPU: Flash Attention, Prompt Compression, and Near-Streaming for the vLLM Semantic Router
arXiv:2603.12646v1 Announce Type: new
Abstract: System-level routers that intercept LLM requests for safety classification, domain routing, and PII detection must be both fast and operationally lightweight: they should add minimal latency to every request, yet not require a dedicated GPU -- an expensive resource better used for LLM inference itself. When the router co-locates on the same GPU as vLLM serving instances, standard attention's $O(n^2)$ memory makes long-context classification (8K--32K tokens) impossible: at 8K tokens, three concurrent classifiers need ${\sim}$4.5\,GB for attention masks alone, far exceeding the memory left by vLLM. We present three staged optimizations for the vLLM Semantic Router, benchmarked on AMD Instinct MI300X, that solve both the latency and the memory problem. \emph{Stage~1}: a custom CK Flash Attention operator for ONNX Runtime on ROCm reduces attention memory from $O(n^2)$ to $O(n)$ and end-to-end (E2E) latency from 4{,}918\,ms to 127\,ms (\textbf{38.7$\times$}), enabling 8K--32K tokens where SDPA OOMs. \emph{Stage~2}: classical NLP prompt compression (TextRank, position weighting, TF-IDF, and novelty scoring) reduces all inputs to ${\sim}$512 tokens without neural inference, capping both latency and GPU memory at a constant regardless of original prompt length (E2E 127$\to$62\,ms, \textbf{2.0$\times$}). \emph{Stage~3}: near-streaming body processing with adaptive chunking and zero-copy JSON eliminates serialization overhead (E2E 62$\to$50\,ms, \textbf{1.2$\times$}). Cumulatively: \textbf{98$\times$} improvement (4{,}918\,ms to 50\,ms), 16K-token routing in 108\,ms, and a total router GPU footprint under 800\,MB -- small enough to share a GPU with LLM serving and removing the need for a dedicated accelerator. Stage~1 targets AMD ROCm (NVIDIA GPUs already have FlashAttention via cuDNN); Stages~2 and~3 are hardware-agnostic.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
Using a Human-AI Teaming Approach to Create and Curate Scientific Datasets with the SCILIRE System
arXiv:2603.12638v1 Announce Type: new
Abstract: The rapid growth of scientific literature has made manual extraction of structured knowledge increasingly impractical. To address this challenge, we introduce SCILIRE, a system for creating datasets from scientific literature. SCILIRE has been designed around Human-AI teaming principles centred on workflows for verifying and curating data. It facilitates an iterative workflow in which researchers can review and correct AI outputs. Furthermore, this interaction is used as a feedback signal to improve future LLM-based inference. We evaluate our design using a combination of intrinsic benchmarking outcomes together with real-world case studies across multiple domains. The results demonstrate that SCILIRE improves extraction fidelity and facilitates efficient dataset creation.
Fonte: arXiv cs.CL
MLOps/Systems • Score 85
AI Model Modulation with Logits Redistribution
arXiv:2603.12755v1 Announce Type: new
Abstract: Large-scale models are typically adapted to meet the diverse requirements of model owners and users. However, maintaining multiple specialized versions of the model is inefficient. In response, we propose AIM, a novel model modulation paradigm that enables a single model to exhibit diverse behaviors to meet the specific end requirements. AIM enables two key modulation modes: utility and focus modulations. The former provides model owners with dynamic control over output quality to deliver varying utility levels, and the latter offers users precise control to shift model's focused input features. AIM introduces a logits redistribution strategy that operates in a training data-agnostic and retraining-free manner. We establish a formal foundation to ensure AIM's regulation capability, based on the statistical properties of logits ordering via joint probability distributions. Our evaluation confirms AIM's practicality and versatility for Al model modulation, with tasks spanning image classification, semantic segmentation and text generation, and prevalent architectures including ResNet, SegFormer and Llama.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Adaptive Vision-Language Model Routing for Computer Use Agents
arXiv:2603.12823v1 Announce Type: new
Abstract: Computer Use Agents (CUAs) translate natural-language instructions into Graphical User Interface (GUI) actions such as clicks, keystrokes, and scrolls by relying on a Vision-Language Model (VLM) to interpret screenshots and predict grounded tool calls. However, grounding accuracy varies dramatically across VLMs, while current CUA systems typically route every action to a single fixed model regardless of difficulty. We propose \textbf{Adaptive VLM Routing} (AVR), a framework that inserts a lightweight semantic routing layer between the CUA orchestrator and a pool of VLMs. For each tool call, AVR estimates action difficulty from multimodal embeddings, probes a small VLM to measure confidence, and routes the action to the cheapest model whose predicted accuracy satisfies a target reliability threshold. For \textit{warm} agents with memory of prior UI interactions, retrieved context further narrows the capability gap between small and large models, allowing many actions to be handled without escalation. We formalize routing as a cost--accuracy trade-off, derive a threshold-based policy for model selection, and evaluate AVR using ScreenSpot-Pro grounding data together with the OpenClaw agent routing benchmark. Across these settings, AVR projects inference cost reductions of up to 78\% while staying within 2 percentage points of an all-large-model baseline. When combined with the Visual Confused Deputy guardrail, AVR also escalates high-risk actions directly to the strongest available model, unifying efficiency and safety within a single routing framework. Materials are also provided Model, benchmark, and code: https://github.com/vllm-project/semantic-router.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
AVION: Aerial Vision-Language Instruction from Offline Teacher to Prompt-Tuned Network
arXiv:2603.12659v1 Announce Type: new
Abstract: Adapting vision-language models to remote sensing imagery remains challenging due to two key factors: limited semantic coverage in textual representations and insufficient adaptability of visual features. These issues are particularly significant in aerial scenes, which involve various visual appearances and fine-grained object distinctions. We propose AVION, a knowledge distillation framework tailored for remote sensing adaptation of vision-language models. The teacher module constructs semantically rich textual prototypes by collecting descriptions from a large language model and verifying validity using remote sensing image features. The student module integrates lightweight and learnable prompts into both vision and language encoders, guided by the teacher to align embeddings and their cross-modal relationships. Once trained, the student operates independently during inference. Experiments on six optical remote sensing benchmarks show that AVION improves few-shot classification and base-class accuracy without degrading generalization to novel categories. It also enhances mean recall for cross-modal retrieval, with minimal additional trainable parameters.
Fonte: arXiv cs.CV
Theory/Optimization • Score 85
No More DeLuLu: Physics-Inspired Kernel Networks for Geometrically-Grounded Neural Computation
arXiv:2603.12276v1 Announce Type: new
Abstract: We introduce the yat-product, a kernel operator combining quadratic alignment with inverse-square proximity. We prove it is a Mercer kernel, analytic, Lipschitz on bounded domains, and self-regularizing, admitting a unique RKHS embedding. Neural Matter Networks (NMNs) use yat-product as the sole non-linearity, replacing conventional linear-activation-normalization blocks with a single geometrically-grounded operation. This architectural simplification preserves universal approximation while shifting normalization into the kernel itself via the denominator, rather than relying on separate normalization layers. Empirically, NMN-based classifiers match linear baselines on MNIST while exhibiting bounded prototype evolution and superposition robustness. In language modeling, Aether-GPT2 achieves lower validation loss than GPT-2 with a comparable parameter budget while using yat-based attention and MLP blocks. Our framework unifies kernel learning, gradient stability, and information geometry, establishing NMNs as a principled alternative to conventional neural architectures.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Federated Hierarchical Clustering with Automatic Selection of Optimal Cluster Numbers
arXiv:2603.12684v1 Announce Type: new
Abstract: Federated Clustering (FC) is an emerging and promising solution in exploring data distribution patterns from distributed and privacy-protected data in an unsupervised manner. Existing FC methods implicitly rely on the assumption that clients are with a known number of uniformly sized clusters. However, the true number of clusters is typically unknown, and cluster sizes are naturally imbalanced in real scenarios. Furthermore, the privacy-preserving transmission constraints in federated learning inevitably reduce usable information, making the development of robust and accurate FC extremely challenging. Accordingly, we propose a novel FC framework named Fed-$k^*$-HC, which can automatically determine an optimal number of clusters $k^*$ based on the data distribution explored through hierarchical clustering. To obtain the global data distribution for $k^*$ determination, we let each client generate micro-subclusters. Their prototypes are then uploaded to the server for hierarchical merging. The density-based merging design allows exploring clusters of varying sizes and shapes, and the progressive merging process can self-terminate according to the neighboring relationships among the prototypes to determine $k^*$. Extensive experiments on diverse datasets demonstrate the FC capability of the proposed Fed-$k^*$-HC in accurately exploring a proper number of clusters.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
When Drafts Evolve: Speculative Decoding Meets Online Learning
arXiv:2603.12617v1 Announce Type: new
Abstract: Speculative decoding has emerged as a widely adopted paradigm for accelerating large language model inference, where a lightweight draft model rapidly generates candidate tokens that are then verified in parallel by a larger target model. However, due to limited model capacity, drafts often struggle to approximate the target distribution, resulting in shorter acceptance lengths and diminished speedup. A key yet under-explored observation is that speculative decoding inherently provides verification feedback that quantifies the deviation between the draft and target models at no additional cost. This process naturally forms an iterative "draft commits-feedback provides-draft adapts" evolving loop, which precisely matches the online learning paradigm. Motivated by this connection, we propose OnlineSpec, a unified framework that systematically leverages interactive feedback to continuously evolve draft models. Grounded in dynamic regret minimization, we establish a formal link between online learning performance and speculative system's acceleration rate, and develop novel algorithms via modern online learning techniques, including optimistic online learning that adaptively reuses historical gradients as predictive update hints, and online ensemble learning that dynamically maintains multiple draft models. Our algorithms are equipped with theoretical justifications and improved acceleration rates, achieving up to 24% speedup over seven benchmarks and three foundation models.
Fonte: arXiv cs.LG
Vision • Score 85
Prompt-Driven Lightweight Foundation Model for Instance Segmentation-Based Fault Detection in Freight Trains
arXiv:2603.12624v1 Announce Type: new
Abstract: Accurate visual fault detection in freight trains remains a critical challenge for intelligent transportation system maintenance, due to complex operational environments, structurally repetitive components, and frequent occlusions or contaminations in safety-critical regions. Conventional instance segmentation methods based on convolutional neural networks and Transformers often suffer from poor generalization and limited boundary accuracy under such conditions. To address these challenges, we propose a lightweight self-prompted instance segmentation framework tailored for freight train fault detection. Our method leverages the Segment Anything Model by introducing a self-prompt generation module that automatically produces task-specific prompts, enabling effective knowledge transfer from foundation models to domain-specific inspection tasks. In addition, we adopt a Tiny Vision Transformer backbone to reduce computational cost, making the framework suitable for real-time deployment on edge devices in railway monitoring systems. We construct a domain-specific dataset collected from real-world freight inspection stations and conduct extensive evaluations. Experimental results show that our method achieves 74.6 $AP^{\text{box}}$ and 74.2 $AP^{\text{mask}}$ on the dataset, outperforming existing state-of-the-art methods in both accuracy and robustness while maintaining low computational overhead. This work offers a deployable and efficient vision solution for automated freight train inspection, demonstrating the potential of foundation model adaptation in industrial-scale fault diagnosis scenarios. Project page: https://github.com/MVME-HBUT/SAM_FTI-FDet.git
Fonte: arXiv cs.CV
Theory/Optimization • Score 85
From Garbage to Gold: A Data-Architectural Theory of Predictive Robustness
arXiv:2603.12288v1 Announce Type: new
Abstract: Tabular machine learning presents a paradox: modern models achieve state-of-the-art performance using high-dimensional (high-D), collinear, error-prone data, defying the "Garbage In, Garbage Out" mantra. To help resolve this, we synthesize principles from Information Theory, Latent Factor Models, and Psychometrics, clarifying that predictive robustness arises not solely from data cleanliness, but from the synergy between data architecture and model capacity. Partitioning predictor-space "noise" into "Predictor Error" and "Structural Uncertainty" (informational deficits from stochastic generative mappings), we prove that leveraging high-D sets of error-prone predictors asymptotically overcomes both types of noise, whereas cleaning a low-D set is fundamentally bounded by Structural Uncertainty. We demonstrate why "Informative Collinearity" (dependencies from shared latent causes) enhances reliability and convergence efficiency, and explain why increased dimensionality reduces the latent inference burden, enabling feasibility with finite samples. To address practical constraints, we propose "Proactive Data-Centric AI" to identify predictors that enable robustness efficiently. We also derive boundaries for Systematic Error Regimes and show why models that absorb "rogue" dependencies can mitigate assumption violations. Linking latent architecture to Benign Overfitting, we offer a first step towards a unified view of robustness to Outcome Error and predictor-space noise, while also delineating when traditional DCAI's focus on label cleaning remains powerful. By redefining data quality from item-level perfection to portfolio-level architecture, we provide a theoretical rationale for "Local Factories" -- learning from live, uncurated enterprise "data swamps" -- supporting a deployment paradigm shift from "Model Transfer" to "Methodology Transfer'' to overcome static generalizability limitations.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
A Geometrically-Grounded Drive for MDL-Based Optimization in Deep Learning
arXiv:2603.12304v1 Announce Type: new
Abstract: This paper introduces a novel optimization framework that fundamentally integrates the Minimum Description Length (MDL) principle into the training dynamics of deep neural networks. Moving beyond its conventional role as a model selection criterion, we reformulate MDL as an active, adaptive driving force within the optimization process itself. The core of our method is a geometrically-grounded cognitive manifold whose evolution is governed by a \textit{coupled Ricci flow}, enriched with a novel \textit{MDL Drive} term derived from first principles. This drive, modulated by the task-loss gradient, creates a seamless harmony between data fidelity and model simplification, actively compressing the internal representation during training. We establish a comprehensive theoretical foundation, proving key properties including the monotonic decrease of description length (Theorem~\ref{thm:convergence}), a finite number of topological phase transitions via a geometric surgery protocol (Theorems~\ref{thm:surgery}, \ref{thm:ultimate_fate}), and the emergence of universal critical behavior (Theorem~\ref{thm:universality}). Furthermore, we provide a practical, computationally efficient algorithm with $O(N \log N)$ per-iteration complexity (Theorem~\ref{thm:complexity}), alongside guarantees for numerical stability (Theorem~\ref{thm:stability}) and exponential convergence under convexity assumptions (Theorem~\ref{thm:convergence_rate}). Empirical validation on synthetic regression and classification tasks confirms the theoretical predictions, demonstrating the algorithm's efficacy in achieving robust generalization and autonomous model simplification. This work provides a principled path toward more autonomous, generalizable, and interpretable AI systems by unifying geometric deep learning with information-theoretic principles.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
ToolTree: Efficient LLM Agent Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional Pruning
arXiv:2603.12740v1 Announce Type: new
Abstract: Large Language Model (LLM) agents are increasingly applied to complex, multi-step tasks that require interaction with diverse external tools across various domains. However, current LLM agent tool planning methods typically rely on greedy, reactive tool selection strategies that lack foresight and fail to account for inter-tool dependencies. In this paper, we present ToolTree, a novel Monte Carlo tree search-inspired planning paradigm for tool planning. ToolTree explores possible tool usage trajectories using a dual-stage LLM evaluation and bidirectional pruning mechanism that enables the agent to make informed, adaptive decisions over extended tool-use sequences while pruning less promising branches before and after the tool execution. Empirical evaluations across both open-set and closed-set tool planning tasks on 4 benchmarks demonstrate that ToolTree consistently improves performance while keeping the highest efficiency, achieving an average gain of around 10\% compared to the state-of-the-art planning paradigm.
Fonte: arXiv cs.AI
RL • Score 85
Steve-Evolving: Open-World Embodied Self-Evolution via Fine-Grained Diagnosis and Dual-Track Knowledge Distillation
arXiv:2603.13131v1 Announce Type: new
Abstract: Open-world embodied agents must solve long-horizon tasks where the main bottleneck is not single-step planning quality but how interaction experience is organized and evolved. To this end, we present Steve-Evolving, a non-parametric self-evolving framework that tightly couples fine-grained execution diagnosis with dual-track knowledge distillation in a closed loop. The method follows three phases: Experience Anchoring, Experience Distillation, and Knowledge-Driven Closed-Loop Control. In detail, Experience Anchoring solidifies each subgoal attempt into a structured experience tuple with a fixed schema (pre-state, action, diagnosis-result, and post-state) and organizes it in a three-tier experience space with multi-dimensional indices (e.g., condition signatures, spatial hashing, and semantic tags) plus rolling summarization for efficient and auditable recall. To ensure sufficient information density for attribution, the execution layer provides compositional diagnosis signals beyond binary outcomes, including state-difference summaries, enumerated failure causes, continuous indicators, and stagnation/loop detection. Moreover, successful trajectories of Experience Distillation are generalized into reusable skills with explicit preconditions and verification criteria, while failures are distilled into executable guardrails that capture root causes and forbid risky operations at both subgoal and task granularities. Besides, Knowledge-Driven Closed-Loop Control retrieved skills and guardrails are injected into an LLM planner, and diagnosis-triggered local replanning updates the active constraints online, forming a continual evolution process without any model parameter updates. Experiments on the long-horizon suite of Minecraft MCU demonstrate consistent improvements over static-retrieval baselines.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Synthetic Data Generation for Brain-Computer Interfaces: Overview, Benchmarking, and Future Directions
arXiv:2603.12296v1 Announce Type: new
Abstract: Deep learning has achieved transformative performance across diverse domains, largely driven by the large-scale, high-quality training data. In contrast, the development of brain-computer interfaces (BCIs) is fundamentally constrained by the limited, heterogeneous, and privacy-sensitive neural recordings. Generating synthetic yet physiologically plausible brain signals has therefore emerged as a compelling way to mitigate data scarcity and enhance model capacity. This survey provides a comprehensive review of brain signal generation for BCIs, covering methodological taxonomies, benchmark experiments, evaluation metrics, and key applications. We systematically categorize existing generative algorithms into four types: knowledge-based, feature-based, model-based, and translation-based approaches. Furthermore, we benchmark existing brain signal generation approaches across four representative BCI paradigms to provide an objective performance comparison. Finally, we discuss the potentials and challenges of current generation approaches and prospect future research on accurate, data-efficient, and privacy-aware BCI systems. The benchmark codebase is publicized at https://github.com/wzwvv/DG4BCI.
Fonte: arXiv cs.LG
Multimodal • Score 85
Learning Pore-scale Multiphase Flow from 4D Velocimetry
arXiv:2603.12516v1 Announce Type: new
Abstract: Multiphase flow in porous media underpins subsurface energy and environmental technologies, including geological CO$_2$ storage and underground hydrogen storage, yet pore-scale dynamics in realistic three-dimensional materials remain difficult to characterize and predict. Here we introduce a multimodal learning framework that infers multiphase pore-scale flow directly from time-resolved four-dimensional (4D) micro-velocimetry measurements. The model couples a graph network simulator for Lagrangian tracer-particle motion with a 3D U-Net for voxelized interface evolution. The imaged pore geometry serves as a boundary constraint to the flow velocity and the multiphase interface predictions, which are coupled and updated iteratively at each time step. Trained autoregressively on experimental sequences in capillary-dominated conditions ($Ca\approx10^{-6}$), the learned surrogate captures transient, nonlocal flow perturbations and abrupt interface rearrangements (Haines jumps) over rollouts spanning seconds of physical time, while reducing hour-to-day--scale direct numerical simulations to seconds of inference. By providing rapid, experimentally informed predictions, the framework opens a route to ''digital experiments'' to replicate pore-scale physics observed in multiphase flow experiments, offering an efficient tool for exploring injection conditions and pore-geometry effects relevant to subsurface carbon and hydrogen storage.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
CA-HFP: Curvature-Aware Heterogeneous Federated Pruning with Model Reconstruction
arXiv:2603.12591v1 Announce Type: new
Abstract: Federated learning on heterogeneous edge devices requires personalized compression while preserving aggregation compatibility and stable convergence. We present Curvature-Aware Heterogeneous Federated Pruning (CA-HFP), a practical framework that enables each client perform structured, device-specific pruning guided by a curvature-informed significance score, and subsequently maps its compact submodel back into a common global parameter space via a lightweight reconstruction. We derive a convergence bound for federated optimization with multiple local SGD steps that explicitly accounts for local computation, data heterogeneity, and pruning-induced perturbations; from which a principled loss-based pruning criterion is derived. Extensive experiments on FMNIST, CIFAR-10, and CIFAR-100 using VGG and ResNet architectures under varying degrees of data heterogeneity demonstrate that CA-HFP preserves model accuracy while significantly reducing per-client computation and communication costs, outperforming standard federated training and existing pruning-based baselines.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
The Perfection Paradox: From Architect to Curator in AI-Assisted API Design
arXiv:2603.12475v1 Announce Type: cross
Abstract: Enterprise API design is often bottlenecked by the tension between rapid feature delivery and the rigorous maintenance of usability standards. We present an industrial case study evaluating an AI-assisted design workflow trained on API Improvement Proposals (AIPs). Through a controlled study with 16 industry experts, we compared AI-generated API specifications against human-authored ones. While quantitative results indicated AI superiority in 10 of 11 usability dimensions and an 87% reduction in authoring time, qualitative analysis revealed a paradox: experts frequently misidentified AI work as human (19% accuracy) yet described the designs as unsettlingly "perfect." We characterize this as a "Perfection Paradox" -- where hyper-consistency signals a lack of pragmatic human judgment. We discuss the implications of this perfection paradox, proposing a shift in the human designer's role from the "drafter" of specifications to the "curator" of AI-generated patterns.
Fonte: arXiv cs.AI
RL • Score 85
One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policies
arXiv:2603.12480v1 Announce Type: cross
Abstract: Generative flow and diffusion models provide the continuous, multimodal action distributions needed for high-precision robotic policies. However, their reliance on iterative sampling introduces severe inference latency, degrading control frequency and harming performance in time-sensitive manipulation. To address this problem, we propose the One-Step Flow Policy (OFP), a from-scratch self-distillation framework for high-fidelity, single-step action generation without a pre-trained teacher. OFP unifies a self-consistency loss to enforce coherent transport across time intervals, and a self-guided regularization to sharpen predictions toward high-density expert modes. In addition, a warm-start mechanism leverages temporal action correlations to minimize the generative transport distance. Evaluations across 56 diverse simulated manipulation tasks demonstrate that a one-step OFP achieves state-of-the-art results, outperforming 100-step diffusion and flow policies while accelerating action generation by over $100\times$. We further integrate OFP into the $\pi_{0.5}$ model on RoboTwin 2.0, where one-step OFP surpasses the original 10-step policy. These results establish OFP as a practical, scalable solution for highly accurate and low-latency robot control.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
LightMoE: Reducing Mixture-of-Experts Redundancy through Expert Replacing
arXiv:2603.12645v1 Announce Type: new
Abstract: Mixture-of-Experts (MoE) based Large Language Models (LLMs) have demonstrated impressive performance and computational efficiency. However, their deployment is often constrained by substantial memory demands, primarily due to the need to load numerous expert modules. While existing expert compression techniques like pruning or merging attempt to mitigate this, they often suffer from irreversible knowledge loss or high training overhead. In this paper, we propose a novel expert compression paradigm termed expert replacing, which replaces redundant experts with parameter-efficient modules and recovers their capabilities with low training costs. We find that even a straightforward baseline of this paradigm yields promising performance. Building on this foundation, we introduce LightMoE, a framework that enhances the paradigm by introducing adaptive expert selection, hierarchical expert construction, and an annealed recovery strategy. Experimental results show that LightMoE matches the performance of LoRA fine-tuning at a 30% compression ratio. Even under a more aggressive 50% compression rate, it outperforms existing methods and achieves average performance improvements of 5.6% across five diverse tasks. These findings demonstrate that LightMoE strikes a superior balance among memory efficiency, training efficiency, and model performance.
Fonte: arXiv cs.LG
Privacy/Security/Fairness • Score 85
SpectralGuard: Detecting Memory Collapse Attacks in State Space Models
arXiv:2603.12414v1 Announce Type: new
Abstract: State Space Models (SSMs) such as Mamba achieve linear-time sequence processing through input-dependent recurrence, but this mechanism introduces a critical safety vulnerability. We show that the spectral radius rho(A-bar) of the discretized transition operator governs effective memory horizon: when an adversary drives rho toward zero through gradient-based Hidden State Poisoning, memory collapses from millions of tokens to mere dozens, silently destroying reasoning capacity without triggering output-level alarms. We prove an Evasion Existence Theorem showing that for any output-only defense, adversarial inputs exist that simultaneously induce spectral collapse and evade detection, then introduce SpectralGuard, a real-time monitor that tracks spectral stability across all model layers. SpectralGuard achieves F1=0.961 against non-adaptive attackers and retains F1=0.842 under the strongest adaptive setting, with sub-15ms per-token latency. Causal interventions and cross-architecture transfer to hybrid SSM-Attention systems confirm that spectral monitoring provides a principled, deployable safety layer for recurrent foundation models.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Lyapunov Stable Graph Neural Flow
arXiv:2603.12557v1 Announce Type: new
Abstract: Graph Neural Networks (GNNs) are highly vulnerable to adversarial perturbations in both topology and features, making the learning of robust representations a critical challenge. In this work, we bridge GNNs with control theory to introduce a novel defense framework grounded in integer- and fractional-order Lyapunov stability. Unlike conventional strategies that rely on resource-heavy adversarial training or data purification, our approach fundamentally constrains the underlying feature-update dynamics of the GNN. We propose an adaptive, learnable Lyapunov function paired with a novel projection mechanism that maps the network's state into a stable space, thereby offering theoretically provable stability guarantees. Notably, this mechanism is orthogonal to existing defenses, allowing for seamless integration with techniques like adversarial training to achieve cumulative robustness. Extensive experiments demonstrate that our Lyapunov-stable graph neural flows substantially outperform base neural flows and state-of-the-art baselines across standard benchmarks and various adversarial attack scenarios.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Addressing Data Scarcity in 3D Trauma Detection through Self-Supervised and Semi-Supervised Learning with Vertex Relative Position Encoding
arXiv:2603.12514v1 Announce Type: new
Abstract: Accurate detection and localization of traumatic injuries in abdominal CT scans remains a critical challenge in emergency radiology, primarily due to severe scarcity of annotated medical data. This paper presents a label-efficient approach combining self-supervised pre-training with semi-supervised detection for 3D medical image analysis. We employ patch-based Masked Image Modeling (MIM) to pre-train a 3D U-Net encoder on 1,206 CT volumes without annotations, learning robust anatomical representations. The pretrained encoder enables two downstream clinical tasks: 3D injury detection using VDETR with Vertex Relative Position Encoding, and multi-label injury classification. For detection, semi-supervised learning with 2,000 unlabeled volumes and consistency regularization achieves 56.57% validation mAP@0.50 and 45.30% test mAP@0.50 with only 144 labeled training samples, representing a 115% improvement over supervised-only training. For classification, expanding to 2,244 labeled samples yields 94.07% test accuracy across seven injury categories using only a frozen encoder, demonstrating immediately transferable self-supervised features. Our results validate that self-supervised pre-training combined with semi-supervised learning effectively addresses label scarcity in medical imaging, enabling robust 3D object detection with limited annotations.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
TASTE-Streaming: Towards Streamable Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
arXiv:2603.12350v1 Announce Type: new
Abstract: Text-speech joint spoken language modeling (SLM) aims at natural and intelligent speech-based interactions, but developing such a system may suffer from modality mismatch: speech unit sequences are much longer than text tokens. Prior work reduces this gap with text-aligned tokenization and embedding (TASTE), producing speech tokens that align in lengths with their textual counterparts. However, the dependence on an external ASR system and the use of a non-causal decoder limits streaming use. To address this limitation, we propose TASTE-S, a streamable extension of TASTE suitable for real-time usage. TASTE-S integrates a CTC-based ASR module into the encoder for instant dual-modality encoding. We also redesign the unit decoder to enable on-the-fly decoding. With joint training, we show that TASTE-S matches TASTE's performance while significantly reducing latency. Further investigations reveal that TASTE-S remains robust to transcriptions and enables long-form encoding and decoding.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
RoboStereo: Dual-Tower 4D Embodied World Models for Unified Policy Optimization
arXiv:2603.12639v1 Announce Type: new
Abstract: Scalable Embodied AI faces fundamental constraints due to prohibitive costs and safety risks of real-world interaction. While Embodied World Models (EWMs) offer promise through imagined rollouts, existing approaches suffer from geometric hallucinations and lack unified optimization frameworks for practical policy improvement. We introduce RoboStereo, a symmetric dual-tower 4D world model that employs bidirectional cross-modal enhancement to ensure spatiotemporal geometric consistency and alleviate physics hallucinations. Building upon this high-fidelity 4D simulator, we present the first unified framework for world-model-based policy optimization: (1) Test-Time Policy Augmentation (TTPA) for pre-execution verification, (2) Imitative-Evolutionary Policy Learning (IEPL) leveraging visual perceptual rewards to learn from expert demonstrations, and (3) Open-Exploration Policy Learning (OEPL) enabling autonomous skill discovery and self-correction. Comprehensive experiments demonstrate RoboStereo achieves state-of-the-art generation quality, with our unified framework delivering >97% average relative improvement on fine-grained manipulation tasks.
Fonte: arXiv cs.CV
Vision • Score 85
Mobile-GS: Real-time Gaussian Splatting for Mobile Devices
arXiv:2603.11531v1 Announce Type: new
Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful representation for high-quality rendering across a wide range of applications.However, its high computational demands and large storage costs pose significant challenges for deployment on mobile devices. In this work, we propose a mobile-tailored real-time Gaussian Splatting method, dubbed Mobile-GS, enabling efficient inference of Gaussian Splatting on edge devices. Specifically, we first identify alpha blending as the primary computational bottleneck, since it relies on the time-consuming Gaussian depth sorting process. To solve this issue, we propose a depth-aware order-independent rendering scheme that eliminates the need for sorting, thereby substantially accelerating rendering. Although this order-independent rendering improves rendering speed, it may introduce transparency artifacts in regions with overlapping geometry due to the scarcity of rendering order. To address this problem, we propose a neural view-dependent enhancement strategy, enabling more accurate modeling of view-dependent effects conditioned on viewing direction, 3D Gaussian geometry, and appearance attributes. In this way, Mobile-GS can achieve both high-quality and real-time rendering. Furthermore, to facilitate deployment on memory-constrained mobile platforms, we also introduce first-order spherical harmonics distillation, a neural vector quantization technique, and a contribution-based pruning strategy to reduce the number of Gaussian primitives and compress the 3D Gaussian representation with the assistance of neural networks. Extensive experiments demonstrate that our proposed Mobile-GS achieves real-time rendering and compact model size while preserving high visual quality, making it well-suited for mobile applications.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing
arXiv:2603.11593v1 Announce Type: new
Abstract: Instruction-based image editing aims to modify specific content within existing images according to user-provided instructions while preserving non-target regions. Beyond traditional object- and style-centric manipulation, text-centric image editing focuses on modifying, translating, or rearranging textual elements embedded within images. However, existing leading models often struggle to execute complex text editing precisely, frequently producing blurry or hallucinated characters. We attribute these failures primarily to the lack of specialized training paradigms tailored for text-centric editing, as well as the absence of large-scale datasets and standardized benchmarks necessary for a closed-loop training and evaluation system. To address these limitations, we present WeEdit, a systematic solution encompassing a scalable data construction pipeline, two benchmarks, and a tailored two-stage training strategy. Specifically, we propose a novel HTML-based automatic editing pipeline, which generates 330K training pairs covering diverse editing operations and 15 languages, accompanied by standardized bilingual and multilingual benchmarks for comprehensive evaluation. On the algorithmic side, we employ glyph-guided supervised fine-tuning to inject explicit spatial and content priors, followed by a multi-objective reinforcement learning stage to align generation with instruction adherence, text clarity, and background preservation. Extensive experiments demonstrate that WeEdit outperforms previous open-source models by a clear margin across diverse editing operations.
Fonte: arXiv cs.CV
Theory/Optimization • Score 85
Mini-batch Estimation for Deep Cox Models: Statistical Foundations and Practical Guidance
arXiv:2408.02839v4 Announce Type: replace
Abstract: The stochastic gradient descent (SGD) algorithm has been widely used to optimize deep Cox neural network (Cox-NN) by updating model parameters using mini-batches of data. We show that SGD aims to optimize the average of mini-batch partial-likelihood, which is different from the standard partial-likelihood. This distinction requires developing new statistical properties for the global optimizer, namely, the mini-batch maximum partial-likelihood estimator (mb-MPLE). We establish that mb-MPLE for Cox-NN is consistent and achieves the optimal minimax convergence rate up to a polylogarithmic factor. For Cox regression with linear covariate effects, we further show that mb-MPLE is $\sqrt{n}$-consistent and asymptotically normal with asymptotic variance approaching the information lower bound as batch size increases, which is confirmed by simulation studies. Additionally, we offer practical guidance on using SGD, supported by theoretical analysis and numerical evidence. For Cox-NN, we demonstrate that the ratio of the learning rate to the batch size is critical in SGD dynamics, offering insight into hyperparameter tuning. For Cox regression, we characterize the iterative convergence of SGD, ensuring that the global optimizer, mb-MPLE, can be approximated with sufficiently many iterations. Finally, we demonstrate the effectiveness of mb-MPLE in a large-scale real-world application where the standard MPLE is intractable.
Fonte: arXiv stat.ML
Multimodal • Score 85
Frequency-Modulated Visual Restoration for Matryoshka Large Multimodal Models
arXiv:2603.11220v1 Announce Type: new
Abstract: Large Multimodal Models (LMMs) struggle to adapt varying computational budgets due to numerous visual tokens. Previous methods attempted to reduce the number of visual tokens before or within LLMs. However, these strategies inevitably result in the loss of visual semantic. To address these issues, we introduce FMVR, a plug-and-play and extremely simple Frequency-Modulated Visual Restoration strategy to boost the reasoning ability of LMMs under visual token reduction. Specifically, FMVR disentangles the visual representation of fewer visual tokens into low- and high-frequency components through AvgPool and MaxPool. The derived frequencies are subsequently modulated using lightweight learnable parameters. The high-frequency from AvgPool acts as a saliency filter to enhance saliency visual semantics, while the low-frequency from MaxPool acts as an anti-saliency filter to strengthen weak visual semantics. It enables the preservation of visual semantics dominated by few visual tokens and the restoration of diluted visual semantics. Additionally, we inject FMVR into Matryoshka Representation Learning to learn coarse-to-fine visual token sets, thus enabling to elastically adjust the number of visual tokens during inference while maintaining comparable performance. Experiments across 10 image-based and 4 video-based bench marks demonstrate that FMVR-LLaVA reduce the FLOPs of LLaVA-1.5-7B by 89%, while maintaining almost 100% of the original accuracy. The code will be open.
Fonte: arXiv cs.CV
Theory/Optimization • Score 85
Learning Tree-Based Models with Gradient Descent
arXiv:2603.11117v1 Announce Type: new
Abstract: Tree-based models are widely recognized for their interpretability and have proven effective in various application domains, particularly in high-stakes domains. However, learning decision trees (DTs) poses a significant challenge due to their combinatorial complexity and discrete, non-differentiable nature. As a result, traditional methods such as CART, which rely on greedy search procedures, remain the most widely used approaches. These methods make locally optimal decisions at each node, constraining the search space and often leading to suboptimal tree structures. Additionally, their demand for custom training methods precludes a seamless integration into modern machine learning (ML) approaches.
In this thesis, we propose a novel method for learning hard, axis-aligned DTs through gradient descent. Our approach utilizes backpropagation with a straight-through operator on a dense DT representation, enabling the joint optimization of all tree parameters, thereby addressing the two primary limitations of traditional DT algorithms. First, gradient-based training is not constrained by the sequential selection of locally optimal splits but, instead, jointly optimizes all tree parameters. Second, by leveraging gradient descent for optimization, our approach seamlessly integrates into existing ML approaches e.g., for multimodal and reinforcement learning tasks, which inherently rely on gradient descent.
These advancements allow us to achieve state-of-the-art results across multiple domains, including interpretable DTs rees for small tabular datasets, advanced models for complex tabular data, multimodal learning, and interpretable reinforcement learning without information loss. By bridging the gap between DTs and gradient-based optimization, our method significantly enhances the performance and applicability of tree-based models across various ML domains.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Group Resonance Network: Learnable Prototypes and Multi-Subject Resonance for EEG Emotion Recognition
arXiv:2603.11119v1 Announce Type: new
Abstract: Electroencephalography(EEG)-basedemotionrecognitionre- mains challenging in cross-subject settings due to severe inter-subject variability. Existing methods mainly learn subject-invariant features, but often under-exploit stimulus-locked group regularities shared across sub- jects. To address this issue, we propose the Group Resonance Network (GRN), which integrates individual EEG dynamics with offline group resonance modeling. GRN contains three components: an individual en- coder for band-wise EEG features, a set of learnable group prototypes for prototype-induced resonance, and a multi-subject resonance branch that encodes PLV/coherence-based synchrony with a small reference set. A resonance-aware fusion module combines individual and group-level rep- resentations for final classification. Experiments on SEED and DEAP under both subject-dependent and leave-one-subject-out protocols show that GRN consistently outperforms competitive baselines, while abla- tion studies confirm the complementary benefits of prototype learning and multi-subject resonance modeling.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
High-resolution weather-guided surrogate modeling for data-efficient cross-location building energy prediction
arXiv:2603.11121v1 Announce Type: new
Abstract: Building design optimization often depends on physics-based simulation tools such as EnergyPlus, which, although accurate, are computationally expensive and slow. Surrogate models provide a faster alternative, yet most are location-specific, and even weather-informed variants require simulations from many sites to generalize to unseen locations. This limitation arises because existing methods do not fully exploit the short-term weather-driven energy patterns shared across regions, restricting their scalability and reusability. This study introduces a high-resolution (weekly) weather-informed surrogate modeling approach that enhances model reusability across locations. By capturing recurring short-term weather-energy demand patterns common to multiple regions, the proposed method produces a generalized surrogate that performs well beyond the training location. Unlike previous weather-informed approaches, it does not require extensive simulations from multiple sites to achieve strong generalization. Experimental results show that when trained on a single location, the model maintains high predictive accuracy for other sites within the same climate zone, with no noticeable performance loss, and exhibits only minimal degradation when applied across different climate zones. These findings demonstrate the potential of climate-informed generalization for developing scalable and reusable surrogate models, supporting more sustainable and optimized building design practices.
Fonte: arXiv cs.LG
RL • Score 85
abx_amr_simulator: A simulation environment for antibiotic prescribing policy optimization under antimicrobial resistance
arXiv:2603.11369v1 Announce Type: new
Abstract: Antimicrobial resistance (AMR) poses a global health threat, reducing the effectiveness of antibiotics and complicating clinical decision-making. To address this challenge, we introduce abx_amr_simulator, a Python-based simulation package designed to model antibiotic prescribing and AMR dynamics within a controlled, reinforcement learning (RL)-compatible environment. The simulator allows users to specify patient populations, antibiotic-specific AMR response curves, and reward functions that balance immedi- ate clinical benefit against long-term resistance management. Key features include a modular design for configuring patient attributes, antibiotic resistance dynamics modeled via a leaky-balloon abstraction, and tools to explore partial observability through noise, bias, and delay in observations. The package is compatible with the Gymnasium RL API, enabling users to train and test RL agents under diverse clinical scenarios. From an ML perspective, the package provides a configurable benchmark environment for sequential decision-making under uncertainty, including partial observability induced by noisy, biased, and delayed observations. By providing a customizable and extensible framework, abx_amr_simulator offers a valuable tool for studying AMR dynamics and optimizing antibiotic stewardship strategies under realistic uncertainty.
Fonte: arXiv cs.LG
Applications • Score 85
Monitoring and Prediction of Mood in Elderly People during Daily Life Activities
arXiv:2603.11230v1 Announce Type: new
Abstract: We present an intelligent wearable system to monitor and predict mood states of elderly people during their daily life activities. Our system is composed of a wristband to record different physiological activities together with a mobile app for ecological momentary assessment (EMA). Machine learning is used to train a classifier to automatically predict different mood states based on the smart band only. Our approach shows promising results on mood accuracy and provides results comparable with the state of the art in the specific detection of happiness and activeness.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Task-Conditioned Routing Signatures in Sparse Mixture-of-Experts Transformers
arXiv:2603.11114v1 Announce Type: new
Abstract: Sparse Mixture-of-Experts (MoE) architectures enable efficient scaling of large language models through conditional computation, yet the routing mechanisms responsible for expert selection remain poorly understood. In this work, we introduce routing signatures, a vector representation summarizing expert activation patterns across layers for a given prompt, and use them to study whether MoE routing exhibits task-conditioned structure. Using OLMoE-1B-7B-0125-Instruct as an empirical testbed, we show that prompts from the same task category induce highly similar routing signatures, while prompts from different categories exhibit substantially lower similarity. Within-category routing similarity (0.8435 +/- 0.0879) significantly exceeds across-category similarity (0.6225 +/- 0.1687), corresponding to Cohen's d = 1.44. A logistic regression classifier trained solely on routing signatures achieves 92.5% +/- 6.1% cross-validated accuracy on four-way task classification. To ensure statistical validity, we introduce permutation and load-balancing baselines and show that the observed separation is not explained by sparsity or balancing constraints alone. We further analyze layer-wise signal strength and low-dimensional projections of routing signatures, finding that task structure becomes increasingly apparent in deeper layers. These results suggest that routing in sparse transformers is not merely a balancing mechanism, but a measurable task-sensitive component of conditional computation. We release MOE-XRAY, a lightweight toolkit for routing telemetry and analysis.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Structure-Aware Epistemic Uncertainty Quantification for Neural Operator PDE Surrogates
arXiv:2603.11052v1 Announce Type: new
Abstract: Neural operators (NOs) provide fast, resolution-invariant surrogates for mapping input fields to PDE solution fields, but their predictions can exhibit significant epistemic uncertainty due to finite data, imperfect optimization, and distribution shift. For practical deployment in scientific computing, uncertainty quantification (UQ) must be both computationally efficient and spatially faithful, i.e., uncertainty bands should align with the localized residual structures that matter for downstream risk management. We propose a structure-aware epistemic UQ scheme that exploits the modular anatomy common to modern NOs (lifting-propagation-recovering). Instead of applying unstructured weight perturbations (e.g., naive dropout) across the entire network, we restrict Monte Carlo sampling to a module-aligned subspace by injecting stochasticity only into the lifting module, and treat the learned solver dynamics (propagation and recovery) as deterministic. We instantiate this principle with two lightweight lifting-level perturbations, including channel-wise multiplicative feature dropout and a Gaussian feature perturbation with matched variance, followed by standard calibration to construct uncertainty bands. Experiments on challenging PDE benchmarks (including discontinuous-coefficient Darcy flow and geometry-shifted 3D car CFD surrogates) demonstrate that the proposed structure-aware design yields more reliable coverage, tighter bands, and improved residual-uncertainty alignment compared with common baselines, while remaining practical in runtime.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
Duration Aware Scheduling for ASR Serving Under Workload Drift
arXiv:2603.11273v1 Announce Type: new
Abstract: Scheduling policies in large-scale Automatic Speech Recognition (ASR) serving pipelines play a key role in determining end-to-end (E2E) latency. Yet, widely used serving engines rely on first-come-first-served (FCFS) scheduling, which ignores variability in request duration and leads to head-of-line blocking under workload drift. We show that audio duration is an accurate proxy for job processing time in ASR models such as Whisper, and use this insight to enable duration-aware scheduling. We integrate two classical algorithms, Shortest Job First (SJF) and Highest Response Ratio Next (HRRN), into vLLM and evaluate them under realistic and drifted workloads. On LibriSpeech test-clean, compared to baseline, SJF reduces median E2E latency by up to $73\%$ at high load, but increases $90$th-percentile tail latency by up to $97\%$ due to starvation of long requests. HRRN addresses this trade-off: it reduces median E2E latency by up to $28\%$ while bounding tail-latency degradation to at most $24\%$. These gains persist under workload drift, with no throughput penalty and $<0.1$\,ms scheduling overhead per request.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
Client-Conditional Federated Learning via Local Training Data Statistics
arXiv:2603.11307v1 Announce Type: new
Abstract: Federated learning (FL) under data heterogeneity remains challenging: existing methods either ignore client differences (FedAvg), require costly cluster discovery (IFCA), or maintain per-client models (Ditto). All degrade when data is sparse or heterogeneity is multi-dimensional. We propose conditioning a single global model on locally-computed PCA statistics of each client's training data, requiring zero additional communication. Evaluating across 97~configurations spanning four heterogeneity types (label shift, covariate shift, concept shift, and combined heterogeneity), four datasets (MNIST, Fashion-MNIST, CIFAR-10, CIFAR-100), and seven FL baseline methods, we find that our method matches the Oracle baseline -- which knows true cluster assignments -- across all settings, surpasses it by 1--6% on combined heterogeneity where continuous statistics are richer than discrete cluster identifiers, and is uniquely sparsity-robust among all tested methods.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
UniCompress: Token Compression for Unified Vision-Language Understanding and Generation
arXiv:2603.11320v1 Announce Type: new
Abstract: Unified models aim to support both understanding and generation by encoding images into discrete tokens and processing them alongside text within a single autoregressive framework. This unified design offers architectural simplicity and cross-modal synergy, which facilitates shared parameterization, consistent training objectives, and seamless transfer between modalities. However, the large number of visual tokens required by such models introduces substantial computation and memory overhead, and this inefficiency directly hinders deployment in resource constrained scenarios such as embodied AI systems. In this work, we propose a unified token compression algorithm UniCompress that significantly reduces visual token count while preserving performance on both image understanding and generation tasks. Our method introduces a plug-in compression and decompression mechanism guided with learnable global meta tokens. The framework is lightweight and modular, enabling efficient integration into existing models without full retraining. Experimental results show that our approach reduces image tokens by up to 4 times, achieves substantial gains in inference latency and training cost, and incurs only minimal performance degradation, which demonstrates the promise of token-efficient unified modeling for real world multimodal applications.
Fonte: arXiv cs.CV
Theory/Optimization • Score 85
Randomized Kriging Believer for Parallel Bayesian Optimization with Regret Bounds
arXiv:2603.01470v2 Announce Type: replace-cross
Abstract: We consider an optimization problem of an expensive-to-evaluate black-box function, in which we can obtain noisy function values in parallel. For this problem, parallel Bayesian optimization (PBO) is a promising approach, which aims to optimize with fewer function evaluations by selecting a diverse input set for parallel evaluation. However, existing PBO methods suffer from poor practical performance or lack theoretical guarantees. In this study, we propose a PBO method, called randomized kriging believer (KB), based on a well-known KB heuristic and inheriting the advantages of the original KB: low computational complexity, a simple implementation, versatility across various BO methods, and applicability to asynchronous parallelization. Furthermore, we show that our randomized KB achieves Bayesian expected regret guarantees. We demonstrate the effectiveness of the proposed method through experiments on synthetic and benchmark functions and emulators of real-world data.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
Relaxed Efficient Acquisition of Context and Temporal Features
arXiv:2603.11370v1 Announce Type: new
Abstract: In many biomedical applications, measurements are not freely available at inference time: each laboratory test, imaging modality, or assessment incurs financial cost, time burden, or patient risk. Longitudinal active feature acquisition (LAFA) seeks to optimize predictive performance under such constraints by adaptively selecting measurements over time, yet the problem remains inherently challenging due to temporally coupled decisions (missed early measurements cannot be revisited, and acquisition choices influence all downstream predictions). Moreover, real-world clinical workflows typically begin with an initial onboarding phase, during which relatively stable contextual descriptors (e.g., demographics or baseline characteristics) are collected once and subsequently condition longitudinal decision-making. Despite its practical importance, the efficient selection of onboarding context has not been studied jointly with temporally adaptive acquisition. We therefore propose REACT (Relaxed Efficient Acquisition of Context and Temporal features), an end-to-end differentiable framework that simultaneously optimizes (i) selection of onboarding contextual descriptors and (ii) adaptive feature--time acquisition plans for longitudinal measurements under cost constraints. REACT employs a Gumbel--Sigmoid relaxation with straight-through estimation to enable gradient-based optimization over discrete acquisition masks, allowing direct backpropagation from prediction loss and acquisition cost. Across real-world longitudinal health and behavioral datasets, REACT achieves improved predictive performance at lower acquisition costs compared to existing longitudinal acquisition baselines, demonstrating the benefit of modeling onboarding and temporally coupled acquisition within a unified optimization framework.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
DyWeight: Dynamic Gradient Weighting for Few-Step Diffusion Sampling
arXiv:2603.11607v1 Announce Type: new
Abstract: Diffusion Models (DMs) have achieved state-of-the-art generative performance across multiple modalities, yet their sampling process remains prohibitively slow due to the need for hundreds of function evaluations. Recent progress in multi-step ODE solvers has greatly improved efficiency by reusing historical gradients, but existing methods rely on handcrafted coefficients that fail to adapt to the non-stationary dynamics of diffusion sampling. To address this limitation, we propose Dynamic Gradient Weighting (DyWeight), a lightweight, learning-based multi-step solver that introduces a streamlined implicit coupling paradigm. By relaxing classical numerical constraints, DyWeight learns unconstrained time-varying parameters that adaptively aggregate historical gradients while intrinsically scaling the effective step size. This implicit time calibration accurately aligns the solver's numerical trajectory with the model's internal denoising dynamics under large integration steps, avoiding complex decoupled parameterizations and optimizations. Extensive experiments on CIFAR-10, FFHQ, AFHQv2, ImageNet64, LSUN-Bedroom, Stable Diffusion and FLUX.1-dev demonstrate that DyWeight achieves superior visual fidelity and stability with significantly fewer function evaluations, establishing a new state-of-the-art among efficient diffusion solvers. Code is available at https://github.com/Westlake-AGI-Lab/DyWeight
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
Micro-Diffusion Compression - Binary Tree Tweedie Denoising for Online Probability Estimation
arXiv:2603.08771v3 Announce Type: replace
Abstract: We present Midicoth, a lossless compression system that introduces a micro-diffusion denoising layer for improving probability estimates produced by adaptive statistical models. In compressors such as Prediction by Partial Matching (PPM), probability estimates are smoothed by a prior to handle sparse observations. When contexts have been seen only a few times, this prior dominates the prediction and produces distributions that are significantly flatter than the true source distribution, leading to compression inefficiency. Midicoth addresses this limitation by treating prior smoothing as a shrinkage process and applying a reverse denoising step that corrects predicted probabilities using empirical calibration statistics. To make this correction data-efficient, the method decomposes each byte prediction into a hierarchy of binary decisions along a bitwise tree. This converts a single 256-way calibration problem into a sequence of binary calibration tasks, enabling reliable estimation of correction terms from relatively small numbers of observations. The denoising process is applied in multiple successive steps, allowing each stage to refine residual prediction errors left by the previous one. The micro-diffusion layer operates as a lightweight post-blend calibration stage applied after all model predictions have been combined, allowing it to correct systematic biases in the final probability distribution. Midicoth combines five fully online components: an adaptive PPM model, a long-range match model, a trie-based word model, a high-order context model, and the micro-diffusion denoiser applied as the final stage.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure
arXiv:2603.11493v1 Announce Type: new
Abstract: Text-to-image (T2I) models face significant safety risks from adversarial induction, yet current concept erasure methods often cause collateral damage to benign attributes when suppressing selected neurons entirely. This occurs because sensitive and benign semantics exhibit non-orthogonal superposition, sharing activation subspaces where their respective vectors are inherently entangled. To address this issue, we propose OrthoEraser, which leverages sparse autoencoders (SAE) to achieve high-resolution feature disentanglement and subsequently redefines erasure as an analytical orthogonalization projection that preserves the benign manifold's invariance. OrthoEraser first employs SAE to decompose dense activations and segregate sensitive neurons. It then uses coupled neuron detection to identify non-sensitive features vulnerable to intervention. The key novelty lies in an analytical gradient orthogonalization strategy that projects erasure vectors onto the null space of the coupled neurons. This orthogonally decouples the sensitive concepts from the identified critical benign subspace, effectively preserving non-sensitive semantics. Experimental results on safety demonstrate that OrthoEraser achieves high erasure precision, effectively removing harmful content while preserving the integrity of the generative manifold, and significantly outperforming SOTA baselines. This paper contains results of unsafe models.
Fonte: arXiv cs.CV
RL • Score 85
Ensuring Safety in Automated Mechanical Ventilation through Offline Reinforcement Learning and Digital Twin Verification
arXiv:2603.11372v1 Announce Type: new
Abstract: Mechanical ventilation (MV) is a life-saving intervention for patients with acute respiratory failure (ARF) in the ICU. However, inappropriate ventilator settings could cause ventilator-induced lung injury (VILI). Also, clinicians workload is shown to be directly linked to patient outcomes. Hence, MV should be personalized and automated to improve patient outcomes. Previous attempts to incorporate personalization and automation in MV include traditional supervised learning and offline reinforcement learning (RL) approaches, which often neglect temporal dependencies and rely excessively on mortality-based rewards. As a result, early stage physiological deterioration and the risk of VILI are not adequately captured. To address these limitations, we propose Transformer-based Conservative Q-Learning (T-CQL), a novel offline RL framework that integrates a Transformer encoder for effective temporal modeling of patient dynamics, conservative adaptive regularization based on uncertainty quantification to ensure safety, and consistency regularization for robust decision-making. We build a clinically informed reward function that incorporates indicators of VILI and a score for severity of patients illness. Also, previous work predominantly uses Fitted Q-Evaluation (FQE) for RL policy evaluation on static offline data, which is less responsive to dynamic environmental changes and susceptible to distribution shifts. To overcome these evaluation limitations, interactive digital twins of ARF patients were used for online "at the bedside" evaluation. Our results demonstrate that T-CQL consistently outperforms existing state-of-the-art offline RL methodologies, providing safer and more effective ventilatory adjustments. Our framework demonstrates the potential of Transformer-based models combined with conservative RL strategies as a decision support tool in critical care.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
A Learning-Based Superposition Operator for Non-Renewal Arrival Processes in Queueing Networks
arXiv:2603.11118v1 Announce Type: new
Abstract: The superposition of arrival processes is a fundamental yet analytically intractable operation in queueing networks when inputs are general non-renewal streams. Classical methods either reduce merged flows to renewal surrogates, rely on computationally prohibitive Markovian representations, or focus solely on mean-value performance measures.
We propose a scalable data-driven superposition operator that maps low-order moments and autocorrelation descriptors of multiple arrival streams to those of their merged process. The operator is a deep learning model trained on synthetically generated Markovian Arrival Processes (MAPs), for which exact superposition is available, and learns a compact representation that accurately reconstructs the first five moments and short-range dependence structure of the aggregate stream. Extensive computational experiments demonstrate uniformly low prediction errors across heterogeneous variability and correlation regimes, substantially outperforming classical renewal-based approximations.
When integrated with learning-based modules for departure-process and steady-state analysis, the proposed operator enables decomposition-based evaluation of feed-forward queueing networks with merging flows. The framework provides a scalable alternative to traditional analytical approaches while preserving higher-order variability and dependence information required for accurate distributional performance analysis.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
SemiTooth: a Generalizable Semi-supervised Framework for Multi-Source Tooth Segmentation
arXiv:2603.11616v1 Announce Type: new
Abstract: With the rapid advancement of artificial intelligence, intelligent dentistry for clinical diagnosis and treatment has become increasingly promising. As the primary clinical dentistry task, tooth structure segmentation for Cone-Beam Computed Tomography (CBCT) has made significant progress in recent years. However, challenges arise from the obtainment difficulty of full-annotated data, and the acquisition variability of multi-source data across different institutions, which have caused low-quality utilization, voxel-level inconsistency, and domain-specific disparity in CBCT slices. Thus, the rational and efficient utilization of multi-source and unlabeled data represents a pivotal problem. In this paper, we propose SemiTooth, a generalizable semi-supervised framework for multi-source tooth segmentation. Specifically, we first compile MS3Toothset, Multi-Source Semi-Supervised Tooth DataSet for clinical dental CBCT, which contains data from three sources with different-level annotations. Then, we design a multi-teacher and multi-student framework, i.e., SemiTooth, which promotes semi-supervised learning for multi-source data. SemiTooth employs distinct student networks that learn from unlabeled data with different sources, supervised by its respective teachers. Furthermore, a Stricter Weighted-Confidence Constraint is introduced for multiple teachers to improve the multi-source accuracy.Extensive experiments are conducted on MS3Toothset to verify the feasibility and superiority of the SemiTooth framework, which achieves SOTA performance on the semi-supervised and multi-source tooth segmentation scenario.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
ES-dLLM: Efficient Inference for Diffusion Large Language Models by Early-Skipping
arXiv:2603.10088v1 Announce Type: new
Abstract: Diffusion large language models (dLLMs) are emerging as a promising alternative to autoregressive models (ARMs) due to their ability to capture bidirectional context and the potential for parallel generation. Despite the advantages, dLLM inference remains computationally expensive as the full input context is processed at every iteration. In this work, we analyze the generation dynamics of dLLMs and find that intermediate representations, including key, value, and hidden states, change only subtly across successive iterations. Leveraging this insight, we propose \textbf{ES-dLLM}, a training-free inference acceleration framework for dLLM that reduces computation by skipping tokens in early layers based on the estimated importance. Token importance is computed with intermediate tensor variation and confidence scores of previous iterations. Experiments on LLaDA-8B and Dream-7B demonstrate that ES-dLLM achieves throughput of up to 226.57 and 308.51 tokens per second (TPS), respectively, on an NVIDIA H200 GPU, delivering 5.6$\times$ to 16.8$\times$ speedup over the vanilla implementation and up to 1.85$\times$ over the state-of-the-art caching method, while preserving generation quality.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
LWM-Temporal: Sparse Spatio-Temporal Attention for Wireless Channel Representation Learning
arXiv:2603.10024v1 Announce Type: new
Abstract: LWM-Temporal is a new member of the Large Wireless Models (LWM) family that targets the spatiotemporal nature of wireless channels. Designed as a task-agnostic foundation model, LWM-Temporal learns universal channel embeddings that capture mobility-induced evolution and are reusable across various downstream tasks. To achieve this objective, LWM-Temporal operates in the angle-delay-time domain and introduces Sparse Spatio-Temporal Attention (SSTA), a propagation-aligned attention mechanism that restricts interactions to physically plausible neighborhoods, reducing attention complexity by an order of magnitude while preserving geometry-consistent dependencies. LWM-Temporal is pretrained in a self-supervised manner using a physics-informed masking curriculum that emulates realistic occlusions, pilot sparsity, and measurement impairments. Experimental results on channel prediction across multiple mobility regimes show consistent improvements over strong baselines, particularly under long horizons and limited fine-tuning data, highlighting the importance of geometry-aware architectures and geometry-consistent pretraining for learning transferable spatiotemporal wireless representations.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios
arXiv:2603.09983v1 Announce Type: new
Abstract: Mixture-of-Experts (MoE) models enable scalable performance but face severe memory constraints on edge devices. Existing offloading strategies struggle with I/O bottlenecks due to the dynamic, low-information nature of autoregressive expert activation. In this paper, we propose to repurpose Speculative Decoding (SD) not merely as a compute accelerator, but as an informative lookahead sensor for memory management, supported by our theoretical and empirical analyses. Hence, we introduce MoE-SpAc, an MoE inference framework that integrates a Speculative Utility Estimator to track expert demand, a Heterogeneous Workload Balancer to dynamically partition computation via online integer optimization, and an Asynchronous Execution Engine to unify the prefetching and eviction in the same utility space. Extensive experiments on seven benchmarks demonstrate that MoE-SpAc achieves a 42% improvement in TPS over the SOTA SD-based baseline, and an average 4.04x speedup over all standard baselines. Code is available at https://github.com/lshAlgorithm/MoE-SpAc .
Fonte: arXiv cs.LG
RL • Score 85
CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR
arXiv:2603.10101v1 Announce Type: new
Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced the reasoning capacity of Large Language Models (LLMs). However, RLVR solely relies on final answers as outcome rewards, neglecting the correctness of intermediate reasoning steps. Training on these process-wrong but outcome-correct rollouts can lead to hallucination and answer-copying, severely undermining the model's generalization and robustness. To address this, we incorporate a Contrastive Learning mechanism into the Policy Optimization (CLIPO) to generalize the RLVR process. By optimizing a contrastive loss over successful rollouts, CLIPO steers the LLM to capture the invariant structure shared across correct reasoning paths. This provides a more robust cross-trajectory regularization than the original single-path supervision in RLVR, effectively mitigating step-level reasoning inconsistencies and suppressing hallucinatory artifacts. In experiments, CLIPO consistently improves multiple RLVR baselines across diverse reasoning benchmarks, demonstrating uniform improvements in generalization and robustness for policy optimization of LLMs. Our code and training recipes are available at https://github.com/Qwen-Applications/CLIPO.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization
arXiv:2603.10085v1 Announce Type: new
Abstract: Improving GPU kernel efficiency is crucial for advancing AI systems. Recent work has explored leveraging large language models (LLMs) for GPU kernel generation and optimization. However, existing LLM-based kernel optimization pipelines typically rely on opaque, implicitly learned heuristics within the LLMs to determine optimization strategies. This leads to inefficient trial-and-error and weakly interpretable optimizations. Our key insight is to replace implicit heuristics with expert optimization skills that are knowledge-driven and aware of task trajectories. Specifically, we present KernelSkill, a multi-agent framework with a dual-level memory architecture. KernelSkill operates by coordinating agents with long-term memory of reusable expert skills and short-term memory to prevent repetitive backtracking. On KernelBench Levels 1-3, KernelSkill achieves a 100% success rate and average speedups of 5.44x, 2.82x, and 1.92x over Torch Eager on Levels 1, 2, and 3, respectively, outperforming prior baselines. Code is available at https://github.com/0satan0/KernelMem/.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Stochastic Port-Hamiltonian Neural Networks: Universal Approximation with Passivity Guarantees
arXiv:2603.10078v1 Announce Type: new
Abstract: Stochastic port-Hamiltonian systems represent open dynamical systems with dissipation, inputs, and stochastic forcing in an energy based form. We introduce stochastic port-Hamiltonian neural networks, SPH-NNs, which parameterize the Hamiltonian with a feedforward network and enforce skew symmetry of the interconnection matrix and positive semidefiniteness of the dissipation matrix. For It\^o dynamics we establish a weak passivity inequality in expectation under an explicit generator condition, stated for a stopped process on a compact set. We also prove a universal approximation result showing that, on any compact set and finite horizon, SPH-NNs approximate the coefficients of a target stochastic port-Hamiltonian system with $C^2$ accuracy of the Hamiltonian and yield coupled solutions that remain close in mean square up to the exit time. Experiments on noisy mass spring, Duffing, and Van der Pol oscillators show improved long horizon rollouts and reduced energy error relative to a multilayer perceptron baseline.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Optimal Expert-Attention Allocation in Mixture-of-Experts: A Scalable Law for Dynamic Model Design
arXiv:2603.10379v1 Announce Type: new
Abstract: This paper presents a novel extension of neural scaling laws to Mixture-of-Experts (MoE) models, focusing on the optimal allocation of compute between expert and attention sub-layers. As MoE architectures have emerged as an efficient method for scaling model capacity without proportionally increasing computation, determining the optimal expert-attention compute ratio becomes critical. We define the ratio $r$ as the fraction of total FLOPs per token dedicated to the expert layers versus the attention layers, and explore how this ratio interacts with the overall compute budget and model sparsity. Through extensive experiments with GPT-style MoE Transformers, we empirically find that the optimal ratio $r^*$ follows a power-law relationship with total compute and varies with sparsity. Our analysis leads to an explicit formula for $r^*$, enabling precise control over the expert-attention compute allocation. We generalize the Chinchilla scaling law by incorporating this architectural parameter, providing a new framework for tuning MoE models beyond size and data. Our findings offer practical guidelines for designing efficient MoE models, optimizing performance while respecting fixed compute budgets.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Mashup Learning: Faster Finetuning by Remixing Past Checkpoints
arXiv:2603.10156v1 Announce Type: new
Abstract: Finetuning on domain-specific data is a well-established method for enhancing LLM performance on downstream tasks. Training on each dataset produces a new set of model weights, resulting in a multitude of checkpoints saved in-house or on open-source platforms. However, these training artifacts are rarely reused for subsequent experiments despite containing improved model abilities for potentially similar tasks. In this paper, we propose Mashup Learning, a simple method to leverage the outputs of prior training runs to enhance model adaptation to new tasks. Our procedure identifies the most relevant historical checkpoints for a target dataset, aggregates them with model merging, and uses the result as an improved initialization for training. Across 8 standard LLM benchmarks, four models, and two collections of source checkpoints, Mashup Learning consistently improves average downstream accuracy by 0.5-5 percentage points over training from scratch. It also accelerates convergence, requiring 41-46% fewer training steps and up to 37% less total wall-clock time to match from-scratch accuracy, including all selection and merging overhead.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
A Survey of Weight Space Learning: Understanding, Representation, and Generation
arXiv:2603.10090v1 Announce Type: new
Abstract: Neural network weights are typically viewed as the end product of training, while most deep learning research focuses on data, features, and architectures. However, recent advances show that the set of all possible weight values (weight space) itself contains rich structure: pretrained models form organized distributions, exhibit symmetries, and can be embedded, compared, or even generated. Understanding such structures has tremendous impact on how neural networks are analyzed and compared, and on how knowledge is transferred across models, beyond individual training instances. This emerging research direction, which we refer to as Weight Space Learning (WSL), treats neural weights as a meaningful domain for analysis and modeling. This survey provides the first unified taxonomy of WSL. We categorize existing methods into three core dimensions: Weight Space Understanding (WSU), which studies the geometry and symmetries of weights; Weight Space Representation (WSR), which learns embeddings over model weights; and Weight Space Generation (WSG), which synthesizes new weights through hypernetworks or generative models. We further show how these developments enable practical applications, including model retrieval, continual and federated learning, neural architecture search, and data-free reconstruction. By consolidating fragmented progress under a coherent framework, this survey highlights weight space as a learnable, structured domain with growing impact across model analysis, transferring, and weight generation. We release an accompanying resource at https://github.com/Zehong-Wang/Awesome-Weight-Space-Learning.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
Hardware Efficient Approximate Convolution with Tunable Error Tolerance for CNNs
arXiv:2603.10100v1 Announce Type: new
Abstract: Modern CNNs' high computational demands hinder edge deployment, as traditional ``hard'' sparsity (skipping mathematical zeros) loses effectiveness in deep layers or with smooth activations like Tanh. We propose a ``soft sparsity'' paradigm using a hardware efficient Most Significant Bit (MSB) proxy to skip negligible non-zero multiplications. Integrated as a custom RISC-V instruction and evaluated on LeNet-5 (MNIST), this method reduces ReLU MACs by 88.42% and Tanh MACs by 74.87% with zero accuracy loss--outperforming zero-skipping by 5x. By clock-gating inactive multipliers, we estimate power savings of 35.2\% for ReLU and 29.96\% for Tanh. While memory access makes power reduction sub-linear to operation savings, this approach significantly optimizes resource-constrained inference.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Estimating condition number with Graph Neural Networks
arXiv:2603.10277v1 Announce Type: new
Abstract: In this paper, we propose a fast method for estimating the condition number of sparse matrices using graph neural networks (GNNs). To enable efficient training and inference of GNNs, our proposed feature engineering for GNNs achieves $\mathrm{O}(\mathrm{nnz} + n)$, where $\mathrm{nnz}$ is the number of non-zero elements in the matrix and $n$ denotes the matrix dimension. We propose two prediction schemes for estimating the matrix condition number using GNNs. The extensive experiments for the two schemes are conducted for 1-norm and 2-norm condition number estimation, which show that our method achieves a significant speedup over the Hager-Higham and Lanczos methods.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Rethinking the Harmonic Loss via Non-Euclidean Distance Layers
arXiv:2603.10225v1 Announce Type: new
Abstract: Cross-entropy loss has long been the standard choice for training deep neural networks, yet it suffers from interpretability limitations, unbounded weight growth, and inefficiencies that can contribute to costly training dynamics. The harmonic loss is a distance-based alternative grounded in Euclidean geometry that improves interpretability and mitigates phenomena such as grokking, or delayed generalization on the test set. However, the study of harmonic loss remains narrow: only Euclidean distance is explored, and no systematic evaluation of computational efficiency or sustainability was conducted. We extend harmonic loss by systematically investigating a broad spectrum of distance metrics as replacements for the Euclidean distance. We comprehensively evaluate distance-tailored harmonic losses on both vision backbones and large language models. Our analysis is framed around a three-way evaluation of model performance, interpretability, and sustainability. On vision tasks, cosine distances provide the most favorable trade-off, consistently improving accuracy while lowering carbon emissions, whereas Bray-Curtis and Mahalanobis further enhance interpretability at varying efficiency costs. On language models, cosine-based harmonic losses improve gradient and learning stability, strengthen representation structure, and reduce emissions relative to cross-entropy and Euclidean heads. Our code is available at: https://anonymous.4open.science/r/rethinking-harmonic-loss-5BAB/.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Federated Active Learning Under Extreme Non-IID and Global Class Imbalance
arXiv:2603.10341v1 Announce Type: new
Abstract: Federated active learning (FAL) seeks to reduce annotation cost under privacy constraints, yet its effectiveness degrades in realistic settings with severe global class imbalance and highly heterogeneous clients. We conduct a systematic study of query-model selection in FAL and uncover a central insight: the model that achieves more class-balanced sampling, especially for minority classes, consistently leads to better final performance. Moreover, global-model querying is beneficial only when the global distribution is highly imbalanced and client data are relatively homogeneous; otherwise, the local model is preferable. Based on these findings, we propose FairFAL, an adaptive class-fair FAL framework. FairFAL (1) infers global imbalance and local-global divergence via lightweight prediction discrepancy, enabling adaptive selection between global and local query models; (2) performs prototype-guided pseudo-labeling using global features to promote class-aware querying; and (3) applies a two-stage uncertainty-diversity balanced sampling strategy with k-center refinement. Experiments on five benchmarks show that FairFAL consistently outperforms state-of-the-art approaches under challenging long-tailed and non-IID settings. The code is available at https://github.com/chenchenzong/FairFAL.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
InFusionLayer: a CFA-based ensemble tool to generate new classifiers for learning and modeling
arXiv:2603.10049v1 Announce Type: new
Abstract: Ensemble learning is a well established body of methods for machine learning to enhance predictive performance by combining multiple algorithms/models. Combinatorial Fusion Analysis (CFA) has provided method and practice for combining multiple scoring systems, using rank-score characteristic (RSC) function and cognitive diversity (CD), including ensemble method and model fusion. However, there is no general-purpose Python tool available that incorporate these techniques. In this paper we introduce \texttt{InFusionLayer}, a machine learning architecture inspired by CFA at the system fusion level that uses a moderate set of base models to optimize unsupervised and supervised learning multiclassification problems. We demonstrate \texttt{InFusionLayer}'s ease of use for PyTorch, TensorFlow, and Scikit-learn workflows by validating its performance on various computer vision datasets. Our results highlight the practical advantages of incorporating distinctive features of RSC function and CD, paving the way for more sophisticated ensemble learning applications in machine learning. We open-sourced our code to encourage continuing development and community accessibility to leverage CFA on github: https://github.com/ewroginek/Infusion
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play Framework
arXiv:2603.10281v1 Announce Type: new
Abstract: While score-based generative models have emerged as powerful priors for solving inverse problems, directly integrating them into optimization algorithms such as ADMM remains nontrivial. Two central challenges arise: i) the mismatch between the noisy data manifolds used to train the score functions and the geometry of ADMM iterates, especially due to the influence of dual variables, and ii) the lack of convergence understanding when ADMM is equipped with score-based denoisers. To address the manifold mismatch issue, we propose ADMM plug-and-play (ADMM-PnP) with the AC-DC denoiser, a new framework that embeds a three-stage denoiser into ADMM: (1) auto-correction (AC) via additive Gaussian noise, (2) directional correction (DC) using conditional Langevin dynamics, and (3) score-based denoising. In terms of convergence, we establish two results: first, under proper denoiser parameters, each ADMM iteration is a weakly nonexpansive operator, ensuring high-probability fixed-point $\textit{ball convergence}$ using a constant step size; second, under more relaxed conditions, the AC-DC denoiser is a bounded denoiser, which leads to convergence under an adaptive step size schedule. Experiments on a range of inverse problems demonstrate that our method consistently improves solution quality over a variety of baselines.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
GaLoRA: Parameter-Efficient Graph-Aware LLMs for Node Classification
arXiv:2603.10298v1 Announce Type: new
Abstract: The rapid rise of large language models (LLMs) and their ability to capture semantic relationships has led to their adoption in a wide range of applications. Text-attributed graphs (TAGs) are a notable example where LLMs can be combined with Graph Neural Networks to improve the performance of node classification. In TAGs, each node is associated with textual content and such graphs are commonly seen in various domains such as social networks, citation graphs, recommendation systems, etc. Effectively learning from TAGs would enable better representations of both structural and textual representations of the graph and improve decision-making in relevant domains. We present GaLoRA, a parameter-efficient framework that integrates structural information into LLMs. GaLoRA demonstrates competitive performance on node classification tasks with TAGs, performing on par with state-of-the-art models with just 0.24% of the parameter count required by full LLM fine-tuning. We experiment with three real-world datasets to showcase GaLoRA's effectiveness in combining structural and semantical information on TAGs.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training
arXiv:2603.03597v1 Announce Type: new
Abstract: The rapid progress of large language models (LLMs) is increasingly constrained by memory and deployment costs, motivating compression methods for practical deployment. Many state-of-the-art compression pipelines leverage the low-rank structure of trained weight matrices, a phenomenon often associated with the properties of popular optimizers such as Adam. In this context, Muon is a recently proposed optimizer that improves LLM pretraining via full-rank update steps, but its induced weight-space structure has not been characterized yet. In this work, we report a surprising empirical finding: despite imposing full-rank updates, Muon-trained models exhibit pronounced low-rank structure in their weight matrices and are readily compressible under standard pipelines. Motivated by this insight, we propose NuMuon, which augments Muon with a nuclear-norm constraint on the update direction, further constraining the learned weights toward low-rank structure. Across billion-parameter-scale models, we show that NuMuon increases weight compressibility and improves post-compression model quality under state-of-the-art LLM compression pipelines while retaining Muon's favorable convergence behavior.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
From Exact Hits to Close Enough: Semantic Caching for LLM Embeddings
arXiv:2603.03301v1 Announce Type: cross
Abstract: The rapid adoption of large language models (LLMs) has created demand for faster responses and lower costs. Semantic caching, reusing semantically similar requests via their embeddings, addresses this need but breaks classic cache assumptions and raises new challenges. In this paper, we explore offline policies for semantic caching, proving that implementing an optimal offline policy is NP-hard, and propose several polynomial-time heuristics. We also present online semantic aware cache policies that combine recency, frequency, and locality. Evaluations on diverse datasets show that while frequency based policies are strong baselines, our novel variant improves semantic accuracy. Our findings reveal effective strategies for current systems and highlight substantial headroom for future innovation. All code is open source.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis
arXiv:2603.03378v1 Announce Type: new
Abstract: Large language model (LLM) agents offer a promising data-driven approach to automating Site Reliability Engineering (SRE), yet their enterprise deployment is constrained by three challenges: restricted access to proprietary data, unsafe action execution under permission-governed environments, and the inability of closed systems to improve from failures. We present AOI (Autonomous Operations Intelligence), a trainable multi-agent framework formulating automated operations as a structured trajectory learning problem under security constraints. Our approach integrates three key components. First, a trainable diagnostic system applies Group Relative Policy Optimization (GRPO) to distill expert-level knowledge into locally deployed open-source models, enabling preference-based learning without exposing sensitive data. Second, a read-write separated execution architecture decomposes operational trajectories into observation, reasoning, and action phases, allowing safe learning while preventing unauthorized state mutation. Third, a Failure Trajectory Closed-Loop Evolver mines unsuccessful trajectories and converts them into corrective supervision signals, enabling continual data augmentation. Evaluated on the AIOpsLab benchmark, our contributions yield cumulative gains. (1) The AOI runtime alone achieves 66.3% best@5 success on all 86 tasks, outperforming the prior state-of-the-art (41.9%) by 24.4 points. (2) Adding Observer GRPO training, a locally deployed 14B model reaches 42.9% avg@1 on 63 held-out tasks with unseen fault types, surpassing Claude Sonnet 4.5. (3) The Evolver converts 37 failed trajectories into diagnostic guidance, improving end-to-end avg@5 by 4.8 points while reducing variance by 35%.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
A Dual-Helix Governance Approach Towards Reliable Agentic AI for WebGIS Development
arXiv:2603.04390v1 Announce Type: new
Abstract: WebGIS development requires rigor, yet agentic AI frequently fails due to five large language model (LLM) limitations: context constraints, cross-session forgetting, stochasticity, instruction failure, and adaptation rigidity. We propose a dual-helix governance framework reframing these challenges as structural governance problems that model capacity alone cannot resolve. We implement the framework as a 3-track architecture (Knowledge, Behavior, Skills) that uses a knowledge graph substrate to stabilize execution by externalizing domain facts and enforcing executable protocols, complemented by a self-learning cycle for autonomous knowledge growth. Applying this to the FutureShorelines WebGIS tool, a governed agent refactored a 2,265-line monolithic codebase into modular ES6 components. Results demonstrated a 51\% reduction in cyclomatic complexity and a 7-point increase in maintainability index. A comparative experiment against a zero-shot LLM confirms that externalized governance, not just model capability, drives operational reliability in geospatial engineering. This approach is implemented in the open-source AgentLoom governance toolkit.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Entropic-Time Inference: Self-Organizing Large Language Model Decoding Beyond Attention
arXiv:2603.03310v1 Announce Type: new
Abstract: Modern large language model (LLM) inference engines optimize throughput and latency under fixed decoding rules, treating generation as a linear progression in token time. We propose a fundamentally different paradigm: entropic\-time inference, where decoding is governed by the flow of uncertainty rather than token index. We introduce a self\-organizing inference architecture that jointly couples scheduling, attention sparsification, and sampling temperature under a unified entropy control objective. Our method extends vLLM with entropy-aware scheduling, entropic pruning of paged attention blocks, and adaptive temperature control that stabilizes generation near a target entropy regime. This transforms inference into a resource\-intelligent thermodynamic process that allocates computation where uncertainty reduction is maximized. We present a concrete systems design, pseudocode, and integration plan, demonstrating how entropy can serve as a first\-class control signal for scalable LLM inference.
Fonte: arXiv cs.CL
MLOps/Systems • Score 85
Agentics 2.0: Logical Transduction Algebra for Agentic Data Workflows
arXiv:2603.04241v1 Announce Type: new
Abstract: Agentic AI is rapidly transitioning from research prototypes to enterprise deployments, where requirements extend to meet the software quality attributes of reliability, scalability, and observability beyond plausible text generation. We present Agentics 2.0, a lightweight, Python-native framework for building high-quality, structured, explainable, and type-safe agentic data workflows. At the core of Agentics 2.0, the logical transduction algebra formalizes a large language model inference call as a typed semantic transformation, which we call a transducible function that enforces schema validity and the locality of evidence. The transducible functions compose into larger programs via algebraically grounded operators and execute as stateless asynchronous calls in parallel in asynchronous Map-Reduce programs. The proposed framework provides semantic reliability through strong typing, semantic observability through evidence tracing between slots of the input and output types, and scalability through stateless parallel execution. We instantiate reusable design patterns and evaluate the programs in Agentics 2.0 on challenging benchmarks, including DiscoveryBench for data-driven discovery and Archer for NL-to-SQL semantic parsing, demonstrating state-of-the-art performance.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents
arXiv:2603.03296v1 Announce Type: cross
Abstract: Long-term memory is essential for large language model (LLM) agents operating in complex environments, yet existing memory designs are either task-specific and non-transferable, or task-agnostic but less effective due to low task-relevance and context explosion from raw memory retrieval. We propose PlugMem, a task-agnostic plugin memory module that can be attached to arbitrary LLM agents without task-specific redesign. Motivated by the fact that decision-relevant information is concentrated as abstract knowledge rather than raw experience, we draw on cognitive science to structure episodic memories into a compact, extensible knowledge-centric memory graph that explicitly represents propositional and prescriptive knowledge. This representation enables efficient memory retrieval and reasoning over task-relevant knowledge, rather than verbose raw trajectories, and departs from other graph-based methods like GraphRAG by treating knowledge as the unit of memory access and organization instead of entities or text chunks. We evaluate PlugMem unchanged across three heterogeneous benchmarks (long-horizon conversational question answering, multi-hop knowledge retrieval, and web agent tasks). The results show that PlugMem consistently outperforms task-agnostic baselines and exceeds task-specific memory designs, while also achieving the highest information density under a unified information-theoretic analysis. Code and data are available at https://github.com/TIMAN-group/PlugMem.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
Extending Neural Operators: Robust Handling of Functions Beyond the Training Set
arXiv:2603.03621v1 Announce Type: new
Abstract: We develop a rigorous framework for extending neural operators to handle out-of-distribution input functions. We leverage kernel approximation techniques and provide theory for characterizing the input-output function spaces in terms of Reproducing Kernel Hilbert Spaces (RKHSs). We provide theorems on the requirements for reliable extensions and their predicted approximation accuracy. We also establish formal relationships between specific kernel choices and their corresponding Sobolev Native Spaces. This connection further allows the extended neural operators to reliably capture not only function values but also their derivatives. Our methods are empirically validated through the solution of elliptic partial differential equations (PDEs) involving operators on manifolds having point-cloud representations and handling geometric contributions. We report results on key factors impacting the accuracy and computational performance of the extension approaches.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
mlx-snn: Spiking Neural Networks on Apple Silicon via MLX
arXiv:2603.03529v1 Announce Type: new
Abstract: We introduce mlx-snn, the first spiking neural network (SNN) library built natively on Apple's MLX framework. As SNN research grows rapidly, all major libraries -- snnTorch, Norse, SpikingJelly, Lava -- target PyTorch or custom backends, leaving Apple Silicon users without a native option. mlx-snn provides six neuron models (LIF, IF, Izhikevich, Adaptive LIF, Synaptic, Alpha), four surrogate gradient functions, four spike encoding methods (including an EEG-specific encoder), and a complete backpropagation-through-time training pipeline. The library leverages MLX's unified memory architecture, lazy evaluation, and composable function transforms (mx.grad, mx.compile) to enable efficient SNN research on Apple Silicon hardware. We validate mlx-snn on MNIST digit classification across five hyperparameter configurations and three backends, achieving up to 97.28% accuracy with 2.0--2.5 times faster training and 3--10 times lower GPU memory than snnTorch on the same M3 Max hardware. mlx-snn is open-source under the MIT license and available on PyPI. https://github.com/D-ST-Sword/mlx-snn
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Hierarchical Inference and Closure Learning via Adaptive Surrogates for ODEs and PDEs
arXiv:2603.03922v1 Announce Type: cross
Abstract: Inverse problems are the task of calibrating models to match data. They play a pivotal role in diverse engineering applications by allowing practitioners to align models with reality. In many applications, engineers and scientists do not have a complete picture of i) the detailed properties of a system (such as material properties, geometry, initial conditions, etc.); ii) the complete laws describing all dynamics at play (such as friction laws, complicated damping phenomena, and general nonlinear interactions). In this paper, we develop a principled methodology for leveraging data from collections of distinct yet related physical systems to jointly estimate the individual model parameters of each system, and learn the shared unknown dynamics in the form of an ML-based closure model. To robustly infer the unknown parameters for each system, we employ a hierarchical Bayesian framework, which allows for the joint inference of multiple systems and their population-level statistics. To learn the closures, we use a maximum marginal likelihood estimate of a neural network embeded within the ODE/PDE formulation of the problem. To realize this framework we utilize the ensemble Metropolis-Adjusted Langevin Algorithm (MALA) for stable and efficient sampling. To mitigate the computational bottleneck of repetitive forward evaluations in solving inverse problems, we introduce a bilevel optimization strategy to simultaneously train a surrogate forward model alongside the inference. Within this framework, we evaluate and compare distinct surrogate architectures, specifically Fourier Neural Operators (FNO) and parametric Physics-Informed Neural Network (PINNs).
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
Riemannian Optimization in Modular Systems
arXiv:2603.03610v1 Announce Type: new
Abstract: Understanding how systems built out of modular components can be jointly optimized is an important problem in biology, engineering, and machine learning. The backpropagation algorithm is one such solution and has been instrumental in the success of neural networks. Despite its empirical success, a strong theoretical understanding of it is lacking. Here, we combine tools from Riemannian geometry, optimal control theory, and theoretical physics to advance this understanding.
We make three key contributions: First, we revisit the derivation of backpropagation as a constrained optimization problem and combine it with the insight that Riemannian gradient descent trajectories can be understood as the minimum of an action. Second, we introduce a recursively defined layerwise Riemannian metric that exploits the modular structure of neural networks and can be efficiently computed using the Woodbury matrix identity, avoiding the $O(n^3)$ cost of full metric inversion. Third, we develop a framework of composable ``Riemannian modules'' whose convergence properties can be quantified using nonlinear contraction theory, providing algorithmic stability guarantees of order $O(\kappa^2 L/(\xi \mu \sqrt{n}))$ where $\kappa$ and $L$ are Lipschitz constants, $\mu$ is the mass matrix scale, and $\xi$ bounds the condition number.
Our layerwise metric approach provides a practical alternative to natural gradient descent. While we focus here on studying neural networks, our approach more generally applies to the study of systems made of modules that are optimized over time, as it occurs in biology during both evolution and development.
Fonte: arXiv cs.LG
Vision • Score 85
Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning
arXiv:2603.03818v1 Announce Type: new
Abstract: Continual learning is a long-standing challenge in robot policy learning, where a policy must acquire new skills over time without catastrophically forgetting previously learned ones. While prior work has extensively studied continual learning in relatively small behavior cloning (BC) policy models trained from scratch, its behavior in modern large-scale pretrained Vision-Language-Action (VLA) models remains underexplored. In this work, we found that pretrained VLAs are remarkably resistant to forgetting compared with smaller policy models trained from scratch. Simple Experience Replay (ER) works surprisingly well on VLAs, sometimes achieving zero forgetting even with a small replay data size. Our analysis reveals that pretraining plays a critical role in downstream continual learning performance: large pretrained models mitigate forgetting with a small replay buffer size while maintaining strong forward learning capabilities. Furthermore, we found that VLAs can retain relevant knowledge from prior tasks despite performance degradation during learning new tasks. This knowledge retention enables rapid recovery of seemingly forgotten skills through finetuning. Together, these insights imply that large-scale pretraining fundamentally changes the dynamics of continual learning, enabling models to continually acquire new skills over time with simple replay. Code and more information can be found at https://ut-austin-rpl.github.io/continual-vla
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Large-Margin Hyperdimensional Computing: A Learning-Theoretical Perspective
arXiv:2603.03830v1 Announce Type: new
Abstract: Overparameterized machine learning (ML) methods such as neural networks may be prohibitively resource intensive for devices with limited computational capabilities. Hyperdimensional computing (HDC) is an emerging resource efficient and low-complexity ML method that allows hardware efficient implementations of (re-)training and inference procedures. In this paper, we propose a maximum-margin HDC classifier, which significantly outperforms baseline HDC methods on several benchmark datasets. Our method leverages a formal relation between HDC and support vector machines (SVMs) that we established for the first time. Our findings may inspire novel HDC methods with potentially more hardware-oriented implementations compared to SVMs, thus enabling more efficient learning solutions for various intelligent resource-constrained applications.
Fonte: arXiv cs.LG
Privacy/Security/Fairness • Score 90
PTOPOFL: Privacy-Preserving Personalised Federated Learning via Persistent Homology
arXiv:2603.04323v1 Announce Type: cross
Abstract: Federated learning (FL) faces two structural tensions: gradient sharing enables data-reconstruction attacks, while non-IID client distributions degrade aggregation quality. We introduce PTOPOFL, a framework that addresses both challenges simultaneously by replacing gradient communication with topological descriptors derived from persistent homology (PH). Clients transmit only 48-dimensional PH feature vectors-compact shape summaries whose many-to-one structure makes inversion provably ill-posed-rather than model gradients. The server performs topology-guided personalised aggregation: clients are clustered by Wasserstein similarity between their PH diagrams, intra-cluster models are topology-weighted,and clusters are blended with a global consensus. We prove an information-contraction theorem showing that PH descriptors leak strictly less mutual information per sample than gradients under strongly convex loss functions, and we establish linear convergence of the Wasserstein-weighted aggregation scheme with an error floor strictly smaller than FedAvg. Evaluated against FedAvg, FedProx, SCAFFOLD, and pFedMe on a non-IID healthcare scenario (8 hospitals, 2 adversarial) and a pathological benchmark (10 clients), PTOPOFL achieves AUC 0.841 and 0.910 respectively-the highest in both settings-while reducing reconstruction risk by a factor of 4.5 relative to gradient sharing. Code is publicly available at https://github.com/MorillaLab/TopoFederatedL and data at https://doi.org/10.5281/zenodo.18827595.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
Federated ADMM from Bayesian Duality
arXiv:2506.13150v4 Announce Type: replace-cross
Abstract: We propose a new Bayesian approach to generalize the federated Alternating Direction Method of Multipliers (ADMM). We show that the solutions of variational-Bayesian (VB) objectives are associated with a duality structure that not only resembles the structure of ADMM's fixed-points but also generalizes it. For example, ADMM-like updates are recovered when the VB objective is optimized over the isotropic-Gaussian family, and new non-trivial extensions are obtained for other exponential-family distributions. These extensions include a Newton-like variant that converges in one step on quadratic objectives and an Adam-like variant that yields up to 7% accuracy boosts for deep heterogeneous cases. Our work opens a new Bayesian way to generalize ADMM and other primal-dual methods.
Fonte: arXiv stat.ML
MLOps/Systems • Score 85
Vector-Quantized Soft Label Compression for Dataset Distillation
arXiv:2603.03808v1 Announce Type: new
Abstract: Dataset distillation is an emerging technique for reducing the computational and storage costs of training machine learning models by synthesizing a small, informative subset of data that captures the essential characteristics of a much larger dataset. Recent methods pair synthetic samples and their augmentations with soft labels from a teacher model, enabling student models to generalize effectively despite the small size of the distilled dataset. While soft labels are critical for effective distillation, the storage and communication overhead they incur, especially when accounting for augmentations, is often overlooked. In practice, each distilled sample is associated with multiple soft labels, making them the dominant contributor to storage costs, particularly in large-class settings such as ImageNet-1K. In this paper, we present a rigorous analysis of bit requirements across dataset distillation frameworks, quantifying the storage demands of both distilled samples and their soft labels. To address the overhead, we introduce a vector-quantized autoencoder (VQAE) for compressing soft labels, achieving substantial compression while preserving the effectiveness of the distilled data. We validate our method on both vision and language distillation benchmarks. On ImageNet-1K, our proposed VQAE achieves 30--40x additional compression over RDED, LPLD, SRE2L, and CDA baselines while retaining over $90\%$ of their original performance.
Fonte: arXiv cs.CV
RL • Score 85
When and Where to Reset Matters for Long-Term Test-Time Adaptation
arXiv:2603.03796v1 Announce Type: new
Abstract: When continual test-time adaptation (TTA) persists over the long term, errors accumulate in the model and further cause it to predict only a few classes for all inputs, a phenomenon known as model collapse. Recent studies have explored reset strategies that completely erase these accumulated errors. However, their periodic resets lead to suboptimal adaptation, as they occur independently of the actual risk of collapse. Moreover, their full resets cause catastrophic loss of knowledge acquired over time, even though such knowledge could be beneficial in the future. To this end, we propose (1) an Adaptive and Selective Reset (ASR) scheme that dynamically determines when and where to reset, (2) an importance-aware regularizer to recover essential knowledge lost due to reset, and (3) an on-the-fly adaptation adjustment scheme to enhance adaptability under challenging domain shifts. Extensive experiments across long-term TTA benchmarks demonstrate the effectiveness of our approach, particularly under challenging conditions. Our code is available at https://github.com/YonseiML/asr.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
When Small Variations Become Big Failures: Reliability Challenges in Compute-in-Memory Neural Accelerators
arXiv:2603.03491v1 Announce Type: new
Abstract: Compute-in-memory (CiM) architectures promise significant improvements in energy efficiency and throughput for deep neural network acceleration by alleviating the von Neumann bottleneck. However, their reliance on emerging non-volatile memory devices introduces device-level non-idealities-such as write variability, conductance drift, and stochastic noise-that fundamentally challenge reliability, predictability, and safety, especially in safety-critical applications. This talk examines the reliability limits of CiM-based neural accelerators and presents a series of techniques that bridge device physics, architecture, and learning algorithms to address these challenges. We first demonstrate that even small device variations can lead to disproportionately large accuracy degradation and catastrophic failures in safety-critical inference workloads, revealing a critical gap between average-case evaluations and worst-case behavior. Building on this insight, we introduce SWIM, a selective write-verify mechanism that strategically applies verification only where it is most impactful, significantly improving reliability while maintaining CiM's efficiency advantages. Finally, we explore a learning-centric solution that improves realistic worst-case performance by training neural networks with right-censored Gaussian noise, aligning training assumptions with hardware-induced variability and enabling robust deployment without excessive hardware overhead. Together, these works highlight the necessity of cross-layer co-design for CiM accelerators and provide a principled path toward dependable, efficient neural inference on emerging memory technologies-paving the way for their adoption in safety- and reliability-critical systems.
Fonte: arXiv cs.LG
Privacy/Security/Fairness • Score 85
LEA: Label Enumeration Attack in Vertical Federated Learning
arXiv:2603.03777v1 Announce Type: new
Abstract: A typical Vertical Federated Learning (VFL) scenario involves several participants collaboratively training a machine learning model, where each party has different features for the same samples, with labels held exclusively by one party. Since labels contain sensitive information, VFL must ensure the privacy of labels. However, existing VFL-targeted label inference attacks are either limited to specific scenarios or require auxiliary data, rendering them impractical in real-world applications.
We introduce a novel Label Enumeration Attack (LEA) that, for the first time, achieves applicability across multiple VFL scenarios and eschews the need for auxiliary data. Our intuition is that an adversary, employing clustering to enumerate mappings between samples and labels, ascertains the accurate label mappings by evaluating the similarity between the benign model and the simulated models trained under each mapping. To achieve that, the first challenge is how to measure model similarity, as models trained on the same data can have different weights. Drawing from our findings, we propose an efficient approach for assessing congruence based on the cosine similarity of the first-round loss gradients, which offers superior efficiency and precision compared to the comparison of parameter similarities. However, the computational cost may be prohibitive due to the necessity of training and comparing the vast number of simulated models generated through enumeration. To overcome this challenge, we propose Binary-LEA from the perspective of reducing the number of models and eliminating futile training, which lowers the number of enumerations from n! to n^3. Moreover, LEA is resilient against common defense mechanisms such as gradient noise and gradient compression.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Developing an AI Assistant for Knowledge Management and Workforce Training in State DOTs
arXiv:2603.03302v1 Announce Type: cross
Abstract: Effective knowledge management is critical for preserving institutional expertise and improving the efficiency of workforce training in state transportation agencies. Traditional approaches, such as static documentation, classroom-based instruction, and informal mentorship, often lead to fragmented knowledge transfer, inefficiencies, and the gradual loss of expertise as senior engineers retire. Moreover, given the enormous volume of technical manuals, guidelines, and research reports maintained by these agencies, it is increasingly challenging for engineers to locate relevant information quickly and accurately when solving field problems or preparing for training tasks. These limitations hinder timely decision-making and create steep learning curves for new personnel in maintenance and construction operations. To address these challenges, this paper proposes a Retrieval-Augmented Generation (RAG) framework with a multi-agent architecture to support knowledge management and decision making. The system integrates structured document retrieval with real-time, context-aware response generation powered by a large language model (LLM). Unlike conventional single-pass RAG systems, the proposed framework employs multiple specialized agents for retrieval, answer generation, evaluation, and query refinement, which enables iterative improvement and quality control. In addition, the system incorporates an open-weight vision-language model to convert technical figures into semantic textual representations, which allows figure-based knowledge to be indexed and retrieved alongside text. Retrieved text and figure-based context are then provided to an open-weight large language model, which generates the final responses grounded in the retrieved evidence.
Fonte: arXiv cs.AI
RL • Score 85
Hybrid Belief Reinforcement Learning for Efficient Coordinated Spatial Exploration
arXiv:2603.03595v1 Announce Type: new
Abstract: Coordinating multiple autonomous agents to explore and serve spatially heterogeneous demand requires jointly learning unknown spatial patterns and planning trajectories that maximize task performance. Pure model-based approaches provide structured uncertainty estimates but lack adaptive policy learning, while deep reinforcement learning often suffers from poor sample efficiency when spatial priors are absent. This paper presents a hybrid belief-reinforcement learning (HBRL) framework to address this gap. In the first phase, agents construct spatial beliefs using a Log-Gaussian Cox Process (LGCP) and execute information-driven trajectories guided by a Pathwise Mutual Information (PathMI) planner with multi-step lookahead. In the second phase, trajectory control is transferred to a Soft Actor-Critic (SAC) agent, warm-started through dual-channel knowledge transfer: belief state initialization supplies spatial uncertainty, and replay buffer seeding provides demonstration trajectories generated during LGCP exploration. A variance-normalized overlap penalty enables coordinated coverage through shared belief state, permitting cooperative sensing in high-uncertainty regions while discouraging redundant coverage in well-explored areas. The framework is evaluated on a multi-UAV wireless service provisioning task. Results show 10.8% higher cumulative reward and 38% faster convergence over baselines, with ablation studies confirming that dual-channel transfer outperforms either channel alone.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
JANUS: Structured Bidirectional Generation for Guaranteed Constraints and Analytical Uncertainty
arXiv:2603.03748v1 Announce Type: new
Abstract: High-stakes synthetic data generation faces a fundamental Quadrilemma: achieving Fidelity to the original distribution, Control over complex logical constraints, Reliability in uncertainty estimation, and Efficiency in computational cost -- simultaneously. State-of-the-art Deep Generative Models (CTGAN, TabDDPM) excel at fidelity but rely on inefficient rejection sampling for continuous range constraints. Conversely, Structural Causal Models offer logical control but struggle with high-dimensional fidelity and complex noise inversion. We introduce JANUS (Joint Ancestral Network for Uncertainty and Synthesis), a framework that unifies these capabilities using a DAG of Bayesian Decision Trees. Our key innovation is Reverse-Topological Back-filling, an algorithm that propagates constraints backwards through the causal graph, achieving 100% constraint satisfaction on feasible constraint sets without rejection sampling. This is paired with an Analytical Uncertainty Decomposition derived from Dirichlet priors, enabling 128x faster uncertainty estimation than Monte Carlo methods. Across 15 datasets and 523 constrained scenarios, JANUS achieves state-of-the-art fidelity (Detection Score 0.497), eliminates mode collapse on imbalanced data, and provides exact handling of complex inter-column constraints (e.g., Salary_offered >= Salary_requested) where baselines fail entirely.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
TAP: A Token-Adaptive Predictor Framework for Training-Free Diffusion Acceleration
arXiv:2603.03792v1 Announce Type: new
Abstract: Diffusion models achieve strong generative performance but remain slow at inference due to the need for repeated full-model denoising passes. We present Token-Adaptive Predictor (TAP), a training-free, probe-driven framework that adaptively selects a predictor for each token at every sampling step. TAP uses a single full evaluation of the model's first layer as a low-cost probe to compute proxy losses for a compact family of candidate predictors (instantiated primarily with Taylor expansions of varying order and horizon), then assigns each token the predictor with the smallest proxy error. This per-token "probe-then-select" strategy exploits heterogeneous temporal dynamics, requires no additional training, and is compatible with various predictor designs. TAP incurs negligible overhead while enabling large speedups with little or no perceptual quality loss. Extensive experiments across multiple diffusion architectures and generation tasks show that TAP substantially improves the accuracy-efficiency frontier compared to fixed global predictors and caching-only baselines.
Fonte: arXiv cs.CV
MLOps/Systems • Score 85
Optimal trajectory-guided stochastic co-optimization for e-fuel system design and real-time operation
arXiv:2603.03484v1 Announce Type: new
Abstract: E-fuels are promising long-term energy carriers supporting the net-zero transition. However, the large combinatorial design-operation spaces under renewable uncertainty make the use of mathematical programming impractical for co-optimizing e-fuel production systems. Here, we present MasCOR, a machine-learning-assisted co-optimization framework that learns from global operational trajectories. By encoding system design and renewable trends, a single MasCOR agent generalizes dynamic operation across diverse configurations and scenarios, substantially simplifying design-operation co-optimization under uncertainty. Benchmark comparisons against state-of-the-art reinforcement learning baselines demonstrate near-optimal performance, while computational costs are substantially lower than those of mathematical programming, enabling rapid parallel evaluation of designs within the co-optimization loop. This framework enables rapid screening of feasible design spaces together with corresponding operational policies. When applied to four potential European sites targeting e-methanol production, MasCOR shows that most locations benefit from reducing system load below 50 MW to achieve carbon-neutral methanol production, with production costs of 1.0-1.2 USD per kg. In contrast, Dunkirk (France), with limited renewable availability and high grid prices, favors system loads above 200 MW and expanded storage to exploit dynamic grid exchange and hydrogen sales to the market. These results underscore the value of the MasCOR framework for site-specific guidance from system design to real-time operation.
Fonte: arXiv cs.LG
Multimodal • Score 85
EvoPrune: Early-Stage Visual Token Pruning for Efficient MLLMs
arXiv:2603.03681v1 Announce Type: new
Abstract: Multimodal Large Language Models (MLLMs) have shown strong performance in vision-language tasks, but their inference efficiency is severely limited by the exponential growth of visual tokens in complex scenarios such as high-resolution images and videos. Existing visual token pruning methods mainly operate after visual encoding, overlooking the substantial computational cost incurred during the encoding stage. To address this issue, we propose EvoPrune, an early-stage visual token pruning method for MLLMs that performs pruning directly during visual encoding. Specifically, EvoPrune employs a layer-wise pruning strategy guided by token similarity, diversity, and attention-based importance to retain the most informative visual tokens at selected encoding layers. Extensive experiments on image and video benchmarks validate the effectiveness of EvoPrune. In particular, on the VideoMME dataset, EvoPrune achieves 2$\times$ inference speedup with less than 1% performance degradation, demonstrating its potential for latency-sensitive MLLM deployment.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Proact-VL: A Proactive VideoLLM for Real-Time AI Companions
arXiv:2603.03447v1 Announce Type: new
Abstract: Proactive and real-time interactive experiences are essential for human-like AI companions, yet face three key challenges: (1) achieving low-latency inference under continuous streaming inputs, (2) autonomously deciding when to respond, and (3) controlling both quality and quantity of generated content to meet real-time constraints. In this work, we instantiate AI companions through two gaming scenarios, commentator and guide, selected for their suitability for automatic evaluation. We introduce the Live Gaming Benchmark, a large-scale dataset with three representative scenarios: solo commentary, co-commentary, and user guidance, and present Proact-VL, a general framework that shapes multimodal language models into proactive, real-time interactive agents capable of human-like environment perception and interaction. Extensive experiments show Proact-VL achieves superior response latency and quality while maintaining strong video understanding capabilities, demonstrating its practicality for real-time interactive applications.
Fonte: arXiv cs.CV
Theory/Optimization • Score 85
Exploiting Subgradient Sparsity in Max-Plus Neural Networks
arXiv:2603.04133v1 Announce Type: new
Abstract: Deep Neural Networks are powerful tools for solving machine learning problems, but their training often involves dense and costly parameter updates. In this work, we use a novel Max-Plus neural architecture in which classical addition and multiplication are replaced with maximum and summation operations respectively. This is a promising architecture in terms of interpretability, but its training is challenging. A particular feature is that this algebraic structure naturally induces sparsity in the subgradients, as only neurons that contribute to the maximum affect the loss. However, standard backpropagation fails to exploit this sparsity, leading to unnecessary computations. In this work, we focus on the minimization of the worst sample loss which transfers this sparsity to the optimization loss. To address this, we propose a sparse subgradient algorithm that explicitly exploits the algebraic sparsity. By tailoring the optimization procedure to the non-smooth nature of Max-Plus models, our method achieves more efficient updates while retaining theoretical guarantees. This highlights a principled path toward bridging algebraic structure and scalable learning.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
Training-free Dropout Sampling for Semantic Token Acceptance in Speculative Decoding
arXiv:2603.03333v1 Announce Type: new
Abstract: Speculative decoding accelerates large language model inference by proposing tokens with a lightweight draft model and selectively accepting them using a target model. This work introduces DropMatch, a novel approach that matches draft tokens to the predictive distribution of the target model via Monte Carlo dropout applied exclusively to the LM head, enabling sampling-based acceptance decisions. By generating multiple decoding paths, our method forms an empirical token distribution against which draft tokens are evaluated for consistency. This acceptance mechanism enables the model to adaptively control the size of decoding paths under an appropriate dropout probability, preventing substantial distortion of the target model predictive distribution. The proposed method operates in a training-free, data-free, and calibration-free manner, requires no architectural modification to pretrained models, and can be orthogonally integrated with a wide range of existing speculative decoding and inference acceleration techniques. Experiments across multiple benchmarks demonstrate that our approach increases acceptance length while maintaining competitive task performance, yielding inference speedups ranging from 1.09x to 1.33x over the standard baseline, and up to an additional 1.09x speedup when applied on top of EAGLE3.
Fonte: arXiv cs.CL
Theory/Optimization • Score 85
HiPPO Zoo: Explicit Memory Mechanisms for Interpretable State Space Models
arXiv:2602.21340v1 Announce Type: new
Abstract: Representing the past in a compressed, efficient, and informative manner is a central problem for systems trained on sequential data. The HiPPO framework, originally proposed by Gu & Dao et al., provides a principled approach to sequential compression by projecting signals onto orthogonal polynomial (OP) bases via structured linear ordinary differential equations. Subsequent works have embedded these dynamics in state space models (SSMs), where HiPPO structure serves as an initialization. Nonlinear successors of these SSM methods such as Mamba are state-of-the-art for many tasks with long-range dependencies, but the mechanisms by which they represent and prioritize history remain largely implicit. In this work, we revisit the HiPPO framework with the goal of making these mechanisms explicit. We show how polynomial representations of history can be extended to support capabilities of modern SSMs such as adaptive allocation of memory and associative memory while retaining direct interpretability in the OP basis. We introduce a unified framework comprising five such extensions, which we collectively refer to as a "HiPPO zoo." Each extension exposes a specific modeling capability through an explicit, interpretable modification of the HiPPO framework. The resulting models adapt their memory online and train in streaming settings with efficient updates. We illustrate the behaviors and modeling advantages of these extensions through a range of synthetic sequence modeling tasks, demonstrating that capabilities typically associated with modern SSMs can be realized through explicit, interpretable polynomial memory structures.
Fonte: arXiv cs.LG
Vision • Score 85
Automating Timed Up and Go Phase Segmentation and Gait Analysis via the tugturn Markerless 3D Pipeline
arXiv:2602.21425v1 Announce Type: new
Abstract: Instrumented Timed Up and Go (TUG) analysis can support clinical and research decision-making, but robust and reproducible markerless pipelines are still limited. We present \textit{tugturn.py}, a Python-based workflow for 3D markerless TUG processing that combines phase segmentation, gait-event detection, spatiotemporal metrics, intersegmental coordination, and dynamic stability analysis. The pipeline uses spatial thresholds to segment each trial into stand, first gait, turning, second gait, and sit phases, and applies a relative-distance strategy to detect heel-strike and toe-off events within valid gait windows. In addition to conventional kinematics, \textit{tugturn} provides Vector Coding outputs and Extrapolated Center of Mass (XCoM)-based metrics. The software is configured through TOML files and produces reproducible artifacts, including HTML reports, CSV tables, and quality-assurance visual outputs. A complete runnable example is provided with test data and command-line instructions. This manuscript describes the implementation, outputs, and reproducibility workflow of \textit{tugturn} as a focused software contribution for markerless biomechanical TUG analysis.
Fonte: arXiv cs.CV
Privacy/Security/Fairness • Score 85
Private Blind Model Averaging - Distributed, Non-interactive, and Convergent
arXiv:2211.02003v3 Announce Type: replace-cross
Abstract: Distributed differentially private learning techniques enable a large number of users to jointly learn a model without having to first centrally collect the training data. At the same time, neither the communication between the users nor the resulting model shall leak information about the training data. This kind of learning technique can be deployed to edge devices if it can be scaled up to a large number of users, particularly if the communication is reduced to a minimum: no interaction, i.e., each party only sends a single message. The best previously known methods are based on gradient averaging, which inherently requires many synchronization rounds. A promising non-interactive alternative to gradient averaging relies on so-called output perturbation: each user first locally finishes training and then submits its model for secure averaging without further synchronization. We analyze this paradigm, which we coin blind model averaging (BlindAvg), in the setting of convex and smooth empirical risk minimization (ERM) like a support vector machine (SVM). While the required noise scale is asymptotically the same as in the centralized setting, it is not well understood how close BlindAvg comes to centralized learning, i.e., its utility cost. We characterize and boost the privacy-utility tradeoff of BlindAvg with two contributions: First, we prove that BlindAvg converges towards the centralized setting for a sufficiently strong L2-regularization for a non-smooth SVM learner. Second, we introduce the novel differentially private convex and smooth ERM learner SoftmaxReg that has a better privacy-utility tradeoff than an SVM in a multi-class setting. We evaluate our findings on three datasets (CIFAR-10, CIFAR-100, and Federated EMNIST) and provide an ablation in an artificially extreme non-IID scenario.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
NGDB-Zoo: Towards Efficient and Scalable Neural Graph Databases Training
arXiv:2602.21597v1 Announce Type: new
Abstract: Neural Graph Databases (NGDBs) facilitate complex logical reasoning over incomplete knowledge structures, yet their training efficiency and expressivity are constrained by rigid query-level batching and structure-exclusive embeddings. We present NGDB-Zoo, a unified framework that resolves these bottlenecks by synergizing operator-level training with semantic augmentation. By decoupling logical operators from query topologies, NGDB-Zoo transforms the training loop into a dynamically scheduled data-flow execution, enabling multi-stream parallelism and achieving a $1.8\times$ - $6.8\times$ throughput compared to baselines. Furthermore, we formalize a decoupled architecture to integrate high-dimensional semantic priors from Pre-trained Text Encoders (PTEs) without triggering I/O stalls or memory overflows. Extensive evaluations on six benchmarks, including massive graphs like ogbl-wikikg2 and ATLAS-Wiki, demonstrate that NGDB-Zoo maintains high GPU utilization across diverse logical patterns and significantly mitigates representation friction in hybrid neuro-symbolic reasoning.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
AgenticTyper: Automated Typing of Legacy Software Projects Using Agentic AI
arXiv:2602.21251v1 Announce Type: cross
Abstract: Legacy JavaScript systems lack type safety, making maintenance risky. While TypeScript can help, manually adding types is expensive. Previous automated typing research focuses on type inference but rarely addresses type checking setup, definition generation, bug identification, or behavioral correctness at repository scale. We present AgenticTyper, a Large Language Model (LLM)-based agentic system that addresses these gaps through iterative error correction and behavior preservation via transpilation comparison. Evaluation on two proprietary repositories (81K LOC) shows that AgenticTyper resolves all 633 initial type errors in 20 minutes, reducing manual effort from one working day.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
ABM-UDE: Developing Surrogates for Epidemic Agent-Based Models via Scientific Machine Learning
arXiv:2602.21588v1 Announce Type: new
Abstract: Agent-based epidemic models (ABMs) encode behavioral and policy heterogeneity but are too slow for nightly hospital planning. We develop county-ready surrogates that learn directly from exascale ABM trajectories using Universal Differential Equations (UDEs): mechanistic SEIR-family ODEs with a neural-parameterized contact rate $\kappa_\phi(u,t)$ (no additive residual). Our contributions are threefold: we adapt multiple shooting and an observer-based prediction-error method (PEM) to stabilize identification of neural-augmented epidemiological dynamics across intervention-driven regime shifts; we enforce positivity and mass conservation and show the learned contact-rate parameterization yields a well-posed vector field; and we quantify accuracy, calibration, and compute against ABM ensembles and UDE baselines. On a representative ExaEpi scenario, PEM-UDE reduces mean MSE by 77% relative to single-shooting UDE (3.00 vs. 13.14) and by 20% relative to MS-UDE (3.75). Reliability improves in parallel: empirical coverage of ABM $10$-$90$% and $25$-$75$% bands rises from 0.68/0.43 (UDE) and 0.79/0.55 (MS-UDE) to 0.86/0.61 with PEM-UDE and 0.94/0.69 with MS+PEM-UDE, indicating calibrated uncertainty rather than overconfident fits. Inference runs in seconds on commodity CPUs (20-35 s per $\sim$90-day forecast), enabling nightly ''what-if'' sweeps on a laptop. Relative to a $\sim$100 CPU-hour ABM reference run, this yields $\sim10^{4}\times$ lower wall-clock per scenario. This closes the realism-cadence gap, supports threshold-aware decision-making (e.g., maintaining ICU occupancy $<75$%), preserves mechanistic interpretability, and enables calibrated, risk-aware scenario planning on standard institutional hardware. Beyond epidemics, the ABM$\to$UDE recipe provides a portable path to distill agent-based simulators into fast, trustworthy surrogates for other scientific domains.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Mamba Meets Scheduling: Learning to Solve Flexible Job Shop Scheduling with Efficient Sequence Modeling
arXiv:2602.21546v1 Announce Type: new
Abstract: The Flexible Job Shop Problem (FJSP) is a well-studied combinatorial optimization problem with extensive applications for manufacturing and production scheduling. It involves assigning jobs to various machines to optimize criteria, such as minimizing total completion time. Current learning-based methods in this domain often rely on localized feature extraction models, limiting their capacity to capture overarching dependencies spanning operations and machines. This paper introduces an innovative architecture that harnesses Mamba, a state-space model with linear computational complexity, to facilitate comprehensive sequence modeling tailored for FJSP. In contrast to prevalent graph-attention-based frameworks that are computationally intensive for FJSP, we show our model is more efficient. Specifically, the proposed model possesses an encoder and a decoder. The encoder incorporates a dual Mamba block to extract operation and machine features separately. Additionally, we introduce an efficient cross-attention decoder to learn interactive embeddings of operations and machines. Our experimental results demonstrate that our method achieves faster solving speed and surpasses the performance of state-of-the-art learning-based methods for FJSP across various benchmarks.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Defensive Generation
arXiv:2602.21390v1 Announce Type: new
Abstract: We study the problem of efficiently producing, in an online fashion, generative models of scalar, multiclass, and vector-valued outcomes that cannot be falsified on the basis of the observed data and a pre-specified collection of computational tests. Our contributions are twofold. First, we expand on connections between online high-dimensional multicalibration with respect to an RKHS and recent advances in expected variational inequality problems, enabling efficient algorithms for the former. We then apply this algorithmic machinery to the problem of outcome indistinguishability. Our procedure, Defensive Generation, is the first to efficiently produce online outcome indistinguishable generative models of non-Bernoulli outcomes that are unfalsifiable with respect to infinite classes of tests, including those that examine higher-order moments of the generated distributions. Furthermore, our method runs in near-linear time in the number of samples and achieves the optimal, vanishing T^{-1/2} rate for generation error.
Fonte: arXiv cs.LG
MLOps/Systems • Score 85
Learning Unknown Interdependencies for Decentralized Root Cause Analysis in Nonlinear Dynamical Systems
arXiv:2602.21928v1 Announce Type: cross
Abstract: Root cause analysis (RCA) in networked industrial systems, such as supply chains and power networks, is notoriously difficult due to unknown and dynamically evolving interdependencies among geographically distributed clients. These clients represent heterogeneous physical processes and industrial assets equipped with sensors that generate large volumes of nonlinear, high-dimensional, and heterogeneous IoT data. Classical RCA methods require partial or full knowledge of the system's dependency graph, which is rarely available in these complex networks. While federated learning (FL) offers a natural framework for decentralized settings, most existing FL methods assume homogeneous feature spaces and retrainable client models. These assumptions are not compatible with our problem setting. Different clients have different data features and often run fixed, proprietary models that cannot be modified. This paper presents a federated cross-client interdependency learning methodology for feature-partitioned, nonlinear time-series data, without requiring access to raw sensor streams or modifying proprietary client models. Each proprietary local client model is augmented with a Machine Learning (ML) model that encodes cross-client interdependencies. These ML models are coordinated via a global server that enforces representation consistency while preserving privacy through calibrated differential privacy noise. RCA is performed using model residuals and anomaly flags. We establish theoretical convergence guarantees and validate our approach on extensive simulations and a real-world industrial cybersecurity dataset.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
Urban Vibrancy Embedding and Application on Traffic Prediction
arXiv:2602.21232v1 Announce Type: cross
Abstract: Urban vibrancy reflects the dynamic human activity within urban spaces and is often measured using mobile data that captures floating population trends. This study proposes a novel approach to derive Urban Vibrancy embeddings from real-time floating population data to enhance traffic prediction models. Specifically, we utilize variational autoencoders (VAE) to compress this data into actionable embeddings, which are then integrated with long short-term memory (LSTM) networks to predict future embeddings. These are subsequently applied in a sequence-to-sequence framework for traffic forecasting. Our contributions are threefold: (1) We use principal component analysis (PCA) to interpret the embeddings, revealing temporal patterns such as weekday versus weekend distinctions and seasonal patterns; (2) We propose a method that combines VAE and LSTM, enabling forecasting dynamic urban knowledge embedding; and (3) Our approach improves accuracy and responsiveness in traffic prediction models, including RNN, DCRNN, GTS, and GMAN. This study demonstrates the potential of Urban Vibrancy embeddings to advance traffic prediction and offer a more nuanced analysis of urban mobility.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Highly Efficient and Effective LLMs with Multi-Boolean Architectures
arXiv:2505.22811v3 Announce Type: replace
Abstract: Weight binarization has emerged as a promising strategy to reduce the complexity of large language models (LLMs). Existing approaches fall into post-training binarization, which is simple but causes severe performance loss, and training-aware methods, which depend on full-precision latent weights, adding complexity and limiting efficiency. We propose a novel framework that represents LLMs with multi-kernel Boolean parameters and, for the first time, enables direct finetuning LMMs in the Boolean domain, eliminating the need for latent weights. This enhances representational capacity and dramatically reduces complexity during both finetuning and inference. Extensive experiments across diverse LLMs show our method outperforms recent ultra low-bit quantization and binarization techniques.
Fonte: arXiv stat.ML
MLOps/Systems • Score 85
AngelSlim: A more accessible, comprehensive, and efficient toolkit for large model compression
arXiv:2602.21233v1 Announce Type: cross
Abstract: This technical report introduces AngelSlim, a comprehensive and versatile toolkit for large model compression developed by the Tencent Hunyuan team. By consolidating cutting-edge algorithms, including quantization, speculative decoding, token pruning, and distillation. AngelSlim provides a unified pipeline that streamlines the transition from model compression to industrial-scale deployment. To facilitate efficient acceleration, we integrate state-of-the-art FP8 and INT8 Post-Training Quantization (PTQ) algorithms alongside pioneering research in ultra-low-bit regimes, featuring HY-1.8B-int2 as the first industrially viable 2-bit large model. Beyond quantization, we propose a training-aligned speculative decoding framework compatible with multimodal architectures and modern inference engines, achieving 1.8x to 2.0x throughput gains without compromising output correctness. Furthermore, we develop a training-free sparse attention framework that reduces Time-to-First-Token (TTFT) in long-context scenarios by decoupling sparse kernels from model architectures through a hybrid of static patterns and dynamic token selection. For multimodal models, AngelSlim incorporates specialized pruning strategies, namely IDPruner for optimizing vision tokens via Maximal Marginal Relevance and Samp for adaptive audio token merging and pruning. By integrating these compression strategies from low-level implementations, AngelSlim enables algorithm-focused research and tool-assisted deployment.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Latent Context Compilation: Distilling Long Context into Compact Portable Memory
arXiv:2602.21221v1 Announce Type: cross
Abstract: Efficient long-context LLM deployment is stalled by a dichotomy between amortized compression, which struggles with out-of-distribution generalization, and Test-Time Training, which incurs prohibitive synthetic data costs and requires modifying model weights, creating stateful parameters that complicate concurrent serving. We propose Latent Context Compilation, a framework that fundamentally shifts context processing from adaptation to compilation. By utilizing a disposable LoRA module as a compiler, we distill long contexts into compact buffer tokens -- stateless, portable memory artifacts that are plug-and-play compatible with frozen base models. Crucially, we introduce a self-aligned optimization strategy that eliminates the need for synthetic context-relevant QA pairs. By regularizing context reconstruction task with context-agnostic random queries, we force compressed tokens to reside within the model's existing instruction-following manifold. Experiments with Llama-3.1-8B demonstrate that Latent Context Compilation preserves fine-grained details and reasoning capabilities where prior methods falter, effectively decoupling memory density from model parameters even at a 16x compression ratio.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
Conditional neural control variates for variance reduction in Bayesian inverse problems
arXiv:2602.21357v1 Announce Type: new
Abstract: Bayesian inference for inverse problems involves computing expectations under posterior distributions -- e.g., posterior means, variances, or predictive quantities -- typically via Monte Carlo (MC) estimation. When the quantity of interest varies significantly under the posterior, accurate estimates demand many samples -- a cost often prohibitive for partial differential equation-constrained problems. To address this challenge, we introduce conditional neural control variates, a modular method that learns amortized control variates from joint model-data samples to reduce the variance of MC estimators. To scale to high-dimensional problems, we leverage Stein's identity to design an architecture based on an ensemble of hierarchical coupling layers with tractable Jacobian trace computation. Training requires: (i) samples from the joint distribution of unknown parameters and observed data; and (ii) the posterior score function, which can be computed from physics-based likelihood evaluations, neural operator surrogates, or learned generative models such as conditional normalizing flows. Once trained, the control variates generalize across observations without retraining. We validate our approach on stylized and partial differential equation-constrained Darcy flow inverse problems, demonstrating substantial variance reduction, even when the analytical score is replaced by a learned surrogate.
Fonte: arXiv stat.ML
Theory/Optimization • Score 85
Asymptotically Fast Clebsch-Gordan Tensor Products with Vector Spherical Harmonics
arXiv:2602.21466v1 Announce Type: new
Abstract: $E(3)$-equivariant neural networks have proven to be effective in a wide range of 3D modeling tasks. A fundamental operation of such networks is the tensor product, which allows interaction between different feature types. Because this operation scales poorly, there has been considerable work towards accelerating this interaction. However, recently \citet{xieprice} have pointed out that most speedups come from a reduction in expressivity rather than true algorithmic improvements on computing Clebsch-Gordan tensor products. A modification of Gaunt tensor product \citep{gaunt} can give a true asymptotic speedup but is incomplete and misses many interactions. In this work, we provide the first complete algorithm which truly provides asymptotic benefits Clebsch-Gordan tensor products. For full CGTP, our algorithm brings runtime complexity from the naive $O(L^6)$ to $O(L^4\log^2 L)$, close to the lower bound of $O(L^4)$. We first show how generalizing fast Fourier based convolution naturally leads to the previously proposed Gaunt tensor product \citep{gaunt}. To remedy antisymmetry issues, we generalize from scalar signals to irrep valued signals, giving us tensor spherical harmonics. We prove a generalized Gaunt formula for the tensor harmonics. Finally, we show that we only need up to vector valued signals to recover the missing interactions of Gaunt tensor product.
Fonte: arXiv cs.LG
Theory/Optimization • Score 85
Dynamic Symmetric Point Tracking: Tackling Non-ideal Reference in Analog In-memory Training
arXiv:2602.21321v1 Announce Type: new
Abstract: Analog in-memory computing (AIMC) performs computation directly within resistive crossbar arrays, offering an energy-efficient platform to scale large vision and language models. However, non-ideal analog device properties make the training on AIMC devices challenging. In particular, its update asymmetry can induce a systematic drift of weight updates towards a device-specific symmetric point (SP), which typically does not align with the optimum of the training objective. To mitigate this bias, most existing works assume the SP is known and pre-calibrate it to zero before training by setting the reference point as the SP. Nevertheless, calibrating AIMC devices requires costly pulse updates, and residual calibration error can directly degrade training accuracy. In this work, we present the first theoretical characterization of the pulse complexity of SP calibration and the resulting estimation error. We further propose a dynamic SP estimation method that tracks the SP during model training, and establishes its convergence guarantees. In addition, we develop an enhanced variant based on chopping and filtering techniques from digital signal processing. Numerical experiments demonstrate both the efficiency and effectiveness of the proposed method.
Fonte: arXiv cs.LG
NLP/LLMs • Score 85
Budget-Aware Agentic Routing via Boundary-Guided Training
arXiv:2602.21227v1 Announce Type: cross
Abstract: As large language models (LLMs) evolve into autonomous agents that execute long-horizon workflows, invoking a high-capability model at every step becomes economically unsustainable. While model routing is effective for single-turn queries, agentic routing is a sequential, path-dependent problem: early mistakes compound, feedback is often at the end of the episode, and deployments often demand strict per-task spending limits. We propose Budget-Aware Agentic Routing, which selects between a cheap and an expensive model at each step to optimize the cost--success frontier and to operate under strict per-task budgets. We propose Boundary-Guided Training, which leverages two boundary policies (always-small vs.\ always-large) to build a difficulty taxonomy and to anchor learning under sparse rewards. Our approach warms start with boundary-guided SFT data synthesis via stratified sampling of cost-efficient trajectories, then applies Boundary-Guided Policy Optimization (BoPO), combining boundary-relative rewards with a reference-guided advantage to avoid degenerate cheap-failure solutions. Experiment results show that our method improves the efficiency frontier, matching strong routing baselines at substantially lower cost while demonstrating generalization to strict inference-time budget constraints. Overall, our work establishes a foundational framework for agentic routing, shifting the paradigm from static model selection to dynamic, budget-aware sequential decision-making.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Structured Prompt Language: Declarative Context Management for LLMs
arXiv:2602.21257v1 Announce Type: new
Abstract: We present SPL (Structured Prompt Language), a declarative SQL-inspired language that treats large language models as generative knowledge bases and their context windows as constrained resources. SPL provides explicit WITH BUDGET/LIMIT token management, an automatic query optimizer, EXPLAIN transparency analogous to SQL's EXPLAIN ANALYZE, and native integration of retrieval-augmented generation (RAG) and persistent memory in a single declarative framework. SPL-flow extends SPL into resilient agentic pipelines with a three-tier provider fallback strategy (Ollama -> OpenRouter -> self-healing retry) fully transparent to the .spl script. Five extensions demonstrate the paradigm's breadth: (1) Text2SPL (multilingual NL->SPL translation); (2) Mixture-of-Models (MoM) routing that dispatches each PROMPT to a domain-specialist model at runtime; (3) Logical Chunking, an intelligent strategy for documents exceeding a single context window--expressed naturally through SPL's existing CTE syntax with no new constructs, decomposing a large query into a Map-Reduce pipeline that reduces attention cost from O(N^2) to O(N^2/k) and runs identically on cloud (parallel) or local hardware (sequential); (4) SPL-flow, a declarative agentic orchestration layer with resilient three-tier provider fallback; and (5) BENCHMARK for parallel multi-model comparison with automatic winner persistence. We provide a formal EBNF grammar, two pip-installable Python packages (spl-llm, spl-flow), and comparison against Prompty, DSPy, and LMQL. SPL reduces prompt boilerplate by 65% on average, surfaces a 68x cost spread across model tiers as a pre-execution signal, and runs the identical .spl script at $0.002 on OpenRouter or at zero marginal cost on a local Ollama instance--without modification.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
FedVG: Gradient-Guided Aggregation for Enhanced Federated Learning
arXiv:2602.21399v1 Announce Type: cross
Abstract: Federated Learning (FL) enables collaborative model training across multiple clients without sharing their private data. However, data heterogeneity across clients leads to client drift, which degrades the overall generalization performance of the model. This effect is further compounded by overemphasis on poorly performing clients. To address this problem, we propose FedVG, a novel gradient-based federated aggregation framework that leverages a global validation set to guide the optimization process. Such a global validation set can be established using readily available public datasets, ensuring accessibility and consistency across clients without compromising privacy. In contrast to conventional approaches that prioritize client dataset volume, FedVG assesses the generalization ability of client models by measuring the magnitude of validation gradients across layers. Specifically, we compute layerwise gradient norms to derive a client-specific score that reflects how much each client needs to adjust for improved generalization on the global validation set, thereby enabling more informed and adaptive federated aggregation. Extensive experiments on both natural and medical image benchmarking datasets, across diverse model architectures, demonstrate that FedVG consistently improves performance, particularly in highly heterogeneous settings. Moreover, FedVG is modular and can be seamlessly integrated with various state-of-the-art FL algorithms, often further improving their results. Our code is available at https://github.com/alinadevkota/FedVG.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
The Mean is the Mirage: Entropy-Adaptive Model Merging under Heterogeneous Domain Shifts in Medical Imaging
arXiv:2602.21372v1 Announce Type: cross
Abstract: Model merging under unseen test-time distribution shifts often renders naive strategies, such as mean averaging unreliable. This challenge is especially acute in medical imaging, where models are fine-tuned locally at clinics on private data, producing domain-specific models that differ by scanner, protocol, and population. When deployed at an unseen clinical site, test cases arrive in unlabeled, non-i.i.d. batches, and the model must adapt immediately without labels. In this work, we introduce an entropy-adaptive, fully online model-merging method that yields a batch-specific merged model via only forward passes, effectively leveraging target information. We further demonstrate why mean merging is prone to failure and misaligned under heterogeneous domain shifts. Next, we mitigate encoder classifier mismatch by decoupling the encoder and classification head, merging with separate merging coefficients. We extensively evaluate our method with state-of-the-art baselines using two backbones across nine medical and natural-domain generalization image classification datasets, showing consistent gains across standard evaluation and challenging scenarios. These performance gains are achieved while retaining single-model inference at test-time, thereby demonstrating the effectiveness of our method.
Fonte: arXiv cs.AI
Evaluation/Benchmarks • Score 85
Black-Box Reliability Certification for AI Agents via Self-Consistency Sampling and Conformal Calibration
arXiv:2602.21368v1 Announce Type: cross
Abstract: Given a black-box AI system and a task, at what confidence level can a practitioner trust the system's output? We answer with a reliability level -- a single number per system-task pair, derived from self-consistency sampling and conformal calibration, that serves as a black-box deployment gate with exact, finite-sample, distribution-free guarantees. Self-consistency sampling reduces uncertainty exponentially; conformal calibration guarantees correctness within 1/(n+1) of the target level, regardless of the system's errors -- made transparently visible through larger answer sets for harder questions. Weaker models earn lower reliability levels (not accuracy -- see Definition 2.4): GPT-4.1 earns 94.6% on GSM8K and 96.8% on TruthfulQA, while GPT-4.1-nano earns 89.8% on GSM8K and 66.5% on MMLU. We validate across five benchmarks, five models from three families, and both synthetic and real data. Conditional coverage on solvable items exceeds 0.93 across all configurations; sequential stopping reduces API costs by around 50%.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
Neural solver for Wasserstein Geodesics and optimal transport dynamics
arXiv:2602.22003v1 Announce Type: cross
Abstract: In recent years, the machine learning community has increasingly embraced the optimal transport (OT) framework for modeling distributional relationships. In this work, we introduce a sample-based neural solver for computing the Wasserstein geodesic between a source and target distribution, along with the associated velocity field. Building on the dynamical formulation of the optimal transport (OT) problem, we recast the constrained optimization as a minimax problem, using deep neural networks to approximate the relevant functions. This approach not only provides the Wasserstein geodesic but also recovers the OT map, enabling direct sampling from the target distribution. By estimating the OT map, we obtain velocity estimates along particle trajectories, which in turn allow us to learn the full velocity field. The framework is flexible and readily extends to general cost functions, including the commonly used quadratic cost. We demonstrate the effectiveness of our method through experiments on both synthetic and real datasets.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
MrBERT: Modern Multilingual Encoders via Vocabulary, Domain, and Dimensional Adaptation
arXiv:2602.21379v1 Announce Type: cross
Abstract: We introduce MrBERT, a family of 150M-300M parameter encoders built on the ModernBERT architecture and pre-trained on 35 languages and code. Through targeted adaptation, this model family achieves state-of-the-art results on Catalan- and Spanish-specific tasks, while establishing robust performance across specialized biomedical and legal domains. To bridge the gap between research and production, we incorporate Matryoshka Representation Learning (MRL), enabling flexible vector sizing that significantly reduces inference and storage costs. Ultimately, the MrBERT family demonstrates that modern encoder architectures can be optimized for both localized linguistic excellence and efficient, high-stakes domain specialization. We open source the complete model family on Huggingface.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation
arXiv:2602.21397v1 Announce Type: new
Abstract: Prompt learning has become a dominant paradigm for adapting vision-language models (VLMs) such as CLIP to downstream tasks without modifying pretrained weights. While extending prompts to both vision and text encoders across multiple transformer layers significantly boosts performance, it dramatically increases the number of trainable parameters, with state-of-the-art methods requiring millions of parameters and abandoning the parameter efficiency that makes prompt tuning attractive. In this work, we propose \textbf{MMLoP} (\textbf{M}ulti-\textbf{M}odal \textbf{Lo}w-Rank \textbf{P}rompting), a framework that achieves deep multi-modal prompting with only \textbf{11.5K trainable parameters}, comparable to early text-only methods like CoOp. MMLoP parameterizes vision and text prompts at each transformer layer through a low-rank factorization, which serves as an implicit regularizer against overfitting on few-shot training data. To further close the accuracy gap with state-of-the-art methods, we introduce three complementary components: a self-regulating consistency loss that anchors prompted representations to frozen zero-shot CLIP features at both the feature and logit levels, a uniform drift correction that removes the global embedding shift induced by prompt tuning to preserve class-discriminative structure, and a shared up-projection that couples vision and text prompts through a common low-rank factor to enforce cross-modal alignment. Extensive experiments across three benchmarks and 11 diverse datasets demonstrate that MMLoP achieves a highly favorable accuracy-efficiency tradeoff, outperforming the majority of existing methods including those with orders of magnitude more parameters, while achieving a harmonic mean of 79.70\% on base-to-novel generalization.
Fonte: arXiv cs.CV
NLP/LLMs • Score 85
Make Every Draft Count: Hidden State based Speculative Decoding
arXiv:2602.21224v1 Announce Type: cross
Abstract: Speculative decoding has emerged as a pivotal technique to accelerate LLM inference by employing a lightweight draft model to generate candidate tokens that are subsequently verified by the target model in parallel. However, while this paradigm successfully increases the arithmetic intensity of memory-bound inference, it causes significant compute inefficiency: the majority of draft tokens fail verification and are discarded, resulting in waste of computation. Motivated by the goal of recollecting this wasted computation, we propose a novel system that transforms discarded drafts into reusable tokens. Our key insight is to perform auto-regressive prediction at the hidden states level and postpone the integrating token information after the hidden states generation, so the draft hidden states are not contaminated by incorrect tokens, enabling hidden state reuse. To implement such a system, first we introduce a draft model architecture based on auto-regressive hidden states, which preserves richer semantics than token-based drafters to facilitate draft repurposing. Second, we design an efficient token information injection mechanism that leverages our specialized draft model to construct high-quality draft token trees and enables resampling tokens from verification failures. Third, we eliminate the overhead hidden in our design to further maximize hardware utilization. We conducted extensive evaluations against various baselines, demonstrating up to a 3.3x speedup against standard speculative decoding.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
A Hierarchical Multi-Agent System for Autonomous Discovery in Geoscientific Data Archives
arXiv:2602.21351v1 Announce Type: new
Abstract: The rapid accumulation of Earth science data has created a significant scalability challenge; while repositories like PANGAEA host vast collections of datasets, citation metrics indicate that a substantial portion remains underutilized, limiting data reusability. Here we present PANGAEA-GPT, a hierarchical multi-agent framework designed for autonomous data discovery and analysis. Unlike standard Large Language Model (LLM) wrappers, our architecture implements a centralized Supervisor-Worker topology with strict data-type-aware routing, sandboxed deterministic code execution, and self-correction via execution feedback, enabling agents to diagnose and resolve runtime errors. Through use-case scenarios spanning physical oceanography and ecology, we demonstrate the system's capacity to execute complex, multi-step workflows with minimal human intervention. This framework provides a methodology for querying and analyzing heterogeneous repository data through coordinated agent workflows.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Scaling View Synthesis Transformers
arXiv:2602.21341v1 Announce Type: cross
Abstract: Geometry-free view synthesis transformers have recently achieved state-of-the-art performance in Novel View Synthesis (NVS), outperforming traditional approaches that rely on explicit geometry modeling. Yet the factors governing their scaling with compute remain unclear. We present a systematic study of scaling laws for view synthesis transformers and derive design principles for training compute-optimal NVS models. Contrary to prior findings, we show that encoder-decoder architectures can be compute-optimal; we trace earlier negative results to suboptimal architectural choices and comparisons across unequal training compute budgets. Across several compute levels, we demonstrate that our encoder-decoder architecture, which we call the Scalable View Synthesis Model (SVSM), scales as effectively as decoder-only models, achieves a superior performance-compute Pareto frontier, and surpasses the previous state-of-the-art on real-world NVS benchmarks with substantially reduced training compute.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
CADC: Content Adaptive Diffusion-Based Generative Image Compression
arXiv:2602.21591v1 Announce Type: new
Abstract: Diffusion-based generative image compression has demonstrated remarkable potential for achieving realistic reconstruction at ultra-low bitrates. The key to unlocking this potential lies in making the entire compression process content-adaptive, ensuring that the encoder's representation and the decoder's generative prior are dynamically aligned with the semantic and structural characteristics of the input image. However, existing methods suffer from three critical limitations that prevent effective content adaptation. First, isotropic quantization applies a uniform quantization step, failing to adapt to the spatially varying complexity of image content and creating a misalignment with the diffusion model's noise-dependent prior. Second, the information concentration bottleneck -- arising from the dimensional mismatch between the high-dimensional noisy latent and the diffusion decoder's fixed input -- prevents the model from adaptively preserving essential semantic information in the primary channels. Third, existing textual conditioning strategies either need significant textual bitrate overhead or rely on generic, content-agnostic textual prompts, thereby failing to provide adaptive semantic guidance efficiently. To overcome these limitations, we propose a content-adaptive diffusion-based image codec with three technical innovations: 1) an Uncertainty-Guided Adaptive Quantization method that learns spatial uncertainty maps to adaptively align quantization distortion with content characteristics; 2) an Auxiliary Decoder-Guided Information Concentration method that uses a lightweight auxiliary decoder to enforce content-aware information preservation in the primary latent channels; and 3) a Bitrate-Free Adaptive Textual Conditioning method that derives content-aware textual descriptions from the auxiliary reconstructed image, enabling semantic guidance without bitrate cost.
Fonte: arXiv cs.CV
Vision • Score 85
UniHand: A Unified Model for Diverse Controlled 4D Hand Motion Modeling
arXiv:2602.21631v1 Announce Type: new
Abstract: Hand motion plays a central role in human interaction, yet modeling realistic 4D hand motion (i.e., 3D hand pose sequences over time) remains challenging. Research in this area is typically divided into two tasks: (1) Estimation approaches reconstruct precise motion from visual observations, but often fail under hand occlusion or absence; (2) Generation approaches focus on synthesizing hand poses by exploiting generative priors under multi-modal structured inputs and infilling motion from incomplete sequences. However, this separation not only limits the effective use of heterogeneous condition signals that frequently arise in practice, but also prevents knowledge transfer between the two tasks. We present UniHand, a unified diffusion-based framework that formulates both estimation and generation as conditional motion synthesis. UniHand integrates heterogeneous inputs by embedding structured signals into a shared latent space through a joint variational autoencoder, which aligns conditions such as MANO parameters and 2D skeletons. Visual observations are encoded with a frozen vision backbone, while a dedicated hand perceptron extracts hand-specific cues directly from image features, removing the need for complex detection and cropping pipelines. A latent diffusion model then synthesizes consistent motion sequences from these diverse conditions. Extensive experiments across multiple benchmarks demonstrate that UniHand delivers robust and accurate hand motion modeling, maintaining performance under severe occlusions and temporally incomplete inputs.
Fonte: arXiv cs.CV
Privacy/Security/Fairness • Score 85
EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors
arXiv:2602.21218v1 Announce Type: cross
Abstract: High-quality data is essential for modern machine learning, yet many valuable corpora are sensitive and cannot be freely shared. Synthetic data offers a practical substitute for downstream development, and large language models (LLMs) have emerged as powerful engines for generating it. However, existing private text generation methods are severely inefficient: they are data-intensive, computationally slow, and often require large private corpora or batch sizes to achieve usable quality. We introduce EPSVec, a differentially-private lightweight alternative that steers LLM generation using *dataset vectors*--directions in activation space that capture the distributional gap between private data and public priors. EPSVec extracts and sanitizes steering vectors just once and then performs standard decoding. This decouples the privacy budget from generation, enabling arbitrarily many synthetic samples without additional privacy cost and yielding strong fidelity even in low-data regimes. Furthermore, we enhance our method by utilizing pretrained (base) models and introducing fixed-shot prompting to boost generation diversity and fidelity. Our experiments demonstrate that EPSVec outperforms existing baselines in distributional alignment and downstream utility, particularly in low-data regimes, while significantly reducing computational overhead.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
ACAR: Adaptive Complexity Routing for Multi-Model Ensembles with Auditable Decision Traces
arXiv:2602.21231v1 Announce Type: cross
Abstract: We present ACAR (Adaptive Complexity and Attribution Routing), a measurement framework for studying multi-model orchestration under auditable conditions. ACAR uses self-consistency variance (sigma) computed from N=3 probe samples to route tasks across single-model, two-model, and three-model execution modes. The system is implemented on top of TEAMLLM, a deterministic execution substrate with immutable artifacts and complete decision traces. We evaluate ACAR on 1,510 tasks spanning four benchmarks: MathArena, Reasoning Gym, LiveCodeBench, and SuperGPQA, using Claude Sonnet 4, GPT-4o, and Gemini 2.0 Flash, producing more than 7,550 auditable runs. Results show that sigma-based routing achieves 55.6 percent accuracy, exceeding the two-model baseline of 54.4 percent while avoiding full ensembling on 54.2 percent of tasks. The routing mechanism is model-agnostic and requires no learned components. We also document negative results. First, retrieval augmentation reduced accuracy by 3.4 percentage points, as median retrieval similarity was only 0.167, demonstrating that experience injection without semantic alignment introduces noise rather than grounding. Second, when models agree on incorrect answers (sigma equals zero), no downstream ensemble can recover; this agreement-but-wrong failure mode is intrinsic to self-consistency and bounds achievable accuracy at approximately eight percentage points below full ensembling. Third, attribution estimates based on proxy signals such as response similarity and entropy showed weak correlation with ground-truth leave-one-out values, indicating that practical attribution requires explicit counterfactual computation. This work documents which assumptions fail in practice and provides falsifiable baselines for future research on routing, retrieval, and multi-model attribution.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Bayesian Generative Adversarial Networks via Gaussian Approximation for Tabular Data Synthesis
arXiv:2602.21948v1 Announce Type: cross
Abstract: Generative Adversarial Networks (GAN) have been used in many studies to synthesise mixed tabular data. Conditional tabular GAN (CTGAN) have been the most popular variant but struggle to effectively navigate the risk-utility trade-off. Bayesian GAN have received less attention for tabular data, but have been explored with unstructured data such as images and text. The most used technique employed in Bayesian GAN is Markov Chain Monte Carlo (MCMC), but it is computationally intensive, particularly in terms of weight storage. In this paper, we introduce Gaussian Approximation of CTGAN (GACTGAN), an integration of the Bayesian posterior approximation technique using Stochastic Weight Averaging-Gaussian (SWAG) within the CTGAN generator to synthesise tabular data, reducing computational overhead after the training phase. We demonstrate that GACTGAN yields better synthetic data compared to CTGAN, achieving better preservation of tabular structure and inferential statistics with less privacy risk. These results highlight GACTGAN as a simpler, effective implementation of Bayesian tabular synthesis.
Fonte: arXiv stat.ML
NLP/LLMs • Score 85
Sparsity Induction for Accurate Post-Training Pruning of Large Language Models
arXiv:2602.21652v1 Announce Type: new
Abstract: Large language models have demonstrated capabilities in text generation, while their increasing parameter scales present challenges in computational and memory efficiency. Post-training sparsity (PTS), which reduces model cost by removing weights from dense networks, is an effective approach. However, native dense matrices lack high sparsity, making existing approaches that directly remove weights disrupt model states, resulting in unsatisfactory performance recovery even with post-tuning. We propose Sparsity Induction, which promotes models toward higher sparsity at both distribution and feature levels before pruning, to push the limits of PTS. At the distribution level, we enhance distributional sparsity through mathematically equivalent scaling transformations, which are fully absorbable and incur no extra parameters or inference-time overhead. At the feature level, we introduce Spectral Norm Loss to promote feature sparsity from a low-rank perspective. Experiments across diverse model architectures and tasks demonstrate that our method further enhances sparsity-friendliness, achieving superior pruning performance over existing approaches.
Fonte: arXiv cs.CL
RL • Score 95
Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
arXiv:2601.16163v1 Announce Type: new
Abstract: Recent video generation models demonstrate remarkable ability to capture complex physical interactions and scene evolution over time. To leverage their spatiotemporal priors, robotics works have adapted video models for policy learning but introduce complexity by requiring multiple stages of post-training and new architectural components for action generation. In this work, we introduce Cosmos Policy, a simple approach for adapting a large pretrained video model (Cosmos-Predict2) into an effective robot policy through a single stage of post-training on the robot demonstration data collected on the target platform, with no architectural modifications. Cosmos Policy learns to directly generate robot actions encoded as latent frames within the video model's latent diffusion process, harnessing the model's pretrained priors and core learning algorithm to capture complex action distributions. Additionally, Cosmos Policy generates future state images and values (expected cumulative rewards), which are similarly encoded as latent frames, enabling test-time planning of action trajectories with higher likelihood of success. In our evaluations, Cosmos Policy achieves state-of-the-art performance on the LIBERO and RoboCasa simulation benchmarks (98.5% and 67.1% average success rates, respectively) and the highest average score in challenging real-world bimanual manipulation tasks, outperforming strong diffusion policies trained from scratch, video model-based policies, and state-of-the-art vision-language-action models fine-tuned on the same robot demonstrations. Furthermore, given policy rollout data, Cosmos Policy can learn from experience to refine its world model and value function and leverage model-based planning to achieve even higher success rates in challenging tasks. We release code, models, and training data at https://research.nvidia.com/labs/dir/cosmos-policy/
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Autonomous Business System via Neuro-symbolic AI
arXiv:2601.15599v1 Announce Type: new
Abstract: Current business environments require organizations to continuously reconfigure cross-functional processes, yet enterprise systems are still organized around siloed departments, rigid workflows, and hard-coded automation. Meanwhile large language models (LLMs) excel at interpreting natural language and unstructured data but lack deterministic, verifiable execution of complex business logic. To address this gap, here we introduce AUTOBUS, an Autonomous Business System that integrates LLM-based AI agents, predicate-logic programming, and business-semantics-centric enterprise data into a coherent neuro-symbolic AI architecture for orchestrating end-to-end business initiatives. AUTOBUS models an initiative as a network of tasks with explicit pre/post conditions, required data, evaluation rules, and API-level actions. Enterprise data is organized as a knowledge graph whose entities, relationships, and constraints are translated into logic facts and foundational rules, providing the semantic grounding for task reasoning. Core AI agents synthesize task instructions, enterprise semantics, and available tools into task-specific logic programs, which are executed by a logic engine that enforces constraints, coordinates auxiliary tools, and orchestrate execution of actions and outcomes. Humans define and maintain the semantics, policies and task instructions, curate tools, and supervise high-impact or ambiguous decisions, ensuring accountability and adaptability. We detail the AUTOBUS architecture, the anatomy of the AI agent generated logic programs, and the role of humans and auxiliary tools in the lifecycle of a business initiative.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Aeon: High-Performance Neuro-Symbolic Memory Management for Long-Horizon LLM Agents
arXiv:2601.15311v1 Announce Type: new
Abstract: Large Language Models (LLMs) are fundamentally constrained by the quadratic computational cost of self-attention and the "Lost in the Middle" phenomenon, where reasoning capabilities degrade as context windows expand. Existing solutions, primarily "Flat RAG" architectures relying on vector databases, treat memory as an unstructured bag of embeddings. This approach fails to capture the hierarchical and temporal structure of long-horizon interactions, leading to "Vector Haze", the retrieval of disjointed facts lacking episodic continuity. We propose Aeon, a Neuro-Symbolic Cognitive Operating System that redefines memory not as a static store, but as a managed OS resource. Aeon structures memory into a Memory Palace (a spatial index implemented via Atlas, a SIMD-accelerated Page-Clustered Vector Index that combines small-world graph navigation with B+ Tree-style disk locality to minimize read amplification) and a Trace (a neuro-symbolic episodic graph). We introduce the Semantic Lookaside Buffer (SLB), a predictive caching mechanism that exploits conversational locality to achieve sub-millisecond retrieval latencies. Benchmarks demonstrate that Aeon achieves < 1ms retrieval latency on conversational workloads while ensuring state consistency via a zero-copy C++/Python bridge, effectively enabling persistent, structured memory for autonomous agents.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
Agentic AI Governance and Lifecycle Management in Healthcare
arXiv:2601.15630v1 Announce Type: new
Abstract: Healthcare organizations are beginning to embed agentic AI into routine workflows, including clinical documentation support and early-warning monitoring. As these capabilities diffuse across departments and vendors, health systems face agent sprawl, causing duplicated agents, unclear accountability, inconsistent controls, and tool permissions that persist beyond the original use case. Existing AI governance frameworks emphasize lifecycle risk management but provide limited guidance for the day-to-day operations of agent fleets. We propose a Unified Agent Lifecycle Management (UALM) blueprint derived from a rapid, practice-oriented synthesis of governance standards, agent security literature, and healthcare compliance requirements. UALM maps recurring gaps onto five control-plane layers: (1) an identity and persona registry, (2) orchestration and cross-domain mediation, (3) PHI-bounded context and memory, (4) runtime policy enforcement with kill-switch triggers, and (5) lifecycle management and decommissioning linked to credential revocation and audit logging. A companion maturity model supports staged adoption. UALM offers healthcare CIOs, CISOs, and clinical leaders an implementable pattern for audit-ready oversight that preserves local innovation and enables safer scaling across clinical and administrative domains.
Fonte: arXiv cs.AI
Theory/Optimization • Score 85
Designing faster mixed integer linear programming algorithm via learning the optimal path
arXiv:2601.16056v1 Announce Type: new
Abstract: Designing faster algorithms for solving Mixed-Integer Linear Programming (MILP) problems is highly desired across numerous practical domains, as a vast array of complex real-world challenges can be effectively modeled as MILP formulations. Solving these problems typically employs the branch-and-bound algorithm, the core of which can be conceived as searching for a path of nodes (or sub-problems) that contains the optimal solution to the original MILP problem. Traditional approaches to finding this path rely heavily on hand-crafted, intuition-based heuristic strategies, which often suffer from unstable and unpredictable performance across different MILP problem instances. To address this limitation, we introduce DeepBound, a deep learning-based node selection algorithm that automates the learning of such human intuition from data. The core of DeepBound lies in learning to prioritize nodes containing the optimal solution, thereby improving solving efficiency. DeepBound introduces a multi-level feature fusion network to capture the node representations. To tackle the inherent node imbalance in branch-and-bound trees, DeepBound employs a pairwise training paradigm that enhances the model's ability to discriminate between nodes. Extensive experiments on three NP-hard MILP benchmarks demonstrate that DeepBound achieves superior solving efficiency over conventional heuristic rules and existing learning-based approaches, obtaining optimal feasible solutions with significantly reduced computation time. Moreover, DeepBound demonstrates strong generalization capability on large and complex instances. The analysis of its learned features reveals that the method can automatically discover more flexible and robust feature selection, which may effectively improve and potentially replace human-designed heuristic rules.
Fonte: arXiv cs.AI
Multimodal • Score 85
EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
arXiv:2601.15876v1 Announce Type: new
Abstract: The development of native computer-use agents (CUA) represents a significant leap in multimodal AI. However, their potential is currently bottlenecked by the constraints of static data scaling. Existing paradigms relying primarily on passive imitation of static datasets struggle to capture the intricate causal dynamics inherent in long-horizon computer tasks. In this work, we introduce EvoCUA, a native computer use agentic model. Unlike static imitation, EvoCUA integrates data generation and policy optimization into a self-sustaining evolutionary cycle. To mitigate data scarcity, we develop a verifiable synthesis engine that autonomously generates diverse tasks coupled with executable validators. To enable large-scale experience acquisition, we design a scalable infrastructure orchestrating tens of thousands of asynchronous sandbox rollouts. Building on these massive trajectories, we propose an iterative evolving learning strategy to efficiently internalize this experience. This mechanism dynamically regulates policy updates by identifying capability boundaries -- reinforcing successful routines while transforming failure trajectories into rich supervision through error analysis and self-correction. Empirical evaluations on the OSWorld benchmark demonstrate that EvoCUA achieves a success rate of 56.7%, establishing a new open-source state-of-the-art. Notably, EvoCUA significantly outperforms the previous best open-source model, OpenCUA-72B (45.0%), and surpasses leading closed-weights models such as UI-TARS-2 (53.1%). Crucially, our results underscore the generalizability of this approach: the evolving paradigm driven by learning from experience yields consistent performance gains across foundation models of varying scales, establishing a robust and scalable path for advancing native agent capabilities.
Fonte: arXiv cs.AI
Multimodal • Score 85
GeMM-GAN: A Multimodal Generative Model Conditioned on Histopathology Images and Clinical Descriptions for Gene Expression Profile Generation
arXiv:2601.15392v1 Announce Type: new
Abstract: Biomedical research increasingly relies on integrating diverse data modalities, including gene expression profiles, medical images, and clinical metadata. While medical images and clinical metadata are routinely collected in clinical practice, gene expression data presents unique challenges for widespread research use, mainly due to stringent privacy regulations and costly laboratory experiments. To address these limitations, we present GeMM-GAN, a novel Generative Adversarial Network conditioned on histopathology tissue slides and clinical metadata, designed to synthesize realistic gene expression profiles. GeMM-GAN combines a Transformer Encoder for image patches with a final Cross Attention mechanism between patches and text tokens, producing a conditioning vector to guide a generative model in generating biologically coherent gene expression profiles. We evaluate our approach on the TCGA dataset and demonstrate that our framework outperforms standard generative models and generates more realistic and functionally meaningful gene expression profiles, improving by more than 11\% the accuracy on downstream disease type prediction compared to current state-of-the-art generative models. Code will be available at: https://github.com/francescapia/GeMM-GAN
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Replayable Financial Agents: A Determinism-Faithfulness Assurance Harness for Tool-Using LLM Agents
arXiv:2601.15322v1 Announce Type: new
Abstract: LLM agents struggle with regulatory audit replay: when asked to reproduce a flagged transaction decision with identical inputs, most deployments fail to return consistent results. This paper introduces the Determinism-Faithfulness Assurance Harness (DFAH), a framework for measuring trajectory determinism and evidence-conditioned faithfulness in tool-using agents deployed in financial services.
Across 74 configurations (12 models, 4 providers, 8-24 runs each at T=0.0) in non-agentic baseline experiments, 7-20B parameter models achieved 100% determinism, while 120B+ models required 3.7x larger validation samples to achieve equivalent statistical reliability. Agentic tool-use introduces additional variance (see Tables 4-7). Contrary to the assumed reliability-capability trade-off, a positive Pearson correlation emerged (r = 0.45, p < 0.01, n = 51 at T=0.0) between determinism and faithfulness; models producing consistent outputs also tended to be more evidence-aligned.
Three financial benchmarks are provided (compliance triage, portfolio constraints, DataOps exceptions; 50 cases each) along with an open-source stress-test harness. In these benchmarks and under DFAH evaluation settings, Tier 1 models with schema-first architectures achieved determinism levels consistent with audit replay requirements.
Fonte: arXiv cs.AI
RL • Score 85
Vehicle Routing with Finite Time Horizon using Deep Reinforcement Learning with Improved Network Embedding
arXiv:2601.15131v1 Announce Type: new
Abstract: In this paper, we study the vehicle routing problem with a finite time horizon. In this routing problem, the objective is to maximize the number of customer requests served within a finite time horizon. We present a novel routing network embedding module which creates local node embedding vectors and a context-aware global graph representation. The proposed Markov decision process for the vehicle routing problem incorporates the node features, the network adjacency matrix and the edge features as components of the state space. We incorporate the remaining finite time horizon into the network embedding module to provide a proper routing context to the embedding module. We integrate our embedding module with a policy gradient-based deep Reinforcement Learning framework to solve the vehicle routing problem with finite time horizon. We trained and validated our proposed routing method on real-world routing networks, as well as synthetically generated Euclidean networks. Our experimental results show that our method achieves a higher customer service rate than the existing routing methods. Additionally, the solution time of our method is significantly lower than that of the existing methods.
Fonte: arXiv cs.AI
RL • Score 85
DARA: Few-shot Budget Allocation in Online Advertising via In-Context Decision Making with RL-Finetuned LLMs
arXiv:2601.14711v1 Announce Type: new
Abstract: Optimizing the advertiser's cumulative value of winning impressions under budget constraints poses a complex challenge in online advertising, under the paradigm of AI-Generated Bidding (AIGB). Advertisers often have personalized objectives but limited historical interaction data, resulting in few-shot scenarios where traditional reinforcement learning (RL) methods struggle to perform effectively. Large Language Models (LLMs) offer a promising alternative for AIGB by leveraging their in-context learning capabilities to generalize from limited data. However, they lack the numerical precision required for fine-grained optimization. To address this limitation, we introduce GRPO-Adaptive, an efficient LLM post-training strategy that enhances both reasoning and numerical precision by dynamically updating the reference policy during training. Built upon this foundation, we further propose DARA, a novel dual-phase framework that decomposes the decision-making process into two stages: a few-shot reasoner that generates initial plans via in-context prompting, and a fine-grained optimizer that refines these plans using feedback-driven reasoning. This separation allows DARA to combine LLMs' in-context learning strengths with precise adaptability required by AIGB tasks. Extensive experiments on both real-world and synthetic data environments demonstrate that our approach consistently outperforms existing baselines in terms of cumulative advertiser value under budget constraints.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Large Language Model-Powered Evolutionary Code Optimization on a Phylogenetic Tree
arXiv:2601.14523v1 Announce Type: new
Abstract: Optimizing scientific computing algorithms for modern GPUs is a labor-intensive and iterative process involving repeated code modification, benchmarking, and tuning across complex hardware and software stacks. Recent work has explored large language model (LLM)-assisted evolutionary methods for automated code optimization, but these approaches primarily rely on outcome-based selection and random mutation, underutilizing the rich trajectory information generated during iterative optimization. We propose PhyloEvolve, an LLM-agent system that reframes GPU-oriented algorithm optimization as an In-Context Reinforcement Learning (ICRL) problem. This formulation enables trajectory-conditioned reuse of optimization experience without model retraining. PhyloEvolve integrates Algorithm Distillation and prompt-based Decision Transformers into an iterative workflow, treating sequences of algorithm modifications and performance feedback as first-class learning signals. To organize optimization history, we introduce a phylogenetic tree representation that captures inheritance, divergence, and recombination among algorithm variants, enabling backtracking, cross-lineage transfer, and reproducibility. The system combines elite trajectory pooling, multi-island parallel exploration, and containerized execution to balance exploration and exploitation across heterogeneous hardware. We evaluate PhyloEvolve on scientific computing workloads including PDE solvers, manifold learning, and spectral graph algorithms, demonstrating consistent improvements in runtime, memory efficiency, and correctness over baseline and evolutionary methods. Code is published at: https://github.com/annihi1ation/phylo_evolve
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
The Responsibility Vacuum: Organizational Failure in Scaled Agent Systems
arXiv:2601.15059v1 Announce Type: new
Abstract: Modern CI/CD pipelines integrating agent-generated code exhibit a structural failure in responsibility attribution. Decisions are executed through formally correct approval processes, yet no entity possesses both the authority to approve those decisions and the epistemic capacity to meaningfully understand their basis.
We define this condition as responsibility vacuum: a state in which decisions occur, but responsibility cannot be attributed because authority and verification capacity do not coincide. We show that this is not a process deviation or technical defect, but a structural property of deployments where decision generation throughput exceeds bounded human verification capacity.
We identify a scaling limit under standard deployment assumptions, including parallel agent generation, CI-based validation, and individualized human approval gates. Beyond a throughput threshold, verification ceases to function as a decision criterion and is replaced by ritualized approval based on proxy signals. Personalized responsibility becomes structurally unattainable in this regime.
We further characterize a CI amplification dynamic, whereby increasing automated validation coverage raises proxy signal density without restoring human capacity. Under fixed time and attention constraints, this accelerates cognitive offloading in the broad sense and widens the gap between formal approval and epistemic understanding. Additional automation therefore amplifies, rather than mitigates, the responsibility vacuum.
We conclude that unless organizations explicitly redesign decision boundaries or reassign responsibility away from individual decisions toward batch- or system-level ownership, responsibility vacuum remains an invisible but persistent failure mode in scaled agent deployments.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
CI4A: Semantic Component Interfaces for Agents Empowering Web Automation
arXiv:2601.14790v1 Announce Type: new
Abstract: While Large Language Models demonstrate remarkable proficiency in high-level semantic planning, they remain limited in handling fine-grained, low-level web component manipulations. To address this limitation, extensive research has focused on enhancing model grounding capabilities through techniques such as Reinforcement Learning. However, rather than compelling agents to adapt to human-centric interfaces, we propose constructing interaction interfaces specifically optimized for agents. This paper introduces Component Interface for Agent (CI4A), a semantic encapsulation mechanism that abstracts the complex interaction logic of UI components into a set of unified tool primitives accessible to agents. We implemented CI4A within Ant Design, an industrial-grade front-end framework, covering 23 categories of commonly used UI components. Furthermore, we developed a hybrid agent featuring an action space that dynamically updates according to the page state, enabling flexible invocation of available CI4A tools. Leveraging the CI4A-integrated Ant Design, we refactored and upgraded the WebArena benchmark to evaluate existing SoTA methods. Experimental results demonstrate that the CI4A-based agent significantly outperforms existing approaches, achieving a new SoTA task success rate of 86.3%, alongside substantial improvements in execution efficiency.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Call2Instruct: Automated Pipeline for Generating Q&A Datasets from Call Center Recordings for LLM Fine-Tuning
arXiv:2601.14263v1 Announce Type: cross
Abstract: The adaptation of Large-Scale Language Models (LLMs) to specific domains depends on high-quality fine-tuning datasets, particularly in instructional format (e.g., Question-Answer - Q&A). However, generating these datasets, particularly from unstructured sources such as call center audio recordings, poses a significant challenge due to the noisy and disorganized nature of the data. This paper presents a solution to this challenge by offering an end-to-end automated pipeline for generating Q&A instructional datasets from such recordings. The methodology developed comprises sequential steps of audio processing (including diarization, noise removal and automatic transcription), textual processing (cleaning, normalization, and anonymization), semantic extraction of customer demands and attendant responses using vector embeddings, and matching via semantic search to form the final Q&A pairs. As a result, the complete pipeline was successfully implemented, generating a dataset specifically formatted for Instruct Fine Tuning. The practical value and feasibility of the generated dataset were substantiated and functionally demonstrated through the successful fine-tuning of an LLM model (based on Llama 2 7B). The conclusion of the paper states that the proposed approach is viable for converting unstructured conversational data from call centers into valuable resources for training LLMs. This development has the potential to open up avenues for creating more effective AI systems for Q&A tasks in the customer service domain. The developed codes have been made publicly available to promote reproducibility and future research.
Fonte: arXiv cs.AI
RecSys • Score 85
Multi-Behavior Sequential Modeling with Transition-Aware Graph Attention Network for E-Commerce Recommendation
arXiv:2601.14955v1 Announce Type: new
Abstract: User interactions on e-commerce platforms are inherently diverse, involving behaviors such as clicking, favoriting, adding to cart, and purchasing. The transitions between these behaviors offer valuable insights into user-item interactions, serving as a key signal for understanding evolving preferences. Consequently, there is growing interest in leveraging multi-behavior data to better capture user intent. Recent studies have explored sequential modeling of multi-behavior data, many relying on transformer-based architectures with polynomial time complexity. While effective, these approaches often incur high computational costs, limiting their applicability in large-scale industrial systems with long user sequences. To address this challenge, we propose the Transition-Aware Graph Attention Network (TGA), a linear-complexity approach for modeling multi-behavior transitions. Unlike traditional transformers that treat all behavior pairs equally, TGA constructs a structured sparse graph by identifying informative transitions from three perspectives: (a) item-level transitions, (b) category-level transitions, and (c) neighbor-level transitions. Built upon the structured graph, TGA employs a transition-aware graph Attention mechanism that jointly models user-item interactions and behavior transition types, enabling more accurate capture of sequential patterns while maintaining computational efficiency. Experiments show that TGA outperforms all state-of-the-art models while significantly reducing computational cost. Notably, TGA has been deployed in a large-scale industrial production environment, where it leads to impressive improvements in key business metrics.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
How to Build AI Agents by Augmenting LLMs with Codified Human Expert Domain Knowledge? A Software Engineering Framework
arXiv:2601.15153v1 Announce Type: new
Abstract: Critical domain knowledge typically resides with few experts, creating organizational bottlenecks in scalability and decision-making. Non-experts struggle to create effective visualizations, leading to suboptimal insights and diverting expert time. This paper investigates how to capture and embed human domain knowledge into AI agent systems through an industrial case study. We propose a software engineering framework to capture human domain knowledge for engineering AI agents in simulation data visualization by augmenting a Large Language Model (LLM) with a request classifier, Retrieval-Augmented Generation (RAG) system for code generation, codified expert rules, and visualization design principles unified in an agent demonstrating autonomous, reactive, proactive, and social behavior. Evaluation across five scenarios spanning multiple engineering domains with 12 evaluators demonstrates 206% improvement in output quality, with our agent achieving expert-level ratings in all cases versus baseline's poor performance, while maintaining superior code quality with lower variance. Our contributions are: an automated agent-based system for visualization generation and a validated framework for systematically capturing human domain knowledge and codifying tacit expert knowledge into AI agents, demonstrating that non-experts can achieve expert-level outcomes in specialized domains.
Fonte: arXiv cs.AI
Multimodal • Score 92
A Cloud-Based Cross-Modal Transformer for Emotion Recognition and Adaptive Human-Computer Interaction
arXiv:2601.14259v1 Announce Type: cross
Abstract: Emotion recognition is a fundamental component of next-generation human-computer interaction (HCI), enabling machines to perceive, understand, and respond to users' affective states. However, existing systems often rely on single-modality analysis such as facial expressions, speech tone, or textual sentiment, resulting in limited robustness and poor generalization in real-world environments. To address these challenges, this study proposes a Cloud-Based Cross-Modal Transformer (CMT) framework for multimodal emotion recognition and adaptive human-computer interaction. The proposed model integrates visual, auditory, and textual signals using pretrained encoders (Vision Transformer, Wav2Vec2, and BERT) and employs a cross-modal attention mechanism to capture complex interdependencies among heterogeneous features. By leveraging cloud computing infrastructure with distributed training on Kubernetes and TensorFlow Serving, the system enables scalable, low-latency emotion recognition for large-scale user interactions. Experiments conducted on benchmark datasets including IEMOCAP, MELD, and AffectNet demonstrate that the CMT achieves state-of-the-art performance, improving the F1-score by 3.0 percent and reducing cross-entropy loss by 12.9 percent compared to strong multimodal baselines. Additionally, cloud deployment evaluations show an average response latency of 128 ms, representing a 35 percent reduction compared with conventional transformer-based fusion systems. These results confirm that the proposed framework enables efficient, real-time emotion recognition and adaptive feedback in applications such as intelligent customer service, virtual tutoring systems, and affective computing interfaces, marking an important step toward cloud-native affective computing and emotionally intelligent interactive systems.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
DDSA: Dual-Domain Strategic Attack for Spatial-Temporal Efficiency in Adversarial Robustness Testing
arXiv:2601.14302v1 Announce Type: cross
Abstract: Image transmission and processing systems in resource-critical applications face significant challenges from adversarial perturbations that compromise mission-specific object classification. Current robustness testing methods require excessive computational resources through exhaustive frame-by-frame processing and full-image perturbations, proving impractical for large-scale deployments where massive image streams demand immediate processing. This paper presents DDSA (Dual-Domain Strategic Attack), a resource-efficient adversarial robustness testing framework that optimizes testing through temporal selectivity and spatial precision. We introduce a scenario-aware trigger function that identifies critical frames requiring robustness evaluation based on class priority and model uncertainty, and employ explainable AI techniques to locate influential pixel regions for targeted perturbation. Our dual-domain approach achieves substantial temporal-spatial resource conservation while maintaining attack effectiveness. The framework enables practical deployment of comprehensive adversarial robustness testing in resource-constrained real-time applications where computational efficiency directly impacts mission success.
Fonte: arXiv cs.AI
MLOps/Systems • Score 75
On the Limits of Learned Importance Scoring for KV Cache Compression
arXiv:2601.14279v1 Announce Type: cross
Abstract: We investigate learned KV cache compression through Speculative Importance Prediction (SIP), a 1.7M parameter non-query-aware scorer that predicts token importance from KV representations alone. Despite architectural sophistication (multi-horizon lookahead, cross-attention), SIP does not outperform simple baselines, including random selection, across 5 seeds, 4 retention levels, and 3 tasks. Key findings: (1) position-based heuristics (keep first 4 + last N tokens) match or exceed learned approaches; (2) prefill attention provides equivalent signal to complex learned scorers; (3) marginal information in KV representations beyond position and prefill attention appears limited for importance prediction. We hypothesize that circular dependence between future queries and generation trajectories contributes to this difficulty.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
Empowering All-in-Loop Health Management of Spacecraft Power System in the Mega-Constellation Era via Human-AI Collaboration
arXiv:2601.12667v1 Announce Type: new
Abstract: It is foreseeable that the number of spacecraft will increase exponentially, ushering in an era dominated by satellite mega-constellations (SMC). This necessitates a focus on energy in space: spacecraft power systems (SPS), especially their health management (HM), given their role in power supply and high failure rates. Providing health management for dozens of SPS and for thousands of SPS represents two fundamentally different paradigms. Therefore, to adapt the health management in the SMC era, this work proposes a principle of aligning underlying capabilities (AUC principle) and develops SpaceHMchat, an open-source Human-AI collaboration (HAIC) framework for all-in-loop health management (AIL HM). SpaceHMchat serves across the entire loop of work condition recognition, anomaly detection, fault localization, and maintenance decision making, achieving goals such as conversational task completion, adaptive human-in-the-loop learning, personnel structure optimization, knowledge sharing, efficiency enhancement, as well as transparent reasoning and improved interpretability. Meanwhile, to validate this exploration, a hardware-realistic fault injection experimental platform is established, and its simulation model is built and open-sourced, both fully replicating the real SPS. The corresponding experimental results demonstrate that SpaceHMchat achieves excellent performance across 23 quantitative metrics, such as 100% conclusion accuracy in logical reasoning of work condition recognition, over 99% success rate in anomaly detection tool invocation, over 90% precision in fault localization, and knowledge base search time under 3 minutes in maintenance decision-making. Another contribution of this work is the release of the first-ever AIL HM dataset of SPS. This dataset contains four sub-datasets, involving 4 types of AIL HM sub-tasks, 17 types of faults, and over 700,000 timestamps.
Fonte: arXiv cs.AI
RL • Score 85
Multi-agent DRL-based Lane Change Decision Model for Cooperative Planning in Mixed Traffic
arXiv:2601.11809v1 Announce Type: new
Abstract: Connected automated vehicles (CAVs) possess the ability to communicate and coordinate with one another, enabling cooperative platooning that enhances both energy efficiency and traffic flow. However, during the initial stage of CAV deployment, the sparse distribution of CAVs among human-driven vehicles reduces the likelihood of forming effective cooperative platoons. To address this challenge, this study proposes a hybrid multi-agent lane change decision model aimed at increasing CAV participation in cooperative platooning and maximizing its associated benefits. The proposed model employs the QMIX framework, integrating traffic data processed through a convolutional neural network (CNN-QMIX). This architecture addresses a critical issue in dynamic traffic scenarios by enabling CAVs to make optimal decisions irrespective of the varying number of CAVs present in mixed traffic. Additionally, a trajectory planner and a model predictive controller are designed to ensure smooth and safe lane-change execution. The proposed model is trained and evaluated within a microsimulation environment under varying CAV market penetration rates. The results demonstrate that the proposed model efficiently manages fluctuating traffic agent numbers, significantly outperforming the baseline rule-based models. Notably, it enhances cooperative platooning rates up to 26.2\%, showcasing its potential to optimize CAV cooperation and traffic dynamics during the early stage of deployment.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Speculative Decoding: Performance or Illusion?
arXiv:2601.11580v1 Announce Type: new
Abstract: Speculative decoding (SD) has become a popular technique to accelerate Large Language Model (LLM) inference, yet its real-world effectiveness remains unclear as prior evaluations rely on research prototypes and unrealistically small batch sizes. We present, to our knowledge, the first systematic study of SD on a production-grade and widely deployed inference engine (vLLM), covering multiple SD variants ($n$-gram, EAGLE/EAGLE-3, Draft-Model, Multi-Token Prediction) across diverse workloads, model scales, and batch sizes. We analyze key factors governing SD performance, and quantify a theoretical upper bound on SD speedup. Our results show that verification by the target model dominates the execution, while acceptance length varies markedly across output token positions, requests, and datasets. Comparing measured performance with theoretical bounds reveals substantial gaps between observed and theoretical upper bounds, and we leverage this observation to highlight new research opportunities that our study opens up in improving SD.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
POLARIS: Typed Planning and Governed Execution for Agentic AI in Back-Office Automation
arXiv:2601.11816v1 Announce Type: new
Abstract: Enterprise back office workflows require agentic systems that are auditable, policy-aligned, and operationally predictable, capabilities that generic multi-agent setups often fail to deliver. We present POLARIS (Policy-Aware LLM Agentic Reasoning for Integrated Systems), a governed orchestration framework that treats automation as typed plan synthesis and validated execution over LLM agents. A planner proposes structurally diverse, type checked directed acyclic graphs (DAGs), a rubric guided reasoning module selects a single compliant plan, and execution is guarded by validator gated checks, a bounded repair loop, and compiled policy guardrails that block or route side effects before they occur. Applied to document centric finance tasks, POLARIS produces decision grade artifacts and full execution traces while reducing human intervention. Empirically, POLARIS achieves a micro F1 of 0.81 on the SROIE dataset and, on a controlled synthetic suite, achieves 0.95 to 1.00 precision for anomaly routing with preserved audit trails. These evaluations constitute an initial benchmark for governed Agentic AI. POLARIS provides a methodological and benchmark reference for policy-aligned Agentic AI. Keywords Agentic AI, Enterprise Automation, Back-Office Tasks, Benchmarks, Governance, Typed Planning, Evaluation
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Don't Start Over: A Cost-Effective Framework for Migrating Personalized Prompts Between LLMs
arXiv:2601.12034v1 Announce Type: new
Abstract: Personalization in Large Language Models (LLMs) often relies on user-specific soft prompts. However, these prompts become obsolete when the foundation model is upgraded, necessitating costly, full-scale retraining. To overcome this limitation, we propose the Prompt-level User Migration Adapter (PUMA), a lightweight framework to efficiently migrate personalized prompts across incompatible models. PUMA utilizes a parameter-efficient adapter to bridge the semantic gap, combined with a group-based user selection strategy to significantly reduce training costs. Experiments on three large-scale datasets show our method matches or even surpasses the performance of retraining from scratch, reducing computational cost by up to 98%. The framework demonstrates strong generalization across diverse model architectures and robustness in advanced scenarios like chained and aggregated migrations, offering a practical path for the sustainable evolution of personalized AI by decoupling user assets from the underlying models.
Fonte: arXiv cs.CL
RL • Score 85
Optimal Power Allocation and Sub-Optimal Channel Assignment for Downlink NOMA Systems Using Deep Reinforcement Learning
arXiv:2601.12242v1 Announce Type: new
Abstract: In recent years, Non-Orthogonal Multiple Access (NOMA) system has emerged as a promising candidate for multiple access frameworks due to the evolution of deep machine learning, trying to incorporate deep machine learning into the NOMA system. The main motivation for such active studies is the growing need to optimize the utilization of network resources as the expansion of the internet of things (IoT) caused a scarcity of network resources. The NOMA addresses this need by power multiplexing, allowing multiple users to access the network simultaneously. Nevertheless, the NOMA system has few limitations. Several works have proposed to mitigate this, including the optimization of power allocation known as joint resource allocation(JRA) method, and integration of the JRA method and deep reinforcement learning (JRA-DRL). Despite this, the channel assignment problem remains unclear and requires further investigation. In this paper, we propose a deep reinforcement learning framework incorporating replay memory with an on-policy algorithm, allocating network resources in a NOMA system to generalize the learning. Also, we provide extensive simulations to evaluate the effects of varying the learning rate, batch size, type of model, and the number of features in the state.
Fonte: arXiv cs.AI
NLP/LLMs • Score 90
Compass-Embedding v4: Robust Contrastive Learning for Multilingual E-commerce Embeddings
arXiv:2601.11565v1 Announce Type: new
Abstract: As global e-commerce rapidly expands into emerging markets, the lack of high-quality semantic representations for low-resource languages has become a decisive bottleneck for retrieval, recommendation, and search systems. In this work, we present Compass-Embedding v4, a high-efficiency multilingual embedding framework specifically optimized for Southeast Asian (SEA) e-commerce scenarios, where data scarcity, noisy supervision, and strict production constraints jointly challenge representation learning. Compass-Embedding v4 addresses three core challenges. First, large-batch contrastive training under mixed task supervision introduces systematic false negatives that degrade semantic alignment. We propose Class-Aware Masking (CAM), a lightweight modification to the InfoNCE objective that suppresses invalid in-batch negatives and improves semantic discrimination without altering training efficiency. Second, low-resource SEA languages suffer from limited and uneven data coverage. We construct a diversified training corpus through context-grounded synthetic data generation, cross-lingual translation, and structured e-commerce data construction, enabling robust multilingual and domain-specific learning. Third, production deployment requires high-throughput inference while preserving embedding quality. We combine robustness-driven large-batch training with spherical model merging to mitigate catastrophic forgetting, and optimize inference via vLLM and FP8 quantization. Extensive evaluations across multilingual benchmarks and proprietary e-commerce tasks show that Compass-Embedding v4 achieves state-of-the-art performance on major SEA languages, significantly outperforming general-purpose embedding models in domain-specific retrieval and classification, while maintaining competitive performance on high-resource languages.
Fonte: arXiv cs.CL
NLP/LLMs • Score 85
AEMA: Verifiable Evaluation Framework for Trustworthy and Controlled Agentic LLM Systems
arXiv:2601.11903v1 Announce Type: new
Abstract: Evaluating large language model (LLM)-based multi-agent systems remains a critical challenge, as these systems must exhibit reliable coordination, transparent decision-making, and verifiable performance across evolving tasks. Existing evaluation approaches often limit themselves to single-response scoring or narrow benchmarks, which lack stability, extensibility, and automation when deployed in enterprise settings at multi-agent scale. We present AEMA (Adaptive Evaluation Multi-Agent), a process-aware and auditable framework that plans, executes, and aggregates multi-step evaluations across heterogeneous agentic workflows under human oversight. Compared to a single LLM-as-a-Judge, AEMA achieves greater stability, human alignment, and traceable records that support accountable automation. Our results on enterprise-style agent workflows simulated using realistic business scenarios demonstrate that AEMA provides a transparent and reproducible pathway toward responsible evaluation of LLM-based multi-agent systems.
Keywords Agentic AI, Multi-Agent Systems, Trustworthy AI, Verifiable Evaluation, Human Oversight
Fonte: arXiv cs.AI
MLOps/Systems • Score 75
Mapping the maturation of TCM as an adjuvant to radiotherapy
arXiv:2601.11923v1 Announce Type: new
Abstract: The integration of complementary medicine into oncology represents a paradigm shift that has seen to increasing adoption of Traditional Chinese Medicine (TCM) as an adjuvant to radiotherapy. About twenty-five years since the formal institutionalization of integrated oncology, it is opportune to synthesize the trajectory of evidence for TCM as an adjuvant to radiotherapy. Here we conduct a large-scale analysis of 69,745 publications (2000 - 2025), emerging a cyclical evolution defined by coordinated expansion and contraction in publication output, international collaboration, and funding commitments that mirrors a define-ideate-test pattern. Using a theme modeling workflow designed to determine a stable thematic structure of the field, we identify five dominant thematic axes - cancer types, supportive care, clinical endpoints, mechanisms, and methodology - that signal a focus on patient well-being, scientific rigor and mechanistic exploration. Cross-theme integration of TCM is patient-centered and systems-oriented. Together with the emergent cycles of evolution, the thematic structure demonstrates progressive specialization and potential defragmentation of the field or saturation of existing research agenda. The analysis points to a field that has matured its current research agenda and is likely at the cusp of something new. Additionally, the field exhibits positive reporting of findings that is homogeneous across publication types, thematic areas, and the cycles of evolution suggesting a system-wide positive reporting bias agnostic to structural drivers.
Fonte: arXiv cs.CL
RL • Score 85
Survival is the Only Reward: Sustainable Self-Training Through Environment-Mediated Selection
arXiv:2601.12310v1 Announce Type: new
Abstract: Self-training systems often degenerate due to the lack of an external criterion for judging data quality, leading to reward hacking and semantic drift. This paper provides a proof-of-concept system architecture for stable self-training under sparse external feedback and bounded memory, and empirically characterises its learning dynamics and failure modes.
We introduce a self-training architecture in which learning is mediated exclusively by environmental viability, rather than by reward, objective functions, or externally defined fitness criteria. Candidate behaviours are executed under real resource constraints, and only those whose environmental effects both persist and preserve the possibility of future interaction are propagated. The environment does not provide semantic feedback, dense rewards, or task-specific supervision; selection operates solely through differential survival of behaviours as world-altering events, making proxy optimisation impossible and rendering reward-hacking evolutionarily unstable.
Analysis of semantic dynamics shows that improvement arises primarily through the persistence of effective and repeatable strategies under a regime of consolidation and pruning, a paradigm we refer to as negative-space learning (NSL), and that models develop meta-learning strategies (such as deliberate experimental failure in order to elicit informative error messages) without explicit instruction. This work establishes that environment-grounded selection enables sustainable open-ended self-improvement, offering a viable path toward more robust and generalisable autonomous systems without reliance on human-curated data or complex reward shaping.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Docs2Synth: A Synthetic Data Trained Retriever Framework for Scanned Visually Rich Documents Understanding
arXiv:2601.12260v1 Announce Type: new
Abstract: Document understanding (VRDU) in regulated domains is particularly challenging, since scanned documents often contain sensitive, evolving, and domain specific knowledge. This leads to two major challenges: the lack of manual annotations for model adaptation and the difficulty for pretrained models to stay up-to-date with domain-specific facts. While Multimodal Large Language Models (MLLMs) show strong zero-shot abilities, they still suffer from hallucination and limited domain grounding. In contrast, discriminative Vision-Language Pre-trained Models (VLPMs) provide reliable grounding but require costly annotations to cover new domains. We introduce Docs2Synth, a synthetic-supervision framework that enables retrieval-guided inference for private and low-resource domains. Docs2Synth automatically processes raw document collections, generates and verifies diverse QA pairs via an agent-based system, and trains a lightweight visual retriever to extract domain-relevant evidence. During inference, the retriever collaborates with an MLLM through an iterative retrieval--generation loop, reducing hallucination and improving response consistency. We further deliver Docs2Synth as an easy-to-use Python package, enabling plug-and-play deployment across diverse real-world scenarios. Experiments on multiple VRDU benchmarks show that Docs2Synth substantially enhances grounding and domain generalization without requiring human annotations.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Rethinking the AI Scientist: Interactive Multi-Agent Workflows for Scientific Discovery
arXiv:2601.12542v1 Announce Type: new
Abstract: Artificial intelligence systems for scientific discovery have demonstrated remarkable potential, yet existing approaches remain largely proprietary and operate in batch-processing modes requiring hours per research cycle, precluding real-time researcher guidance. This paper introduces Deep Research, a multi-agent system enabling interactive scientific investigation with turnaround times measured in minutes. The architecture comprises specialized agents for planning, data analysis, literature search, and novelty detection, unified through a persistent world state that maintains context across iterative research cycles. Two operational modes support different workflows: semi-autonomous mode with selective human checkpoints, and fully autonomous mode for extended investigations. Evaluation on the BixBench computational biology benchmark demonstrated state-of-the-art performance, achieving 48.8% accuracy on open response and 64.5% on multiple-choice evaluation, exceeding existing baselines by 14 to 26 percentage points. Analysis of architectural constraints, including open access literature limitations and challenges inherent to automated novelty assessment, informs practical deployment considerations for AI-assisted scientific workflows.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
ORBITFLOW: SLO-Aware Long-Context LLM Serving with Fine-Grained KV Cache Reconfiguration
arXiv:2601.10729v1 Announce Type: new
Abstract: Serving long-context LLMs is challenging because request lengths and batch composition vary during token generation, causing the memory footprint to fluctuate significantly at runtime. Offloading KV caches to host memory limits effective memory usage, but existing static and predetermined offloading strategies cannot adapt to the rapidly shifting memory demands of long-context serving. This often leads to excessive CPU-to-GPU KV transfers that translate into latency spikes and frequent SLO violations. To address these challenges, we introduce ORBITFLOW, a fine-grained and adaptive KV cache management system that meets latency SLOs in long-context LLM serving. ORBITFLOW employs a lightweight ILP solver to decide which layers' KV caches to retain on the GPU for each request, within memory capacity constraints. It continuously refines KV placements based on runtime feedback when the active plan becomes suboptimal during token generation. Under heavy load, ORBITFLOW invokes a fallback mechanism to temporarily defer in-flight requests with large memory footprints, preserving overall SLO attainment. Our experiments demonstrate that ORBITFLOW improves SLO attainment for TPOT and TBT by up to 66% and 48%, respectively, while reducing the 95th percentile latency by 38% and achieving up to 3.3x higher throughput compared to existing offloading methods.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent Systems
arXiv:2601.11147v1 Announce Type: new
Abstract: Multi-Agent Systems (MAS) built on large language models typically solve complex tasks by coordinating multiple agents through workflows. Existing approaches generates workflows either at task level or query level, but their relative costs and benefits remain unclear. After rethinking and empirical analyses, we show that query-level workflow generation is not always necessary, since a small set of top-K best task-level workflows together already covers equivalent or even more queries. We further find that exhaustive execution-based task-level evaluation is both extremely token-costly and frequently unreliable. Inspired by the idea of self-evolution and generative reward modeling, we propose a low-cost task-level generation framework \textbf{SCALE}, which means \underline{\textbf{S}}elf prediction of the optimizer with few shot \underline{\textbf{CAL}}ibration for \underline{\textbf{E}}valuation instead of full validation execution. Extensive experiments demonstrate that \textbf{SCALE} maintains competitive performance, with an average degradation of just 0.61\% compared to existing approach across multiple datasets, while cutting overall token usage by up to 83\%.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
RobuMTL: Enhancing Multi-Task Learning Robustness Against Weather Conditions
arXiv:2601.10921v1 Announce Type: cross
Abstract: Robust Multi-Task Learning (MTL) is crucial for autonomous systems operating in real-world environments, where adverse weather conditions can severely degrade model performance and reliability. In this paper, we introduce RobuMTL, a novel architecture designed to adaptively address visual degradation by dynamically selecting task-specific hierarchical Low-Rank Adaptation (LoRA) modules and a LoRA expert squad based on input perturbations in a mixture-of-experts fashion. Our framework enables adaptive specialization based on input characteristics, improving robustness across diverse real-world conditions. To validate our approach, we evaluated it on the PASCAL and NYUD-v2 datasets and compared it against single-task models, standard MTL baselines, and state-of-the-art methods. On the PASCAL benchmark, RobuMTL delivers a +2.8% average relative improvement under single perturbations and up to +44.4% under mixed weather conditions compared to the MTL baseline. On NYUD-v2, RobuMTL achieves a +9.7% average relative improvement across tasks. The code is available at GitHub.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Towards Reliable ML Feature Engineering via Planning in Constrained-Topology of LLM Agents
arXiv:2601.10820v1 Announce Type: cross
Abstract: Recent advances in code generation models have unlocked unprecedented opportunities for automating feature engineering, yet their adoption in real-world ML teams remains constrained by critical challenges: (i) the scarcity of datasets capturing the iterative and complex coding processes of production-level feature engineering, (ii) limited integration and personalization of widely used coding agents, such as CoPilot and Devin, with a team's unique tools, codebases, workflows, and practices, and (iii) suboptimal human-AI collaboration due to poorly timed or insufficient feedback. We address these challenges with a planner-guided, constrained-topology multi-agent framework that generates code for repositories in a multi-step fashion. The LLM-powered planner leverages a team's environment, represented as a graph, to orchestrate calls to available agents, generate context-aware prompts, and use downstream failures to retroactively correct upstream artifacts. It can request human intervention at critical steps, ensuring generated code is reliable, maintainable, and aligned with team expectations. On a novel in-house dataset, our approach achieves 38% and 150% improvement in the evaluation metric over manually crafted and unplanned workflows respectively. In practice, when building features for recommendation models serving over 120 million users, our approach has delivered real-world impact by reducing feature engineering cycles from three weeks to a single day.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Line-based Event Preprocessing: Towards Low-Energy Neuromorphic Computer Vision
arXiv:2601.10742v1 Announce Type: cross
Abstract: Neuromorphic vision made significant progress in recent years, thanks to the natural match between spiking neural networks and event data in terms of biological inspiration, energy savings, latency and memory use for dynamic visual data processing. However, optimising its energy requirements still remains a challenge within the community, especially for embedded applications. One solution may reside in preprocessing events to optimise data quantity thus lowering the energy cost on neuromorphic hardware, proportional to the number of synaptic operations. To this end, we extend an end-to-end neuromorphic line detection mechanism to introduce line-based event data preprocessing. Our results demonstrate on three benchmark event-based datasets that preprocessing leads to an advantageous trade-off between energy consumption and classification performance. Depending on the line-based preprocessing strategy and the complexity of the classification task, we show that one can maintain or increase the classification accuracy while significantly reducing the theoretical energy consumption. Our approach systematically leads to a significant improvement of the neuromorphic classification efficiency, thus laying the groundwork towards a more frugal neuromorphic computer vision thanks to event preprocessing.
Fonte: arXiv cs.AI
Applications • Score 90
BoxMind: Closed-loop AI strategy optimization for elite boxing validated in the 2024 Olympics
arXiv:2601.11492v1 Announce Type: new
Abstract: Competitive sports require sophisticated tactical analysis, yet combat disciplines like boxing remain underdeveloped in AI-driven analytics due to the complexity of action dynamics and the lack of structured tactical representations. To address this, we present BoxMind, a closed-loop AI expert system validated in elite boxing competition. By defining atomic punch events with precise temporal boundaries and spatial and technical attributes, we parse match footage into 18 hierarchical technical-tactical indicators. We then propose a graph-based predictive model that fuses these explicit technical-tactical profiles with learnable, time-variant latent embeddings to capture the dynamics of boxer matchups. Modeling match outcome as a differentiable function of technical-tactical indicators, we turn winning probability gradients into executable tactical adjustments. Experiments show that the outcome prediction model achieves state-of-the-art performance, with 69.8% accuracy on BoxerGraph test set and 87.5% on Olympic matches. Using this predictive model as a foundation, the system generates strategic recommendations that demonstrate proficiency comparable to human experts. BoxMind is validated through a closed-loop deployment during the 2024 Paris Olympics, directly contributing to the Chinese National Team's historic achievement of three gold and two silver medals. BoxMind establishes a replicable paradigm for transforming unstructured video data into strategic intelligence, bridging the gap between computer vision and decision support in competitive sports.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
ReCreate: Reasoning and Creating Domain Agents Driven by Experience
arXiv:2601.11100v1 Announce Type: new
Abstract: Large Language Model agents are reshaping the industrial landscape. However, most practical agents remain human-designed because tasks differ widely, making them labor-intensive to build. This situation poses a central question: can we automatically create and adapt domain agents in the wild? While several recent approaches have sought to automate agent creation, they typically treat agent generation as a black-box procedure and rely solely on final performance metrics to guide the process. Such strategies overlook critical evidence explaining why an agent succeeds or fails, and often require high computational costs. To address these limitations, we propose ReCreate, an experience-driven framework for the automatic creation of domain agents. ReCreate systematically leverages agent interaction histories, which provide rich concrete signals on both the causes of success or failure and the avenues for improvement. Specifically, we introduce an agent-as-optimizer paradigm that effectively learns from experience via three key components: (i) an experience storage and retrieval mechanism for on-demand inspection; (ii) a reasoning-creating synergy pipeline that maps execution experience into scaffold edits; and (iii) hierarchical updates that abstract instance-level details into reusable domain patterns. In experiments across diverse domains, ReCreate consistently outperforms human-designed agents and existing automated agent generation methods, even when starting from minimal seed scaffolds.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
CTHA: Constrained Temporal Hierarchical Architecture for Stable Multi-Agent LLM Systems
arXiv:2601.10738v1 Announce Type: new
Abstract: Recently, multi-time-scale agent architectures have extended the ubiquitous single-loop paradigm by introducing temporal hierarchies with distinct cognitive layers. While yielding substantial performance gains, this diversification fundamentally compromises the coordination stability intrinsic to unified agent systems, which causes severe inter-layer conflicts, unbounded error propagation, and restricted scalability. To address these challenges, we propose Constrained Temporal Hierarchical Architecture (CTHA), a general framework that projects the inter-layer communication space onto structured manifolds to restore coordination stability, while incorporating principled arbitration mechanisms to ensure coherent decision-making. Specifically, CTHA enforces three key constraints: (1) Message Contract Constraints that formalize information flow between layers via typed summary, plan, and policy packets; (2) Authority Manifold Constraints that bound each layer's decision space according to its temporal scope; and (3) Arbiter Resolution Constraints that guarantee conflict-free composition of multi-layer decisions. Empirical experiments demonstrate that CTHA is effective for complex task execution at scale, offering 47% reduction in failure cascades, 2.3x improvement in sample efficiency, and superior scalability compared to unconstrained hierarchical baselines. We anticipate that CTHA, as a principled extension of temporal hierarchies, will contribute to a deeper understanding of multi-agent coordination and suggest promising directions for the evolution of robust autonomous systems.
Fonte: arXiv cs.AI
Vision • Score 90
Self-learned representation-guided latent diffusion model for breast cancer classification in deep ultraviolet whole surface images
arXiv:2601.10917v1 Announce Type: cross
Abstract: Breast-Conserving Surgery (BCS) requires precise intraoperative margin assessment to preserve healthy tissue. Deep Ultraviolet Fluorescence Scanning Microscopy (DUV-FSM) offers rapid, high-resolution surface imaging for this purpose; however, the scarcity of annotated DUV data hinders the training of robust deep learning models. To address this, we propose an Self-Supervised Learning (SSL)-guided Latent Diffusion Model (LDM) to generate high-quality synthetic training patches. By guiding the LDM with embeddings from a fine-tuned DINO teacher, we inject rich semantic details of cellular structures into the synthetic data. We combine real and synthetic patches to fine-tune a Vision Transformer (ViT), utilizing patch prediction aggregation for WSI-level classification. Experiments using 5-fold cross-validation demonstrate that our method achieves 96.47 % accuracy and reduces the FID score to 45.72, significantly outperforming class-conditioned baselines.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
PaperScout: An Autonomous Agent for Academic Paper Search with Process-Aware Sequence-Level Policy Optimization
arXiv:2601.10029v1 Announce Type: new
Abstract: Academic paper search is a fundamental task in scientific research, yet most existing approaches rely on rigid, predefined workflows that struggle with complex, conditional queries. To address this limitation, we propose PaperScout, an autonomous agent that reformulates paper search as a sequential decision-making process. Unlike static workflows, PaperScout dynamically decides whether, when, and how to invoke search and expand tools based on accumulated retrieval context. However, training such agents presents a fundamental challenge: standard reinforcement learning methods, typically designed for single-turn tasks, suffer from a granularity mismatch when applied to multi-turn agentic tasks, where token-level optimization diverges from the granularity of sequence-level interactions, leading to noisy credit assignment. We introduce Proximal Sequence Policy Optimization (PSPO), a process-aware, sequence-level policy optimization method that aligns optimization with agent-environment interaction. Comprehensive experiments on both synthetic and real-world benchmarks demonstrate that PaperScout significantly outperforms strong workflow-driven and RL baselines in both recall and relevance, validating the effectiveness of our adaptive agentic framework and optimization strategy.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Beyond Rule-Based Workflows: An Information-Flow-Orchestrated Multi-Agents Paradigm via Agent-to-Agent Communication from CORAL
arXiv:2601.09883v1 Announce Type: new
Abstract: Most existing Large Language Model (LLM)-based Multi-Agent Systems (MAS) rely on predefined workflows, where human engineers enumerate task states in advance and specify routing rules and contextual injections accordingly. Such workflow-driven designs are essentially rule-based decision trees, which suffer from two fundamental limitations: they require substantial manual effort to anticipate and encode possible task states, and they cannot exhaustively cover the state space of complex real-world tasks. To address these issues, we propose an Information-Flow-Orchestrated Multi-Agent Paradigm via Agent-to-Agent (A2A) Communication from CORAL, in which a dedicated information flow orchestrator continuously monitors task progress and dynamically coordinates other agents through the A2A toolkit using natural language, without relying on predefined workflows. We evaluate our approach on the general-purpose benchmark GAIA, using the representative workflow-based MAS OWL as the baseline while controlling for agent roles and underlying models. Under the pass@1 setting, our method achieves 63.64% accuracy, outperforming OWL's 55.15% by 8.49 percentage points with comparable token consumption. Further case-level analysis shows that our paradigm enables more flexible task monitoring and more robust handling of edge cases. Our implementation is publicly available at: https://github.com/Coral-Protocol/Beyond-Rule-Based-Workflows
Fonte: arXiv cs.AI
Privacy/Security/Fairness • Score 85
CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents
arXiv:2601.09923v1 Announce Type: new
Abstract: AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior to steal credentials or cause financial loss. The only known robust defense is architectural isolation that strictly separates trusted task planning from untrusted environment observations. However, applying this design to Computer Use Agents (CUAs) -- systems that automate tasks by viewing screens and executing actions -- presents a fundamental challenge: current agents require continuous observation of UI state to determine each action, conflicting with the isolation required for security. We resolve this tension by demonstrating that UI workflows, while dynamic, are structurally predictable. We introduce Single-Shot Planning for CUAs, where a trusted planner generates a complete execution graph with conditional branches before any observation of potentially malicious content, providing provable control flow integrity guarantees against arbitrary instruction injections. Although this architectural isolation successfully prevents instruction injections, we show that additional measures are needed to prevent Branch Steering attacks, which manipulate UI elements to trigger unintended valid paths within the plan. We evaluate our design on OSWorld, and retain up to 57% of the performance of frontier models while improving performance for smaller open-source models by up to 19%, demonstrating that rigorous security and utility can coexist in CUAs.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
M^4olGen: Multi-Agent, Multi-Stage Molecular Generation under Precise Multi-Property Constraints
arXiv:2601.10131v1 Announce Type: new
Abstract: Generating molecules that satisfy precise numeric constraints over multiple physicochemical properties is critical and challenging. Although large language models (LLMs) are expressive, they struggle with precise multi-objective control and numeric reasoning without external structure and feedback. We introduce \textbf{M olGen}, a fragment-level, retrieval-augmented, two-stage framework for molecule generation under multi-property constraints. Stage I : Prototype generation: a multi-agent reasoner performs retrieval-anchored, fragment-level edits to produce a candidate near the feasible region. Stage II : RL-based fine-grained optimization: a fragment-level optimizer trained with Group Relative Policy Optimization (GRPO) applies one- or multi-hop refinements to explicitly minimize the property errors toward our target while regulating edit complexity and deviation from the prototype. A large, automatically curated dataset with reasoning chains of fragment edits and measured property deltas underpins both stages, enabling deterministic, reproducible supervision and controllable multi-hop reasoning. Unlike prior work, our framework better reasons about molecules by leveraging fragments and supports controllable refinement toward numeric targets. Experiments on generation under two sets of property constraints (QED, LogP, Molecular Weight and HOMO, LUMO) show consistent gains in validity and precise satisfaction of multi-property targets, outperforming strong LLMs and graph-based algorithms.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Topo-RAG: Topology-aware retrieval for hybrid text-table documents
arXiv:2601.10215v1 Announce Type: new
Abstract: In enterprise datasets, documents are rarely pure. They are not just text, nor just numbers; they are a complex amalgam of narrative and structure. Current Retrieval-Augmented Generation (RAG) systems have attempted to address this complexity with a blunt tool: linearization. We convert rich, multidimensional tables into simple Markdown-style text strings, hoping that an embedding model will capture the geometry of a spreadsheet in a single vector. But it has already been shown that this is mathematically insufficient.
This work presents Topo-RAG, a framework that challenges the assumption that "everything is text". We propose a dual architecture that respects the topology of the data: we route fluid narrative through traditional dense retrievers, while tabular structures are processed by a Cell-Aware Late Interaction mechanism, preserving their spatial relationships. Evaluated on SEC-25, a synthetic enterprise corpus that mimics real-world complexity, Topo-RAG demonstrates an 18.4% improvement in nDCG@10 on hybrid queries compared to standard linearization approaches. It's not just about searching better; it's about understanding the shape of information.
Fonte: arXiv cs.AI
RecSys • Score 85
PCN-Rec: Agentic Proof-Carrying Negotiation for Reliable Governance-Constrained Recommendation
arXiv:2601.09771v1 Announce Type: new
Abstract: Modern LLM-based recommenders can generate compelling ranked lists, but they struggle to reliably satisfy governance constraints such as minimum long-tail exposure or diversity requirements. We present PCN-Rec, a proof-carrying negotiation pipeline that separates natural-language reasoning from deterministic enforcement. A base recommender (MF/CF) produces a candidate window of size W, which is negotiated by two agents: a User Advocate optimizing relevance and a Policy Agent enforcing constraints. A mediator LLM synthesizes a top-N slate together with a structured certificate (JSON) describing the claimed constraint satisfaction. A deterministic verifier recomputes all constraints from the slate and accepts only verifier-checked certificates; if verification fails, a deterministic constrained-greedy repair produces a compliant slate for re-verification, yielding an auditable trace. On MovieLens-100K with governance constraints, PCN-Rec achieves a 98.55% pass rate on feasible users (n = 551, W = 80) versus a one-shot single-LLM baseline without verification/repair, while preserving utility with only a 0.021 absolute drop in NDCG@10 (0.403 vs. 0.424); differences are statistically significant (p < 0.05).
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
SPRInG: Continual LLM Personalization via Selective Parametric Adaptation and Retrieval-Interpolated Generation
arXiv:2601.09974v1 Announce Type: new
Abstract: Personalizing Large Language Models typically relies on static retrieval or one-time adaptation, assuming user preferences remain invariant over time. However, real-world interactions are dynamic, where user interests continuously evolve, posing a challenge for models to adapt to preference drift without catastrophic forgetting. Standard continual learning approaches often struggle in this context, as they indiscriminately update on noisy interaction streams, failing to distinguish genuine preference shifts from transient contexts. To address this, we introduce SPRInG, a novel semi-parametric framework designed for effective continual personalization. During training, SPRInG employs drift-driven selective adaptation, which utilizes a likelihood-based scoring function to identify high-novelty interactions. This allows the model to selectively update the user-specific adapter on drift signals while preserving hard-to-learn residuals in a replay buffer. During inference, we apply strict relevance gating and fuse parametric knowledge with retrieved history via logit interpolation. Experiments on the long-form personalized generation benchmark demonstrate that SPRInG outperforms existing baselines, validating its robustness for real-world continual personalization.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
How does downsampling affect needle electromyography signals? A generalisable workflow for understanding downsampling effects on high-frequency time series
arXiv:2601.10191v1 Announce Type: new
Abstract: Automated analysis of needle electromyography (nEMG) signals is emerging as a tool to support the detection of neuromuscular diseases (NMDs), yet the signals' high and heterogeneous sampling rates pose substantial computational challenges for feature-based machine-learning models, particularly for near real-time analysis. Downsampling offers a potential solution, but its impact on diagnostic signal content and classification performance remains insufficiently understood. This study presents a workflow for systematically evaluating information loss caused by downsampling in high-frequency time series. The workflow combines shape-based distortion metrics with classification outcomes from available feature-based machine learning models and feature space analysis to quantify how different downsampling algorithms and factors affect both waveform integrity and predictive performance. We use a three-class NMD classification task to experimentally evaluate the workflow. We demonstrate how the workflow identifies downsampling configurations that preserve diagnostic information while substantially reducing computational load. Analysis of shape-based distortion metrics showed that shape-aware downsampling algorithms outperform standard decimation, as they better preserve peak structure and overall signal morphology. The results provide practical guidance for selecting downsampling configurations that enable near real-time nEMG analysis and highlight a generalisable workflow that can be used to balance data reduction with model performance in other high-frequency time-series applications as well.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
MHub.ai: A Simple, Standardized, and Reproducible Platform for AI Models in Medical Imaging
arXiv:2601.10154v1 Announce Type: new
Abstract: Artificial intelligence (AI) has the potential to transform medical imaging by automating image analysis and accelerating clinical research. However, research and clinical use are limited by the wide variety of AI implementations and architectures, inconsistent documentation, and reproducibility issues. Here, we introduce MHub.ai, an open-source, container-based platform that standardizes access to AI models with minimal configuration, promoting accessibility and reproducibility in medical imaging. MHub.ai packages models from peer-reviewed publications into standardized containers that support direct processing of DICOM and other formats, provide a unified application interface, and embed structured metadata. Each model is accompanied by publicly available reference data that can be used to confirm model operation. MHub.ai includes an initial set of state-of-the-art segmentation, prediction, and feature extraction models for different modalities. The modular framework enables adaptation of any model and supports community contributions. We demonstrate the utility of the platform in a clinical use case through comparative evaluation of lung segmentation models. To further strengthen transparency and reproducibility, we publicly release the generated segmentations and evaluation metrics and provide interactive dashboards that allow readers to inspect individual cases and reproduce or extend our analysis. By simplifying model use, MHub.ai enables side-by-side benchmarking with identical execution commands and standardized outputs, and lowers the barrier to clinical translation.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering
arXiv:2601.10402v1 Announce Type: new
Abstract: The advancement of artificial intelligence toward agentic science is currently bottlenecked by the challenge of ultra-long-horizon autonomy, the ability to sustain strategic coherence and iterative correction over experimental cycles spanning days or weeks. While Large Language Models (LLMs) have demonstrated prowess in short-horizon reasoning, they are easily overwhelmed by execution details in the high-dimensional, delayed-feedback environments of real-world research, failing to consolidate sparse feedback into coherent long-term guidance. Here, we present ML-Master 2.0, an autonomous agent that masters ultra-long-horizon machine learning engineering (MLE) which is a representative microcosm of scientific discovery. By reframing context management as a process of cognitive accumulation, our approach introduces Hierarchical Cognitive Caching (HCC), a multi-tiered architecture inspired by computer systems that enables the structural differentiation of experience over time. By dynamically distilling transient execution traces into stable knowledge and cross-task wisdom, HCC allows agents to decouple immediate execution from long-term experimental strategy, effectively overcoming the scaling limits of static context windows. In evaluations on OpenAI's MLE-Bench under 24-hour budgets, ML-Master 2.0 achieves a state-of-the-art medal rate of 56.44%. Our findings demonstrate that ultra-long-horizon autonomy provides a scalable blueprint for AI capable of autonomous exploration beyond human-precedent complexities.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
FilDeep: Learning Large Deformations of Elastic-Plastic Solids with Multi-Fidelity Data
arXiv:2601.10031v1 Announce Type: new
Abstract: The scientific computation of large deformations in elastic-plastic solids is crucial in various manufacturing applications. Traditional numerical methods exhibit several inherent limitations, prompting Deep Learning (DL) as a promising alternative. The effectiveness of current DL techniques typically depends on the availability of high-quantity and high-accuracy datasets, which are yet difficult to obtain in large deformation problems. During the dataset construction process, a dilemma stands between data quantity and data accuracy, leading to suboptimal performance in the DL models. To address this challenge, we focus on a representative application of large deformations, the stretch bending problem, and propose FilDeep, a Fidelity-based Deep Learning framework for large Deformation of elastic-plastic solids. Our FilDeep aims to resolve the quantity-accuracy dilemma by simultaneously training with both low-fidelity and high-fidelity data, where the former provides greater quantity but lower accuracy, while the latter offers higher accuracy but in less quantity. In FilDeep, we provide meticulous designs for the practical large deformation problem. Particularly, we propose attention-enabled cross-fidelity modules to effectively capture long-range physical interactions across MF data. To the best of our knowledge, our FilDeep presents the first DL framework for large deformation problems using MF data. Extensive experiments demonstrate that our FilDeep consistently achieves state-of-the-art performance and can be efficiently deployed in manufacturing.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
History Is Not Enough: An Adaptive Dataflow System for Financial Time-Series Synthesis
arXiv:2601.10143v1 Announce Type: new
Abstract: In quantitative finance, the gap between training and real-world performance-driven by concept drift and distributional non-stationarity-remains a critical obstacle for building reliable data-driven systems. Models trained on static historical data often overfit, resulting in poor generalization in dynamic markets. The mantra "History Is Not Enough" underscores the need for adaptive data generation that learns to evolve with the market rather than relying solely on past observations. We present a drift-aware dataflow system that integrates machine learning-based adaptive control into the data curation process. The system couples a parameterized data manipulation module comprising single-stock transformations, multi-stock mix-ups, and curation operations, with an adaptive planner-scheduler that employs gradient-based bi-level optimization to control the system. This design unifies data augmentation, curriculum learning, and data workflow management under a single differentiable framework, enabling provenance-aware replay and continuous data quality monitoring. Extensive experiments on forecasting and reinforcement learning trading tasks demonstrate that our framework enhances model robustness and improves risk-adjusted returns. The system provides a generalizable approach to adaptive data management and learning-guided workflow automation for financial data.
Fonte: arXiv cs.AI
Applications • Score 85
WaterCopilot: An AI-Driven Virtual Assistant for Water Management
arXiv:2601.08559v1 Announce Type: new
Abstract: Sustainable water resource management in transboundary river basins is challenged by fragmented data, limited real-time access, and the complexity of integrating diverse information sources. This paper presents WaterCopilot-an AI-driven virtual assistant developed through collaboration between the International Water Management Institute (IWMI) and Microsoft Research for the Limpopo River Basin (LRB) to bridge these gaps through a unified, interactive platform. Built on Retrieval-Augmented Generation (RAG) and tool-calling architectures, WaterCopilot integrates static policy documents and real-time hydrological data via two custom plugins: the iwmi-doc-plugin, which enables semantic search over indexed documents using Azure AI Search, and the iwmi-api-plugin, which queries live databases to deliver dynamic insights such as environmental-flow alerts, rainfall trends, reservoir levels, water accounting, and irrigation data. The system features guided multilingual interactions (English, Portuguese, French), transparent source referencing, automated calculations, and visualization capabilities. Evaluated using the RAGAS framework, WaterCopilot achieves an overall score of 0.8043, with high answer relevancy (0.8571) and context precision (0.8009). Key innovations include automated threshold-based alerts, integration with the LRB Digital Twin, and a scalable deployment pipeline hosted on AWS. While limitations in processing non-English technical documents and API latency remain, WaterCopilot establishes a replicable AI-augmented framework for enhancing water governance in data-scarce, transboundary contexts. The study demonstrates the potential of this AI assistant to support informed, timely decision-making and strengthen water security in complex river basins.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Resisting Manipulative Bots in Memecoin Copy Trading: A Multi-Agent Approach with Chain-of-Thought Reasoning
arXiv:2601.08641v1 Announce Type: new
Abstract: The launch of \$Trump coin ignited a wave in meme coin investment. Copy trading, as a strategy-agnostic approach that eliminates the need for deep trading knowledge, quickly gains widespread popularity in the meme coin market. However, copy trading is not a guarantee of profitability due to the prevalence of manipulative bots, the uncertainty of the followed wallets' future performance, and the lag in trade execution. Recently, large language models (LLMs) have shown promise in financial applications by effectively understanding multi-modal data and producing explainable decisions. However, a single LLM struggles with complex, multi-faceted tasks such as asset allocation. These challenges are even more pronounced in cryptocurrency markets, where LLMs often lack sufficient domain-specific knowledge in their training data.
To address these challenges, we propose an explainable multi-agent system for meme coin copy trading. Inspired by the structure of an asset management team, our system decomposes the complex task into subtasks and coordinates specialized agents to solve them collaboratively. Employing few-shot chain-of-though (CoT) prompting, each agent acquires professional meme coin trading knowledge, interprets multi-modal data, and generates explainable decisions. Using a dataset of 1,000 meme coin projects' transaction data, our empirical evaluation shows that the proposed multi-agent system outperforms both traditional machine learning models and single LLMs, achieving 73% and 70% precision in identifying high-quality meme coin projects and key opinion leader (KOL) wallets, respectively. The selected KOLs collectively generated a total profit of \$500,000 across these projects.
Fonte: arXiv cs.AI
Vision • Score 85
Sketch-Based Facade Renovation With Generative AI: A Streamlined Framework for Bypassing As-Built Modelling in Industrial Adaptive Reuse
arXiv:2601.08531v1 Announce Type: new
Abstract: Facade renovation offers a more sustainable alternative to full demolition, yet producing design proposals that preserve existing structures while expressing new intent remains challenging. Current workflows typically require detailed as-built modelling before design, which is time-consuming, labour-intensive, and often involves repeated revisions. To solve this issue, we propose a three-stage framework combining generative artificial intelligence (AI) and vision-language models (VLM) that directly processes rough structural sketch and textual descriptions to produce consistent renovation proposals. First, the input sketch is used by a fine-tuned VLM model to predict bounding boxes specifying where modifications are needed and which components should be added. Next, a stable diffusion model generates detailed sketches of new elements, which are merged with the original outline through a generative inpainting pipeline. Finally, ControlNet is employed to refine the result into a photorealistic image. Experiments on datasets and real industrial buildings indicate that the proposed framework can generate renovation proposals that preserve the original structure while improving facade detail quality. This approach effectively bypasses the need for detailed as-built modelling, enabling architects to rapidly explore design alternatives, iterate on early-stage concepts, and communicate renovation intentions with greater clarity.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
The Agent's First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios
arXiv:2601.08173v1 Announce Type: new
Abstract: The rapid evolution of Multi-modal Large Language Models (MLLMs) has advanced workflow automation; however, existing research mainly targets performance upper bounds in static environments, overlooking robustness for stochastic real-world deployment. We identify three key challenges: dynamic task scheduling, active exploration under uncertainty, and continuous learning from experience. To bridge this gap, we introduce \method{}, a dynamic evaluation environment that simulates a "trainee" agent continuously exploring a novel setting. Unlike traditional benchmarks, \method{} evaluates agents along three dimensions: (1) context-aware scheduling for streaming tasks with varying priorities; (2) prudent information acquisition to reduce hallucination via active exploration; and (3) continuous evolution by distilling generalized strategies from rule-based, dynamically generated tasks. Experiments show that cutting-edge agents have significant deficiencies in dynamic environments, especially in active exploration and continual learning. Our work establishes a framework for assessing agent reliability, shifting evaluation from static tests to realistic, production-oriented scenarios. Our codes are available at https://github.com/KnowledgeXLab/EvoEnv
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
Hybrid Distillation with CoT Guidance for Edge-Drone Control Code Generation
arXiv:2601.08412v1 Announce Type: new
Abstract: With large language models demonstrating significant potential in code generation tasks, their application to onboard control of resource-constrained Unmanned Aerial Vehicles has emerged as an important research direction. However, a notable contradiction exists between the high resource consumption of large models and the real-time, lightweight requirements of UAV platforms. This paper proposes an integrated approach that combines knowledge distillation, chain-of-thought guidance, and supervised fine-tuning for UAV multi-SDK control tasks, aiming to efficiently transfer complex reasoning and code generation capabilities to smaller models. Firstly, a high-quality dataset covering various mainstream UAV SDKs is constructed, featuring instruction-code-reasoning chains, and incorporates counterfactual negative samples for data augmentation, guiding the model to learn the end-to-end logic from instruction parsing to code generation. Secondly, leveraging DeepSeek-Coder-V2-Lite quantized via QLoRA as the teacher model, and based on a hybrid black-box and white-box distillation strategy, high-quality chain-of-thought soft labels are generated. These are combined with a weighted cross-entropy loss using hard labels to transfer complex reasoning capabilities to the smaller student model. Finally, through prompt tuning engineering optimized for the UAV control scenario, the model performance on core tasks such as SDK type recognition and function call matching is enhanced. Experimental results indicate that the distilled lightweight model maintains high code generation accuracy while achieving significant improvements in deployment and inference efficiency, effectively demonstrating the feasibility and superiority of our approach in achieving precise and lightweight intelligent control for UAVs
Fonte: arXiv cs.AI
RL • Score 85
AtomMem : Learnable Dynamic Agentic Memory with Atomic Memory Operation
arXiv:2601.08323v1 Announce Type: new
Abstract: Equipping agents with memory is essential for solving real-world long-horizon problems. However, most existing agent memory mechanisms rely on static and hand-crafted workflows. This limits the performance and generalization ability of these memory designs, which highlights the need for a more flexible, learning-based memory framework. In this paper, we propose AtomMem, which reframes memory management as a dynamic decision-making problem. We deconstruct high-level memory processes into fundamental atomic CRUD (Create, Read, Update, Delete) operations, transforming the memory workflow into a learnable decision process. By combining supervised fine-tuning with reinforcement learning, AtomMem learns an autonomous, task-aligned policy to orchestrate memory behaviors tailored to specific task demands. Experimental results across 3 long-context benchmarks demonstrate that the trained AtomMem-8B consistently outperforms prior static-workflow memory methods. Further analysis of training dynamics shows that our learning-based formulation enables the agent to discover structured, task-aligned memory management strategies, highlighting a key advantage over predefined routines.
Fonte: arXiv cs.AI
RL • Score 85
Forecast Aware Deep Reinforcement Learning for Efficient Electricity Load Scheduling in Dairy Farms
arXiv:2601.08052v1 Announce Type: new
Abstract: Dairy farming is an energy intensive sector that relies heavily on grid electricity. With increasing renewable energy integration, sustainable energy management has become essential for reducing grid dependence and supporting the United Nations Sustainable Development Goal 7 on affordable and clean energy. However, the intermittent nature of renewables poses challenges in balancing supply and demand in real time. Intelligent load scheduling is therefore crucial to minimize operational costs while maintaining reliability. Reinforcement Learning has shown promise in improving energy efficiency and reducing costs. However, most RL-based scheduling methods assume complete knowledge of future prices or generation, which is unrealistic in dynamic environments. Moreover, standard PPO variants rely on fixed clipping or KL divergence thresholds, often leading to unstable training under variable tariffs. To address these challenges, this study proposes a Deep Reinforcement Learning framework for efficient load scheduling in dairy farms, focusing on battery storage and water heating under realistic operational constraints. The proposed Forecast Aware PPO incorporates short term forecasts of demand and renewable generation using hour of day and month based residual calibration, while the PID KL PPO variant employs a proportional integral derivative controller to regulate KL divergence for stable policy updates adaptively. Trained on real world dairy farm data, the method achieves up to 1% lower electricity cost than PPO, 4.8% than DQN, and 1.5% than SAC. For battery scheduling, PPO reduces grid imports by 13.1%, demonstrating scalability and effectiveness for sustainable energy management in modern dairy farming.
Fonte: arXiv cs.AI
Applications • Score 85
Integrating Attendance Tracking and Emotion Detection for Enhanced Student Engagement in Smart Classrooms
arXiv:2601.08049v1 Announce Type: new
Abstract: The increasing adoption of smart classroom technologies in higher education has mainly focused on automating attendance, with limited attention given to students' emotional and cognitive engagement during lectures. This limits instructors' ability to identify disengagement and adapt teaching strategies in real time. This paper presents SCASED (Smart Classroom Attendance System with Emotion Detection), an IoT-based system that integrates automated attendance tracking with facial emotion recognition to support classroom engagement monitoring. The system uses a Raspberry Pi camera and OpenCV for face detection, and a finetuned MobileNetV2 model to classify four learning-related emotional states: engagement, boredom, confusion, and frustration. A session-based mechanism is implemented to manage attendance and emotion monitoring by recording attendance once per session and performing continuous emotion analysis thereafter. Attendance and emotion data are visualized through a cloud-based dashboard to provide instructors with insights into classroom dynamics. Experimental evaluation using the DAiSEE dataset achieved an emotion classification accuracy of 89.5%. The results show that integrating attendance data with emotion analytics can provide instructors with additional insight into classroom dynamics and support more responsive teaching practices.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
ToolACE-MCP: Generalizing History-Aware Routing from MCP Tools to the Agent Web
arXiv:2601.08276v1 Announce Type: new
Abstract: With the rise of the Agent Web and Model Context Protocol (MCP), the agent ecosystem is evolving into an open collaborative network, exponentially increasing accessible tools. However, current architectures face severe scalability and generality bottlenecks. To address this, we propose ToolACE-MCP, a pipeline for training history-aware routers to empower precise navigation in large-scale ecosystems. By leveraging a dependency-rich candidate Graph to synthesize multi-turn trajectories, we effectively train routers with dynamic context understanding to create the plug-and-play Light Routing Agent. Experiments on the real-world benchmarks MCP-Universe and MCP-Mark demonstrate superior performance. Notably, ToolACE-MCP exhibits critical properties for the future Agent Web: it not only generalizes to multi-agent collaboration with minimal adaptation but also maintains exceptional robustness against noise and scales effectively to massive candidate spaces. These findings provide a strong empirical foundation for universal orchestration in open-ended ecosystems.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
Embedded AI Companion System on Edge Devices
arXiv:2601.08128v1 Announce Type: new
Abstract: Computational resource constraints on edge devices make it difficult to develop a fully embedded AI companion system with a satisfactory user experience. AI companion and memory systems detailed in existing literature cannot be directly used in such an environment due to lack of compute resources and latency concerns. In this paper, we propose a memory paradigm that alternates between active and inactive phases: during phases of user activity, the system performs low-latency, real-time dialog using lightweight retrieval over existing memories and context; whereas during phases of user inactivity, it conducts more computationally intensive extraction, consolidation, and maintenance of memories across full conversation sessions. This design minimizes latency while maintaining long-term personalization under the tight constraints of embedded hardware. We also introduce an AI Companion benchmark designed to holistically evaluate the AI Companion across both its conversational quality and memory capabilities. In our experiments, we found that our system (using a very weak model: Qwen2.5-7B-Instruct quantized int4) outperforms the equivalent raw LLM without memory across most metrics, and performs comparably to GPT-3.5 with 16k context window.
Fonte: arXiv cs.AI
RL • Score 85
Project Synapse: A Hierarchical Multi-Agent Framework with Hybrid Memory for Autonomous Resolution of Last-Mile Delivery Disruptions
arXiv:2601.08156v1 Announce Type: new
Abstract: This paper introduces Project Synapse, a novel agentic framework designed for the autonomous resolution of last-mile delivery disruptions. Synapse employs a hierarchical multi-agent architecture in which a central Resolution Supervisor agent performs strategic task decomposition and delegates subtasks to specialized worker agents responsible for tactical execution. The system is orchestrated using LangGraph to manage complex and cyclical workflows. To validate the framework, a benchmark dataset of 30 complex disruption scenarios was curated from a qualitative analysis of over 6,000 real-world user reviews. System performance is evaluated using an LLM-as-a-Judge protocol with explicit bias mitigation.
Fonte: arXiv cs.AI
RL • Score 85
ZeroDVFS: Zero-Shot LLM-Guided Core and Frequency Allocation for Embedded Platforms
arXiv:2601.08166v1 Announce Type: new
Abstract: Dynamic voltage and frequency scaling (DVFS) and task-to-core allocation are critical for thermal management and balancing energy and performance in embedded systems. Existing approaches either rely on utilization-based heuristics that overlook stall times, or require extensive offline profiling for table generation, preventing runtime adaptation. We propose a model-based hierarchical multi-agent reinforcement learning (MARL) framework for thermal- and energy-aware scheduling on multi-core platforms. Two collaborative agents decompose the exponential action space, achieving 358ms latency for subsequent decisions. First decisions require 3.5 to 8.0s including one-time LLM feature extraction. An accurate environment model leverages regression techniques to predict thermal dynamics and performance states. When combined with LLM-extracted semantic features, the environment model enables zero-shot deployment for new workloads on trained platforms by generating synthetic training data without requiring workload-specific profiling samples. We introduce LLM-based semantic feature extraction that characterizes OpenMP programs through 13 code-level features without execution. The Dyna-Q-inspired framework integrates direct reinforcement learning with model-based planning, achieving 20x faster convergence than model-free methods. Experiments on BOTS and PolybenchC benchmarks across NVIDIA Jetson TX2, Jetson Orin NX, RubikPi, and Intel Core i7 demonstrate 7.09x better energy efficiency and 4.0x better makespan than Linux ondemand governor. First-decision latency is 8,300x faster than table-based profiling, enabling practical deployment in dynamic embedded systems.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
LiveVectorLake: A Real-Time Versioned Knowledge Base Architecture for Streaming Vector Updates and Temporal Retrieval
arXiv:2601.05270v1 Announce Type: cross
Abstract: Modern Retrieval-Augmented Generation (RAG) systems struggle with a fundamental architectural tension: vector indices are optimized for query latency but poorly handle continuous knowledge updates, while data lakes excel at versioning but introduce query latency penalties. We introduce LiveVectorLake, a dual-tier temporal knowledge base architecture that enables real-time semantic search on current knowledge while maintaining complete version history for compliance, auditability, and point-in-time retrieval. The system introduces three core architectural contributions: (1) Content-addressable chunk-level synchronization using SHA-256 hashing for deterministic change detection without external state tracking; (2) Dual-tier storage separating hot-tier vector indices (Milvus with HNSW) from cold-tier columnar versioning (Delta Lake with Parquet), optimizing query latency and storage cost independently; (3) Temporal query routing enabling point-in-time knowledge retrieval via delta-versioning with ACID consistency across tiers. Evaluation on a 100-document corpus versioned across five time points demonstrates: (i) 10-15% re-processing of content during updates compared to 100% for full re-indexing; (ii) sub-100ms retrieval latency on current knowledge; (iii) sub-2s latency for temporal queries across version history; and (iv) storage cost optimization through hot/cold tier separation (only current chunks in expensive vector indices). The approach enables production RAG deployments requiring simultaneous optimization for query performance, update efficiency, and regulatory compliance. Code and resources: [https://github.com/praj-tarun/LiveVectorLake]
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
MoEBlaze: Breaking the Memory Wall for Efficient MoE Training on Modern GPUs
arXiv:2601.05296v1 Announce Type: cross
Abstract: The pervasive "memory wall" bottleneck is significantly amplified in modern large-scale Mixture-of-Experts (MoE) architectures. MoE's inherent architectural sparsity leads to sparse arithmetic compute and also introduces substantial activation memory overheads -- driven by large token routing buffers and the need to materialize and buffer intermediate tensors. This memory pressure limits the maximum batch size and sequence length that can fit on GPUs, and also results in excessive data movements that hinders performance and efficient model scaling. We present MoEBlaze, a memory-efficient MoE training framework that addresses these issues through a co-designed system approach: (i) an end-to-end token dispatch and MoE training method with optimized data structures to eliminate intermediate buffers and activation materializing, and (ii) co-designed kernels with smart activation checkpoint to mitigate memory footprint while simultaneously achieving better performance. We demonstrate that MoEBlaze can achieve over 4x speedups and over 50% memory savings compared to existing MoE frameworks.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Retrieval-Augmented Multi-LLM Ensemble for Industrial Part Specification Extraction
arXiv:2601.05266v1 Announce Type: cross
Abstract: Industrial part specification extraction from unstructured text remains a persistent challenge in manufacturing, procurement, and maintenance, where manual processing is both time-consuming and error-prone. This paper introduces a retrieval-augmented multi-LLM ensemble framework that orchestrates nine state-of-the-art Large Language Models (LLMs) within a structured three-phase pipeline. RAGsemble addresses key limitations of single-model systems by combining the complementary strengths of model families including Gemini (2.0, 2.5, 1.5), OpenAI (GPT-4o, o4-mini), Mistral Large, and Gemma (1B, 4B, 3n-e4b), while grounding outputs in factual data using FAISS-based semantic retrieval. The system architecture consists of three stages: (1) parallel extraction by diverse LLMs, (2) targeted research augmentation leveraging high-performing models, and (3) intelligent synthesis with conflict resolution and confidence-aware scoring. RAG integration provides real-time access to structured part databases, enabling the system to validate, refine, and enrich outputs through similarity-based reference retrieval. Experimental results using real industrial datasets demonstrate significant gains in extraction accuracy, technical completeness, and structured output quality compared to leading single-LLM baselines. Key contributions include a scalable ensemble architecture for industrial domains, seamless RAG integration throughout the pipeline, comprehensive quality assessment mechanisms, and a production-ready solution suitable for deployment in knowledge-intensive manufacturing environments.
Fonte: arXiv cs.AI
RL • Score 85
From Off-Policy to On-Policy: Enhancing GUI Agents via Bi-level Expert-to-Policy Assimilation
arXiv:2601.05787v1 Announce Type: new
Abstract: Vision-language models are increasingly deployed as computer-use agents (CUAs) that operate desktops and browsers. Top-performing CUAs are framework-based systems that decompose planning and execution, while end-to-end screenshot-to-action policies are easier to deploy but lag behind on benchmarks such as OSWorld-Verified. GUI datasets like OSWorld pose two bottlenecks: they expose only a few hundred interactive, verifiable tasks and environments, and expert trajectories must be gathered by interacting with these environments, making such data hard to scale. We therefore ask how reinforcement learning from verifiable rewards (RLVR) can best exploit a small pool of exist expert trajectories to train end-to-end policies. Naively mixing these off-policy traces into on-policy RLVR is brittle: even after format conversion, expert trajectories exhibit structural mismatch and distribution shift from the learner. We propose BEPA (Bi-Level Expert-to-Policy Assimilation), which turns static expert traces into policy-aligned guidance via self-rolled reachable trajectories under the base policy (LEVEL-1) and a per-task, dynamically updated cache used in RLVR (LEVEL-2). On OSWorld-Verified, BEPA improves UITARS1.5-7B success from 22.87% to 32.13% and raises a held-out split from 5.74% to 10.30%, with consistent gains on MMBench-GUI and Online-Mind2Web. Our code and data are available at: https://github.com/LEON-gittech/Verl_GUI.git
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Engenharia da RAG Stack: Uma Revisão Abrangente da Arquitetura e Frameworks de Confiança para Sistemas de Geração Aumentada por Recuperação
arXiv:2601.05264v1 Tipo de Anúncio: cruzado. Resumo: Este artigo fornece uma revisão sistemática abrangente da literatura sobre estudos acadêmicos, aplicações industriais e implementações do mundo real de 2018 a 2025, oferecendo um guia prático e uma visão detalhada das modernas arquiteturas de Geração Aumentada por Recuperação (RAG). RAG oferece uma abordagem modular para integrar conhecimento externo sem aumentar a capacidade do modelo à medida que os sistemas LLM se expandem. As práticas de pesquisa e engenharia têm sido fragmentadas em decorrência da crescente diversidade de metodologias RAG, que abrange uma variedade de mecanismos de fusão, estratégias de recuperação e abordagens de orquestração. Fornecemos frameworks de avaliação quantitativa, analisamos as implicações para confiança e alinhamento, e consolidamos sistematicamente as técnicas RAG existentes em uma taxonomia unificada. Este documento é um framework prático para a implementação de sistemas RAG resilientes, seguros e adaptáveis a domínios, sintetizando insights da literatura acadêmica, relatórios da indústria e guias de implementação técnica. Ele também funciona como uma referência técnica.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
StackPlanner: Um Sistema Multi-Agent Hierárquico Centralizado com Gerenciamento de Memória de Experiência de Tarefa
Sistemas multi-agente baseados em grandes modelos de linguagem, especialmente arquiteturas centralizadas, mostraram recentemente um forte potencial para tarefas complexas e intensivas em conhecimento. No entanto, agentes centrais frequentemente enfrentam problemas de colaboração instável a longo prazo devido à falta de gerenciamento de memória. Propomos o StackPlanner, um framework multi-agente hierárquico com controle de memória explícito.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
EvoC2Rust: A Skeleton-guided Framework for Project-Level C-to-Rust Translation
arXiv:2508.04295v3 Announce Type: cross
Abstract: Translating legacy C codebases to Rust is increasingly demanded for building safety-critical systems. While various approaches have emerged for this task, they face inherent trade-offs: rule-based methods often struggle to satisfy code safety and idiomaticity requirements, while LLM-based methods frequently fail to generate semantically equivalent Rust code, due to the heavy dependencies of modules across the entire codebase. Recent studies have revealed that both solutions are limited to small-scale programs. In this paper, we propose EvoC2Rust, an automated framework for converting complete C projects to equivalent Rust ones. EvoC2Rust employs a skeleton-guided translation strategy for project-level translation. The pipeline consists of three stages: 1) it first decomposes the C project into functional modules, employs a feature-mapping-enhanced LLM to transform definitions and macros, and generates type-checked function stubs, which form a compilable Rust skeleton; 2) it then incrementally translates functions, replacing the corresponding stub placeholders; 3) finally, it repairs compilation errors by integrating LLM and static analysis. Through evolutionary augmentation, EvoC2Rust combines the advantages of both rule-based and LLM-based solutions. Our evaluation on open-source benchmarks and six industrial projects demonstrates the superior performance of EvoC2Rust in project-level C-to-Rust translation. The results show that our approach outperforms the strongest LLM-based baseline by 17.24% in syntax accuracy and 14.32% in semantic accuracy, while also achieving a 43.59% higher code safety rate than the best rule-based tool.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
Toward Maturity-Based Certification of Embodied AI: Quantifying Trustworthiness Through Measurement Mechanisms
arXiv:2601.03470v1 Announce Type: new
Abstract: We propose a maturity-based framework for certifying embodied AI systems through explicit measurement mechanisms. We argue that certifiable embodied AI requires structured assessment frameworks, quantitative scoring mechanisms, and methods for navigating multi-objective trade-offs inherent in trustworthiness evaluation. We demonstrate this approach using uncertainty quantification as an exemplar measurement mechanism and illustrate feasibility through an Uncrewed Aircraft System (UAS) detection case study.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models
arXiv:2601.03969v1 Announce Type: new
Abstract: Large reasoning models enhanced by reinforcement learning with verifiable rewards have achieved significant performance gains by extending their chain-of-thought. However, this paradigm incurs substantial deployment costs as models often exhibit excessive verbosity on simple queries. Existing efficient reasoning methods relying on explicit length penalties often introduce optimization conflicts and leave the generative mechanisms driving overthinking largely unexamined. In this paper, we identify a phenomenon termed length shift where models increasingly generate unnecessary reasoning on trivial inputs during training. To address this, we introduce Dynamic Outlier Truncation (DOT), a training-time intervention that selectively suppresses redundant tokens. This method targets only the extreme tail of response lengths within fully correct rollout groups while preserving long-horizon reasoning capabilities for complex problems. To complement this intervention and ensure stable convergence, we further incorporate auxiliary KL regularization and predictive dynamic sampling. Experimental results across multiple model scales demonstrate that our approach significantly pushes the efficiency-performance Pareto frontier outward. Notably, on the AIME-24, our method reduces inference token usage by 78% while simultaneously increasing accuracy compared to the initial policy and surpassing state-of-the-art efficient reasoning methods.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Architecting Agentic Communities using Design Patterns
arXiv:2601.03624v1 Announce Type: new
Abstract: The rapid evolution of Large Language Models (LLM) and subsequent Agentic AI technologies requires systematic architectural guidance for building sophisticated, production-grade systems. This paper presents an approach for architecting such systems using design patterns derived from enterprise distributed systems standards, formal methods, and industry practice. We classify these patterns into three tiers: LLM Agents (task-specific automation), Agentic AI (adaptive goal-seekers), and Agentic Communities (organizational frameworks where AI agents and human participants coordinate through formal roles, protocols, and governance structures). We focus on Agentic Communities - coordination frameworks encompassing LLM Agents, Agentic AI entities, and humans - most relevant for enterprise and industrial applications. Drawing on established coordination principles from distributed systems, we ground these patterns in a formal framework that specifies collaboration agreements where AI agents and humans fill roles within governed ecosystems. This approach provides both practical guidance and formal verification capabilities, enabling expression of organizational, legal, and ethical rules through accountability mechanisms that ensure operational and verifiable governance of inter-agent communication, negotiation, and intent modeling. We validate this framework through a clinical trial matching case study. Our goal is to provide actionable guidance to practitioners while maintaining the formal rigor essential for enterprise deployment in dynamic, multi-agent ecosystems.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
ComfySearch: Autonomous Exploration and Reasoning for ComfyUI Workflows
arXiv:2601.04060v1 Announce Type: new
Abstract: AI-generated content has progressed from monolithic models to modular workflows, especially on platforms like ComfyUI, allowing users to customize complex creative pipelines. However, the large number of components in ComfyUI and the difficulty of maintaining long-horizon structural consistency under strict graph constraints frequently lead to low pass rates and workflows of limited quality. To tackle these limitations, we present ComfySearch, an agentic framework that can effectively explore the component space and generate functional ComfyUI pipelines via validation-guided workflow construction. Experiments demonstrate that ComfySearch substantially outperforms existing methods on complex and creative tasks, achieving higher executability (pass) rates, higher solution rates, and stronger generalization.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
Lightweight Transformer Architectures for Edge Devices in Real-Time Applications
arXiv:2601.03290v1 Announce Type: cross
Abstract: The deployment of transformer-based models on resource-constrained edge devices represents a critical challenge in enabling real-time artificial intelligence applications. This comprehensive survey examines lightweight transformer architectures specifically designed for edge deployment, analyzing recent advances in model compression, quantization, pruning, and knowledge distillation techniques. We systematically review prominent lightweight variants including MobileBERT, TinyBERT, DistilBERT, EfficientFormer, EdgeFormer, and MobileViT, providing detailed performance benchmarks on standard datasets such as GLUE, SQuAD, ImageNet-1K, and COCO. Our analysis encompasses current industry adoption patterns across major hardware platforms (NVIDIA Jetson, Qualcomm Snapdragon, Apple Neural Engine, ARM architectures), deployment frameworks (TensorFlow Lite, ONNX Runtime, PyTorch Mobile, CoreML), and optimization strategies. Experimental results demonstrate that modern lightweight transformers can achieve 75-96% of full-model accuracy while reducing model size by 4-10x and inference latency by 3-9x, enabling deployment on devices with as little as 2-5W power consumption. We identify sparse attention mechanisms, mixed-precision quantization (INT8/FP16), and hardware-aware neural architecture search as the most effective optimization strategies. Novel findings include memory-bandwidth bottleneck analysis revealing 15-40M parameter models achieve optimal hardware utilization (60-75% efficiency), quantization sweet spots for different model types, and comprehensive energy efficiency profiling across edge platforms. We establish real-time performance boundaries and provide a practical 6-step deployment pipeline achieving 8-12x size reduction with less than 2% accuracy degradation.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
A New Benchmark for the Appropriate Evaluation of RTL Code Optimization
arXiv:2601.01765v1 Announce Type: new
Abstract: The rapid progress of artificial intelligence increasingly relies on efficient integrated circuit (IC) design. Recent studies have explored the use of large language models (LLMs) for generating Register Transfer Level (RTL) code, but existing benchmarks mainly evaluate syntactic correctness rather than optimization quality in terms of power, performance, and area (PPA). This work introduces RTL-OPT, a benchmark for assessing the capability of LLMs in RTL optimization. RTL-OPT contains 36 handcrafted digital designs that cover diverse implementation categories including combinational logic, pipelined datapaths, finite state machines, and memory interfaces. Each task provides a pair of RTL codes, a suboptimal version and a human-optimized reference that reflects industry-proven optimization patterns not captured by conventional synthesis tools. Furthermore, RTL-OPT integrates an automated evaluation framework to verify functional correctness and quantify PPA improvements, enabling standardized and meaningful assessment of generative models for hardware design optimization.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
CaveAgent: Transforming LLMs into Stateful Runtime Operators
arXiv:2601.01569v1 Announce Type: new
Abstract: LLM-based agents are increasingly capable of complex task execution, yet current agentic systems remain constrained by text-centric paradigms. Traditional approaches rely on procedural JSON-based function calling, which often struggles with long-horizon tasks due to fragile multi-turn dependencies and context drift. In this paper, we present CaveAgent, a framework that transforms the paradigm from "LLM-as-Text-Generator" to "LLM-as-Runtime-Operator." We introduce a Dual-stream Context Architecture that decouples state management into a lightweight semantic stream for reasoning and a persistent, deterministic Python Runtime stream for execution. In addition to leveraging code generation to efficiently resolve interdependent sub-tasks (e.g., loops, conditionals) in a single step, we introduce \textit{Stateful Runtime Management} in CaveAgent. Distinct from existing code-based approaches that remain text-bound and lack the support for external object injection and retrieval, CaveAgent injects, manipulates, and retrieves complex Python objects (e.g., DataFrames, database connections) that persist across turns. This persistence mechanism acts as a high-fidelity external memory to eliminate context drift, avoid catastrophic forgetting, while ensuring that processed data flows losslessly to downstream applications. Comprehensive evaluations on Tau$^2$-bench, BFCL and various case studies across representative SOTA LLMs demonstrate CaveAgent's superiority. Specifically, our framework achieves a 10.5\% success rate improvement on retail tasks and reduces total token consumption by 28.4\% in multi-turn scenarios. On data-intensive tasks, direct variable storage and retrieval reduces token consumption by 59\%, allowing CaveAgent to handle large-scale data that causes context overflow failures in both JSON-based and Code-based agents.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
MathLedger: Um Substrato de Aprendizado Verificável com Feedback Atestado por Ledger
Os sistemas de IA contemporâneos alcançam desempenho extraordinário, mas permanecem opacos e não verificáveis, criando uma crise de confiança para implantações críticas de segurança. Apresentamos o MathLedger, um substrato para cognição de máquina verificável que integra verificação formal, atestação criptográfica e dinâmicas de aprendizado em um único loop epistêmico.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Temporal Attack Pattern Detection in Multi-Agent AI Workflows: An Open Framework for Training Trace-Based Security Models
arXiv:2601.00848v1 Announce Type: new
Abstract: We present an openly documented methodology for fine-tuning language models to detect temporal attack patterns in multi-agent AI workflows using OpenTelemetry trace analysis. We curate a dataset of 80,851 examples from 18 public cybersecurity sources and 35,026 synthetic OpenTelemetry traces. We apply iterative QLoRA fine-tuning on resource-constrained ARM64 hardware (NVIDIA DGX Spark) through three training iterations with strategic augmentation. Our custom benchmark accuracy improves from 42.86% to 74.29%, a statistically significant 31.4-point gain. Targeted examples addressing specific knowledge gaps outperform indiscriminate scaling. Key contributions include: (1) synthetic trace generation methodology for multi-agent coordination attacks and regulatory violations, (2) empirical evidence that training data composition fundamentally determines behavior, and (3) complete open release of datasets, training scripts, and evaluation benchmarks on HuggingFace. While practical deployment requires human oversight due to false positive rates, this work establishes the first reproducible framework enabling practitioners to build custom agentic security models adapted to their threat landscapes.
Fonte: arXiv cs.AI
MLOps/Systems • Score 85
Roteamento Consciente de Energia para Grandes Modelos de Raciocínio
Modelos de raciocínio grandes (LRMs) apresentam custos de energia de inferência heterogêneos, dependendo do modelo utilizado e da quantidade de raciocínio realizada. Para reduzir o consumo de energia, é crucial escolher o LRM adequado e operá-lo de forma eficiente. O desempenho dos sistemas que distribuem tarefas entre diferentes LRMs individuais depende do equilíbrio entre o fornecimento médio de energia e as flutuações estocásticas.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Jenius Agent: Towards Experience-Driven Accuracy Optimization in Real-World Scenarios
arXiv:2601.01857v1 Announce Type: new
Abstract: As agent systems powered by large language models (LLMs) advance, improving the task performance of an autonomous agent, especially in context understanding, tool usage, and response generation, has become increasingly critical. Although prior studies have advanced the overall design of LLM-based agents, systematic optimization of their internal reasoning and tool-use pipelines remains underexplored. This paper introduces an agent framework grounded in real-world practical experience, with three key innovations: (1) an adaptive prompt generation strategy that aligns with the agent's state and task goals to improve reliability and robustness; (2) a context-aware tool orchestration module that performs tool categorization, semantic retrieval, and adaptive invocation based on user intent and context; and (3) a layered memory mechanism that integrates session memory, task history, and external summaries to improve relevance and efficiency through dynamic summarization and compression. An end-to-end framework named Jenius-Agent has been integrated with three key optimizations, including tools based on the Model Context Protocol (MCP), file input/output (I/O), and execution feedback. The experiments show a 20 percent improvement in task accuracy, along with a reduced token cost, response latency, and invocation failures. The framework is already deployed in Jenius (https://www.jenius.cn), providing a lightweight and scalable solution for robust, protocol-compatible autonomous agents.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
Digital Twin AI: Opportunities and Challenges from Large Language Models to World Models
arXiv:2601.01321v1 Announce Type: new
Abstract: Digital twins, as precise digital representations of physical systems, have evolved from passive simulation tools into intelligent and autonomous entities through the integration of artificial intelligence technologies. This paper presents a unified four-stage framework that systematically characterizes AI integration across the digital twin lifecycle, spanning modeling, mirroring, intervention, and autonomous management. By synthesizing existing technologies and practices, we distill a unified four-stage framework that systematically characterizes how AI methodologies are embedded across the digital twin lifecycle: (1) modeling the physical twin through physics-based and physics-informed AI approaches, (2) mirroring the physical system into a digital twin with real-time synchronization, (3) intervening in the physical twin through predictive modeling, anomaly detection, and optimization strategies, and (4) achieving autonomous management through large language models, foundation models, and intelligent agents. We analyze the synergy between physics-based modeling and data-driven learning, highlighting the shift from traditional numerical solvers to physics-informed and foundation models for physical systems. Furthermore, we examine how generative AI technologies, including large language models and generative world models, transform digital twins into proactive and self-improving cognitive systems capable of reasoning, communication, and creative scenario generation. Through a cross-domain review spanning eleven application domains, including healthcare, aerospace, smart manufacturing, robotics, and smart cities, we identify common challenges related to scalability, explainability, and trustworthiness, and outline directions for responsible AI-driven digital twin systems.
Fonte: arXiv cs.AI
NLP/LLMs • Score 85
AI Agentiva para Tomada de Decisão de Risco de Crédito Autônoma, Explicável e em Tempo Real
arXiv:2601.00818v1 Tipo de Anúncio: novo
Resumo: A digitalização significativa dos serviços financeiros em um curto período de tempo levou a uma demanda urgente por sistemas de tomada de decisão de risco de crédito autônomos, transparentes e em tempo real. Os modelos tradicionais de machine learning são eficazes em reconhecimento de padrões, mas não possuem o raciocínio adaptativo, a consciência situacional e a autonomia necessárias nas operações financeiras modernas. Como proposta, este artigo apresenta uma estrutura de AI Agentiva, ou um sistema onde agentes de IA visualizam o mundo do crédito dinâmico independentemente de observadores humanos, que então tomam ações com base em seus caminhos de tomada de decisão articuláveis. A pesquisa introduz um sistema multiagente com aprendizado por reforço, raciocínio em linguagem natural, módulos de AI explicável e pipelines de absorção de dados em tempo real como meio de avaliar os perfis de risco dos tomadores de empréstimos com pouca intervenção humana. Os processos consistem em protocolo de colaboração de agentes, motores de pontuação de risco, camadas de interpretabilidade e ciclos de aprendizado com feedback contínuo. As descobertas indicam que a velocidade de decisão, transparência e capacidade de resposta são melhores do que os modelos tradicionais de pontuação de crédito. No entanto, ainda existem algumas limitações práticas, como riscos de desvio do modelo, inconsistências na interpretação de dados de alta dimensão e incertezas regulatórias, além de limitações de infraestrutura em ambientes com poucos recursos. O sistema sugerido tem um alto potencial para transformar a análise de crédito e futuros estudos devem ser direcionados a mobilizadores de conformidade regulatória dinâmica, novas colaborações entre agentes, robustez adversarial e implementação em larga escala em ecossistemas de crédito entre países.
Fonte: arXiv cs.AI
Vision • Score 96
IMBWatch -- uma abordagem de Rede Neural Gráfica Espacial-Temporal para detectar Negócios de Massagem Ilícitos
Os Negócios de Massagem Ilícitos (IMBs) são uma forma encoberta e persistente de exploração organizada que operam sob a fachada de serviços de bem-estar legítimos. A detecção de IMBs é difícil devido a anúncios digitais codificados e mudanças frequentes de pessoal e locais. Apresentamos o IMBWatch, um framework de rede neural gráfica espacial-temporal (ST-GNN) para a detecção em larga escala de IMBs, que combina operações de convolução gráfica com mecanismos de atenção temporal.
Fonte: arXiv cs.LG
RL • Score 95
Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trends
arXiv:2601.00536v1 Announce Type: new
Abstract: Multi-hop question answering (QA) requires systems to iteratively retrieve evidence and reason across multiple hops. While recent RAG and agentic methods report strong results, the underlying retrieval--reasoning \emph{process} is often left implicit, making procedural choices hard to compare across model families. This survey takes the execution procedure as the unit of analysis and introduces a four-axis framework covering (A) overall execution plan, (B) index structure, (C) next-step control (strategies and triggers), and (D) stop/continue criteria. Using this schema, we map representative multi-hop QA systems and synthesize reported ablations and tendencies on standard benchmarks (e.g., HotpotQA, 2WikiMultiHopQA, MuSiQue), highlighting recurring trade-offs among effectiveness, efficiency, and evidence faithfulness. We conclude with open challenges for retrieval--reasoning agents, including structure-aware planning, transferable control policies, and robust stopping under distribution shift.
Fonte: arXiv cs.CL
MLOps/Systems • Score 92
Noise-Aware Named Entity Recognition for Historical VET Documents
arXiv:2601.00488v1 Announce Type: new
Abstract: This paper addresses Named Entity Recognition (NER) in the domain of Vocational Education and Training (VET), focusing on historical, digitized documents that suffer from OCR-induced noise. We propose a robust NER approach leveraging Noise-Aware Training (NAT) with synthetically injected OCR errors, transfer learning, and multi-stage fine-tuning. Three complementary strategies, training on noisy, clean, and artificial data, are systematically compared. Our method is one of the first to recognize multiple entity types in VET documents. It is applied to German documents but transferable to arbitrary languages. Experimental results demonstrate that domain-specific and noise-aware fine-tuning substantially increases robustness and accuracy under noisy conditions. We provide publicly available code for reproducible noise-aware NER in domain-specific contexts.
Fonte: arXiv cs.CL
Vision • Score 93
Detecção Inteligente de Falhas no Sistema de Energia Elétrica de Nanosatélites
Este artigo apresenta um novo método de detecção de falhas no sistema de energia elétrica de nanosatélites sem um Subsystema de Controle de Determinação de Atitude (ADCS) em órbita LEO. O sistema é simulado sem falhas com base em uma rede neural, utilizando radiação solar e temperatura da superfície do painel solar como dados de entrada.
Fonte: arXiv cs.LG
Vision • Score 95
DepFlow: Disentangled Speech Generation to Mitigate Semantic Bias in Depression Detection
arXiv:2601.00303v1 Announce Type: new
Abstract: Speech is a scalable and non-invasive biomarker for early mental health screening. However, widely used depression datasets like DAIC-WOZ exhibit strong coupling between linguistic sentiment and diagnostic labels, encouraging models to learn semantic shortcuts. As a result, model robustness may be compromised in real-world scenarios, such as Camouflaged Depression, where individuals maintain socially positive or neutral language despite underlying depressive states. To mitigate this semantic bias, we propose DepFlow, a three-stage depression-conditioned text-to-speech framework. First, a Depression Acoustic Encoder learns speaker- and content-invariant depression embeddings through adversarial training, achieving effective disentanglement while preserving depression discriminability (ROC-AUC: 0.693). Second, a flow-matching TTS model with FiLM modulation injects these embeddings into synthesis, enabling control over depressive severity while preserving content and speaker identity. Third, a prototype-based severity mapping mechanism provides smooth and interpretable manipulation across the depression continuum. Using DepFlow, we construct a Camouflage Depression-oriented Augmentation (CDoA) dataset that pairs depressed acoustic patterns with positive/neutral content from a sentiment-stratified text bank, creating acoustic-semantic mismatches underrepresented in natural data. Evaluated across three depression detection architectures, CDoA improves macro-F1 by 9%, 12%, and 5%, respectively, consistently outperforming conventional augmentation strategies in depression Detection. Beyond enhancing robustness, DepFlow provides a controllable synthesis platform for conversational systems and simulation-based evaluation, where real clinical data remains limited by ethical and coverage constraints.
Fonte: arXiv cs.CL
NLP/LLMs • Score 96
Detecção de Descargas de Onda Espigada (SWD) usando 1-dimensional Residual UNet
A rotulagem manual de eventos em registros de eletroencefalografia (EEG) é um processo demorado, especialmente quando as gravações são contínuas por semanas a meses. Um método para rotular automaticamente eventos relevantes de EEG reduz a carga de trabalho manual. Neste estudo, comparamos o desempenho de 14 classificadores de machine learning em um conjunto de dados anotado manualmente, encontrando que um 1D UNet é o mais eficaz para rotular SWDs.
Fonte: arXiv cs.LG
RL • Score 93
Ideação Progressiva usando um Framework de IA Agente para Co-Criação Humano-IA
A geração de ideias verdadeiramente novas e diversificadas é crucial para o design de engenharia contemporâneo, mas continua sendo um desafio cognitivo significativo para designers novatos. Propomos o MIDAS (Meta-cognitive Ideation through Distributed Agentic AI System), um framework inovador que substitui o paradigma de IA única por uma 'equipe' distribuída de agentes de IA especializados, projetados para emular o fluxo de trabalho de ideação meta-cognitiva humana.
Fonte: arXiv cs.AI
Vision • Score 95
Simulação como Supervisão: Pré-treinamento Mecânico para Descoberta Científica
A modelagem científica enfrenta um trade-off entre a interpretabilidade da teoria mecanicista e o poder preditivo do machine learning. Apresentamos as Simulation-Grounded Neural Networks (SGNNs), um framework que incorpora conhecimento de domínio nos dados de treinamento, permitindo que o modelo aprenda padrões amplos de possibilidade física e seja mais robusto a erros de especificação do modelo.
Fonte: arXiv stat.ML
RL • Score 95
Integração de Multi-Armed Bandit, Aprendizado Ativo e Computação Distribuída para Otimização Escalável
Problemas modernos de otimização em domínios científicos e de engenharia frequentemente dependem de avaliações black-box caras. Propomos o ALMAB-DC, um framework modular e unificado para otimização black-box escalável que integra aprendizado ativo, multi-armed bandits e computação distribuída, com aceleração opcional por GPU. Resultados empíricos mostram que ALMAB-DC supera consistentemente otimizadores black-box de última geração.
Fonte: arXiv stat.ML
RL • Score 96
Métodos Semânticos Podem Aprimorar Táticas em Esportes Coletivos? Uma Metodologia para Futebol com Aplicações Mais Amplas
Este artigo explora como o raciocínio em espaço semântico, tradicionalmente utilizado em linguística computacional, pode ser estendido à tomada de decisão tática em esportes coletivos. A metodologia proposta modela configurações táticas como estruturas semânticas composicionais, representando cada jogador como um vetor multidimensional que integra atributos técnicos, físicos e psicológicos.
Fonte: arXiv cs.AI
Vision • Score 95
Robust Assembly Progress Estimation via Deep Metric Learning
arXiv:2601.00422v1 Announce Type: new
Abstract: In recent years, the advancement of AI technologies has accelerated the development of smart factories. In particular, the automatic monitoring of product assembly progress is crucial for improving operational efficiency, minimizing the cost of discarded parts, and maximizing factory productivity. However, in cases where assembly tasks are performed manually over multiple days, implementing smart factory systems remains a challenge. Previous work has proposed Anomaly Triplet-Net, which estimates assembly progress by applying deep metric learning to the visual features of products. Nevertheless, when visual changes between consecutive tasks are subtle, misclassification often occurs. To address this issue, this paper proposes a robust system for estimating assembly progress, even in cases of occlusion or minimal visual change, using a small-scale dataset. Our method leverages a Quadruplet Loss-based learning approach for anomaly images and introduces a custom data loader that strategically selects training samples to enhance estimation accuracy. We evaluated our approach using a image datasets: captured during desktop PC assembly. The proposed Anomaly Quadruplet-Net outperformed existing methods on the dataset. Specifically, it improved the estimation accuracy by 1.3% and reduced misclassification between adjacent tasks by 1.9% in the desktop PC dataset and demonstrating the effectiveness of the proposed method.
Fonte: arXiv cs.CV
NLP/LLMs • Score 95
From Transformers to LLMs: A Systematic Survey of Efficiency Considerations in NLP
arXiv:2406.16893v2 Announce Type: replace
Abstract: The emergence of Transformer-based Large Language Models (LLMs) has substantially augmented the capabilities of Natural Language Processing (NLP), thereby intensifying the demand for computational resources. Therefore, enhancing efficiency based on factors like computational requirements, energy consumption, carbon footprint and financial cost has become a vital area of research. This motivates us to conduct a systematic literature review on Transformer-based LLMs in NLP from the perspective of efficiency. In this survey of 312 articles published between the years 2011 and 2025, efficiency-improvement endeavors have been systematically discussed targeting various aspects such as data curation, model design, model downsizing, and dynamic inferencing. This has been augmented with efficiency considerations in model adaptation strategies like pre-training, fine-tuning, prompt-engineering and Retrieval-Augmented Generation (RAG). Furthermore, a statistical analysis of the articles has been performed followed by an in-depth evaluation of the efficiency and efficacy of more than 30 renowned NLP models has been conducted on 13 evaluation benchmarks. This paper offers valuable insights for researchers, professionals as well as scholars, and explores the trend of research toward sustainable practices in NLP.
Fonte: arXiv cs.CL
Vision • Score 95
A Cascaded Information Interaction Network for Precise Image Segmentation
arXiv:2601.00562v1 Announce Type: new
Abstract: Visual perception plays a pivotal role in enabling autonomous behavior, offering a cost-effective and efficient alternative to complex multi-sensor systems. However, robust segmentation remains a challenge in complex scenarios. To address this, this paper proposes a cascaded convolutional neural network integrated with a novel Global Information Guidance Module. This module is designed to effectively fuse low-level texture details with high-level semantic features across multiple layers, thereby overcoming the inherent limitations of single-scale feature extraction. This architectural innovation significantly enhances segmentation accuracy, particularly in visually cluttered or blurred environments where traditional methods often fail. Experimental evaluations on benchmark image segmentation datasets demonstrate that the proposed framework achieves superior precision, outperforming existing state-of-the-art methods. The results highlight the effectiveness of the approach and its promising potential for deployment in practical robotic applications.
Fonte: arXiv cs.CV
Vision • Score 95
A Comprehensive Dataset for Human vs. AI Generated Image Detection
arXiv:2601.00553v1 Announce Type: new
Abstract: Multimodal generative AI systems like Stable Diffusion, DALL-E, and MidJourney have fundamentally changed how synthetic images are created. These tools drive innovation but also enable the spread of misleading content, false information, and manipulated media. As generated images become harder to distinguish from photographs, detecting them has become an urgent priority. To combat this challenge, We release MS COCOAI, a novel dataset for AI generated image detection consisting of 96000 real and synthetic datapoints, built using the MS COCO dataset. To generate synthetic images, we use five generators: Stable Diffusion 3, Stable Diffusion 2.1, SDXL, DALL-E 3, and MidJourney v6. Based on the dataset, we propose two tasks: (1) classifying images as real or generated, and (2) identifying which model produced a given synthetic image. The dataset is available at https://huggingface.co/datasets/Rajarshi-Roy-research/Defactify_Image_Dataset.
Fonte: arXiv cs.CV
NLP/LLMs • Score 95
Pat-DEVAL: Chain-of-Legal-Thought Evaluation for Patent Description
arXiv:2601.00166v1 Announce Type: new
Abstract: Patent descriptions must deliver comprehensive technical disclosure while meeting strict legal standards such as enablement and written description requirements. Although large language models have enabled end-to-end automated patent drafting, existing evaluation approaches fail to assess long-form structural coherence and statutory compliance specific to descriptions. We propose Pat-DEVAL, the first multi-dimensional evaluation framework dedicated to patent description bodies. Leveraging the LLM-as-a-judge paradigm, Pat-DEVAL introduces Chain-of-Legal-Thought (CoLT), a legally-constrained reasoning mechanism that enforces sequential patent-law-specific analysis. Experiments validated by patent expert on our Pap2Pat-EvalGold dataset demonstrate that Pat-DEVAL achieves a Pearson correlation of 0.69, significantly outperforming baseline metrics and existing LLM evaluators. Notably, the framework exhibits a superior correlation of 0.73 in Legal-Professional Compliance, proving that the explicit injection of statutory constraints is essential for capturing nuanced legal validity. By establishing a new standard for ensuring both technical soundness and legal compliance, Pat-DEVAL provides a robust methodological foundation for the practical deployment of automated patent drafting systems.
Fonte: arXiv cs.CL
NLP/LLMs • Score 95
Correção Residual Segura Inspirada em Causalidade para Séries Temporais Multivariadas
Embora os preditores multivariados modernos, como Transformers e GNNs, apresentem forte desempenho em benchmarks, eles frequentemente sofrem de erros sistemáticos em variáveis ou horizontes específicos e, criticamente, carecem de garantias contra degradação de desempenho na implementação. Para abordar essa lacuna de segurança, propomos o CRC (Correção Residual Segura Inspirada em Causalidade), um framework projetado para garantir não degradação.
Fonte: arXiv stat.ML
NLP/LLMs • Score 95
Beyond IVR: Benchmarking Customer Support LLM Agents for Business-Adherence
arXiv:2601.00596v1 Announce Type: new
Abstract: Traditional customer support systems, such as Interactive Voice Response (IVR), rely on rigid scripts and lack the flexibility required for handling complex, policy-driven tasks. While large language model (LLM) agents offer a promising alternative, evaluating their ability to act in accordance with business rules and real-world support workflows remains an open challenge. Existing benchmarks primarily focus on tool usage or task completion, overlooking an agent's capacity to adhere to multi-step policies, navigate task dependencies, and remain robust to unpredictable user or environment behavior. In this work, we introduce JourneyBench, a benchmark designed to assess policy-aware agents in customer support. JourneyBench leverages graph representations to generate diverse, realistic support scenarios and proposes the User Journey Coverage Score, a novel metric to measure policy adherence. We evaluate multiple state-of-the-art LLMs using two agent designs: a Static-Prompt Agent (SPA) and a Dynamic-Prompt Agent (DPA) that explicitly models policy control. Across 703 conversations in three domains, we show that DPA significantly boosts policy adherence, even allowing smaller models like GPT-4o-mini to outperform more capable ones like GPT-4o. Our findings demonstrate the importance of structured orchestration and establish JourneyBench as a critical resource to advance AI-driven customer support beyond IVR-era limitations.
Fonte: arXiv cs.CL
NLP/LLMs • Score 96
Framework Auto-reparador Agente Bio-inspirado para Sistemas de Computação Distribuída Resilientes
Este artigo apresenta o ReCiSt, um framework auto-reparador bio-inspirado projetado para alcançar resiliência em Sistemas de Computação Distribuída (DCCS). O ReCiSt reconstrói fases biológicas em camadas computacionais que realizam isolamento autônomo de falhas, diagnóstico causal, recuperação adaptativa e consolidação de conhecimento a partir de agentes impulsionados por Language Model (LM).
Fonte: arXiv cs.AI
Vision • Score 95
TeleWorld: Towards Dynamic Multimodal Synthesis with a 4D World Model
arXiv:2601.00051v1 Announce Type: new
Abstract: World models aim to endow AI systems with the ability to represent, generate, and interact with dynamic environments in a coherent and temporally consistent manner. While recent video generation models have demonstrated impressive visual quality, they remain limited in real-time interaction, long-horizon consistency, and persistent memory of dynamic scenes, hindering their evolution into practical world models. In this report, we present TeleWorld, a real-time multimodal 4D world modeling framework that unifies video generation, dynamic scene reconstruction, and long-term world memory within a closed-loop system. TeleWorld introduces a novel generation-reconstruction-guidance paradigm, where generated video streams are continuously reconstructed into a dynamic 4D spatio-temporal representation, which in turn guides subsequent generation to maintain spatial, temporal, and physical consistency. To support long-horizon generation with low latency, we employ an autoregressive diffusion-based video model enhanced with Macro-from-Micro Planning (MMPL)--a hierarchical planning method that reduces error accumulation from frame-level to segment-level-alongside efficient Distribution Matching Distillation (DMD), enabling real-time synthesis under practical computational budgets. Our approach achieves seamless integration of dynamic object modeling and static scene representation within a unified 4D framework, advancing world models toward practical, interactive, and computationally accessible systems. Extensive experiments demonstrate that TeleWorld achieves strong performance in both static and dynamic world understanding, long-term consistency, and real-time generation efficiency, positioning it as a practical step toward interactive, memory-enabled world models for multimodal generation and embodied intelligence.
Fonte: arXiv cs.CV
NLP/LLMs • Score 95
Intelligent Traffic Surveillance for Real-Time Vehicle Detection, License Plate Recognition, and Speed Estimation
arXiv:2601.00344v1 Announce Type: new
Abstract: Speeding is a major contributor to road fatalities, particularly in developing countries such as Uganda, where road safety infrastructure is limited. This study proposes a real-time intelligent traffic surveillance system tailored to such regions, using computer vision techniques to address vehicle detection, license plate recognition, and speed estimation. The study collected a rich dataset using a speed gun, a Canon Camera, and a mobile phone to train the models. License plate detection using YOLOv8 achieved a mean average precision (mAP) of 97.9%. For character recognition of the detected license plate, the CNN model got a character error rate (CER) of 3.85%, while the transformer model significantly reduced the CER to 1.79%. Speed estimation used source and target regions of interest, yielding a good performance of 10 km/h margin of error. Additionally, a database was established to correlate user information with vehicle detection data, enabling automated ticket issuance via SMS via Africa's Talking API. This system addresses critical traffic management needs in resource-constrained environments and shows potential to reduce road accidents through automated traffic enforcement in developing countries where such interventions are urgently needed.
Fonte: arXiv cs.CV
NLP/LLMs • Score 96
FaithSCAN: Detecção de Alucinações em Uma Única Passagem Baseada em Modelos para Respostas Visuais de Perguntas Fiéis
As alucinações de fidelidade em VQA ocorrem quando modelos de visão-linguagem produzem respostas fluentes, mas visualmente não fundamentadas, comprometendo sua confiabilidade em aplicações críticas de segurança. Propomos o FaithSCAN, uma rede leve que detecta alucinações explorando sinais internos ricos dos VLMs, superando limitações de métodos existentes em eficiência e desempenho de detecção.
Fonte: arXiv cs.AI
RL • Score 95
Mitigando o viés otimista na estimativa e otimização de risco entrópico
A medida de risco entrópico é amplamente utilizada em decisões críticas em economia, ciência da gestão, finanças e sistemas de controle críticos, pois captura riscos extremos associados a perdas incertas. Este trabalho apresenta um procedimento de bootstrap paramétrico que corrige o viés do estimador empírico de risco entrópico, melhorando a precisão na tomada de decisões.
Fonte: arXiv stat.ML
RL • Score 93
Proteção de Erro Desigual Aprendida por Reforço para Embeddings Semânticos Quantizados
Este artigo aborda o desafio premente de preservar o significado semântico em sistemas de comunicação com largura de banda limitada. Introduzimos um novo framework de aprendizado por reforço que alcança proteção desigual por dimensão via codificação de repetição adaptativa, utilizando uma métrica de distorção semântica composta que equilibra a similaridade global de embeddings com a preservação em nível de entidade.
Fonte: arXiv cs.LG
NLP/LLMs • Score 95
Application Research of a Deep Learning Model Integrating CycleGAN and YOLO in PCB Infrared Defect Detection
arXiv:2601.00237v1 Announce Type: new
Abstract: This paper addresses the critical bottleneck of infrared (IR) data scarcity in Printed Circuit Board (PCB) defect detection by proposing a cross-modal data augmentation framework integrating CycleGAN and YOLOv8. Unlike conventional methods relying on paired supervision, we leverage CycleGAN to perform unpaired image-to-image translation, mapping abundant visible-light PCB images into the infrared domain. This generative process synthesizes high-fidelity pseudo-IR samples that preserve the structural semantics of defects while accurately simulating thermal distribution patterns. Subsequently, we construct a heterogeneous training strategy that fuses generated pseudo-IR data with limited real IR samples to train a lightweight YOLOv8 detector. Experimental results demonstrate that this method effectively enhances feature learning under low-data conditions. The augmented detector significantly outperforms models trained on limited real data alone and approaches the performance benchmarks of fully supervised training, proving the efficacy of pseudo-IR synthesis as a robust augmentation strategy for industrial inspection.
Fonte: arXiv cs.CV
RL • Score 96
Colocação Ótima de Táxis Consciente do Tráfego Usando Aprendizado por Reforço Baseado em Redes Neurais Gráficas
No contexto do transporte em cidades inteligentes, o emparelhamento eficiente da oferta de táxis com a demanda de passageiros requer a integração em tempo real de dados da rede de tráfego urbano e padrões de mobilidade. Este artigo apresenta um framework de aprendizado por reforço (RL) baseado em grafos para a colocação ótima de táxis em ambientes metropolitanos.
Fonte: arXiv cs.LG
NLP/LLMs • Score 95
Limite de Largura Infinita de uma Única Camada de Atenção: Análise via Programas Tensor
No presente artigo, identificamos rigorosamente a distribuição do limite de largura infinita de variáveis dentro de uma única camada de atenção, utilizando o framework Tensor Programs. Derivamos a forma exata dessa lei limite, demonstrando que ela se desvia fundamentalmente da Gaussianidade. Nossos experimentos numéricos validam as previsões teóricas, confirmando a eficácia da teoria em largura finita e a descrição precisa de atenções com cabeçotes finitos.
Fonte: arXiv stat.ML
NLP/LLMs • Score 95
Focal-RegionFace: Generating Fine-Grained Multi-attribute Descriptions for Arbitrarily Selected Face Focal Regions
arXiv:2601.00156v1 Announce Type: new
Abstract: In this paper, we introduce an underexplored problem in facial analysis: generating and recognizing multi-attribute natural language descriptions, containing facial action units (AUs), emotional states, and age estimation, for arbitrarily selected face regions (termed FaceFocalDesc). We argue that the system's ability to focus on individual facial areas leads to better understanding and control. To achieve this capability, we construct a new multi-attribute description dataset for arbitrarily selected face regions, providing rich region-level annotations and natural language descriptions. Further, we propose a fine-tuned vision-language model based on Qwen2.5-VL, called Focal-RegionFace for facial state analysis, which incrementally refines its focus on localized facial features through multiple progressively fine-tuning stages, resulting in interpretable age estimation, FAU and emotion detection. Experimental results show that Focal-RegionFace achieves the best performance on the new benchmark in terms of traditional and widely used metrics, as well as new proposed metrics. This fully verifies its effectiveness and versatility in fine-grained multi-attribute face region-focal analysis scenarios.
Fonte: arXiv cs.CV
NLP/LLMs • Score 95
Rule-Based Approaches to Atomic Sentence Extraction
arXiv:2601.00506v1 Announce Type: new
Abstract: Natural language often combines multiple ideas into complex sentences. Atomic sentence extraction, the task of decomposing complex sentences into simpler sentences that each express a single idea, improves performance in information retrieval, question answering, and automated reasoning systems. Previous work has formalized the "split-and-rephrase" task and established evaluation metrics, and machine learning approaches using large language models have improved extraction accuracy. However, these methods lack interpretability and provide limited insight into which linguistic structures cause extraction failures. Although some studies have explored dependency-based extraction of subject-verb-object triples and clauses, no principled analysis has examined which specific clause structures and dependencies lead to extraction difficulties. This study addresses this gap by analyzing how complex sentence structures, including relative clauses, adverbial clauses, coordination patterns, and passive constructions, affect the performance of rule-based atomic sentence extraction. Using the WikiSplit dataset, we implemented dependency-based extraction rules in spaCy, generated 100 gold=standard atomic sentence sets, and evaluated performance using ROUGE and BERTScore. The system achieved ROUGE-1 F1 = 0.6714, ROUGE-2 F1 = 0.478, ROUGE-L F1 = 0.650, and BERTScore F1 = 0.5898, indicating moderate-to-high lexical, structural, and semantic alignment. Challenging structures included relative clauses, appositions, coordinated predicates, adverbial clauses, and passive constructions. Overall, rule-based extraction is reasonably accurate but sensitive to syntactic complexity.
Fonte: arXiv cs.CL
NLP/LLMs • Score 95
Spatial4D-Bench: A Versatile 4D Spatial Intelligence Benchmark
arXiv:2601.00092v1 Announce Type: new
Abstract: 4D spatial intelligence involves perceiving and processing how objects move or change over time. Humans naturally possess 4D spatial intelligence, supporting a broad spectrum of spatial reasoning abilities. To what extent can Multimodal Large Language Models (MLLMs) achieve human-level 4D spatial intelligence? In this work, we present Spatial4D-Bench, a versatile 4D spatial intelligence benchmark designed to comprehensively assess the 4D spatial reasoning abilities of MLLMs. Unlike existing spatial intelligence benchmarks that are often small-scale or limited in diversity, Spatial4D-Bench provides a large-scale, multi-task evaluation benchmark consisting of ~40,000 question-answer pairs covering 18 well-defined tasks. We systematically organize these tasks into six cognitive categories: object understanding, scene understanding, spatial relationship understanding, spatiotemporal relationship understanding, spatial reasoning and spatiotemporal reasoning. Spatial4D-Bench thereby offers a structured and comprehensive benchmark for evaluating the spatial cognition abilities of MLLMs, covering a broad spectrum of tasks that parallel the versatility of human spatial intelligence. We benchmark various state-of-the-art open-source and proprietary MLLMs on Spatial4D-Bench and reveal their substantial limitations in a wide variety of 4D spatial reasoning aspects, such as route plan, action recognition, and physical plausibility reasoning. We hope that the findings provided in this work offer valuable insights to the community and that our benchmark can facilitate the development of more capable MLLMs toward human-level 4D spatial intelligence. More resources can be found on our project page.
Fonte: arXiv cs.CV
Vision • Score 95
Context-Aware Pesticide Recommendation via Few-Shot Pest Recognition for Precision Agriculture
arXiv:2601.00243v1 Announce Type: new
Abstract: Effective pest management is crucial for enhancing agricultural productivity, especially for crops such as sugarcane and wheat that are highly vulnerable to pest infestations. Traditional pest management methods depend heavily on manual field inspections and the use of chemical pesticides. These approaches are often costly, time-consuming, labor-intensive, and can have a negative impact on the environment. To overcome these challenges, this study presents a lightweight framework for pest detection and pesticide recommendation, designed for low-resource devices such as smartphones and drones, making it suitable for use by small and marginal farmers.
The proposed framework includes two main components. The first is a Pest Detection Module that uses a compact, lightweight convolutional neural network (CNN) combined with prototypical meta-learning to accurately identify pests even when only a few training samples are available. The second is a Pesticide Recommendation Module that incorporates environmental factors like crop type and growth stage to suggest safe and eco-friendly pesticide recommendations. To train and evaluate our framework, a comprehensive pest image dataset was developed by combining multiple publicly available datasets. The final dataset contains samples with different viewing angles, pest sizes, and background conditions to ensure strong generalization.
Experimental results show that the proposed lightweight CNN achieves high accuracy, comparable to state-of-the-art models, while significantly reducing computational complexity. The Decision Support System additionally improves pest management by reducing dependence on traditional chemical pesticides and encouraging sustainable practices, demonstrating its potential for real-time applications in precision agriculture.
Fonte: arXiv cs.CV
NLP/LLMs • Score 94
Controles de Abstenção Explícita para Confiabilidade Previsível em Respostas a Perguntas em Vídeo
A implementação de modelos de visão-linguagem (VLMs) em situações críticas exige previsões seletivas, onde os sistemas se abstêm quando incertos, evitando erros custosos. Investigamos se a abstenção baseada em confiança oferece controle confiável sobre as taxas de erro em respostas a perguntas em vídeo e se esse controle se mantém robusto sob mudança de distribuição.
Fonte: arXiv cs.AI
NLP/LLMs • Score 96
Pergunte, Esclareça, Otimize: Colaboração Humano-LLM para um Controle de Estoque Mais Inteligente
arXiv:2601.00121v1 Tipo de Anúncio: novo
Resumo: A gestão de estoque continua sendo um desafio para muitas pequenas e médias empresas que carecem da expertise para implementar métodos avançados de otimização. Este artigo investiga se os Large Language Models (LLMs) podem ajudar a preencher essa lacuna. Mostramos que empregar LLMs como solucionadores diretos, de ponta a ponta, acarreta um significativo "custo de alucinação": uma diferença de desempenho decorrente da incapacidade do modelo de realizar raciocínio estocástico fundamentado. Para abordar isso, propomos uma estrutura híbrida de agente que desacopla estritamente o raciocínio semântico do cálculo matemático. Nesta arquitetura, o LLM funciona como uma interface inteligente, extraindo parâmetros da linguagem natural e interpretando resultados enquanto chama automaticamente algoritmos rigorosos para construir o motor de otimização.
Para avaliar este sistema interativo em relação à ambiguidade e inconsistência do diálogo gerencial do mundo real, introduzimos o Human Imitator, um "gêmeo digital" ajustado de um gerente racionalmente limitado que permite testes de estresse escaláveis e reproduzíveis. Nossa análise empírica revela que a estrutura híbrida de agente reduz os custos totais de estoque em 32,1% em relação a uma linha de base interativa usando o GPT-4o como solucionador de ponta a ponta. Além disso, descobrimos que fornecer informações perfeitas de verdade fundamental por si só é insuficiente para melhorar o desempenho do GPT-4o, confirmando que o gargalo é fundamentalmente computacional e não informacional. Nossos resultados posicionam os LLMs não como substitutos da pesquisa operacional, mas como interfaces de linguagem natural que tornam políticas rigorosas baseadas em solucionadores acessíveis a não especialistas.
Fonte: arXiv cs.AI
NLP/LLMs • Score 95
RoLID-11K: A Dashcam Dataset for Small-Object Roadside Litter Detection
arXiv:2601.00398v1 Announce Type: new
Abstract: Roadside litter poses environmental, safety and economic challenges, yet current monitoring relies on labour-intensive surveys and public reporting, providing limited spatial coverage. Existing vision datasets for litter detection focus on street-level still images, aerial scenes or aquatic environments, and do not reflect the unique characteristics of dashcam footage, where litter appears extremely small, sparse and embedded in cluttered road-verge backgrounds. We introduce RoLID-11K, the first large-scale dataset for roadside litter detection from dashcams, comprising over 11k annotated images spanning diverse UK driving conditions and exhibiting pronounced long-tail and small-object distributions. We benchmark a broad spectrum of modern detectors, from accuracy-oriented transformer architectures to real-time YOLO models, and analyse their strengths and limitations on this challenging task. Our results show that while CO-DETR and related transformers achieve the best localisation accuracy, real-time models remain constrained by coarse feature hierarchies. RoLID-11K establishes a challenging benchmark for extreme small-object detection in dynamic driving scenes and aims to support the development of scalable, low-cost systems for roadside-litter monitoring. The dataset is available at https://github.com/xq141839/RoLID-11K.
Fonte: arXiv cs.CV
NLP/LLMs • Score 95
Geometry of Reason: Spectral Signatures of Valid Mathematical Reasoning
arXiv:2601.00791v1 Announce Type: cross
Abstract: We present a training-free method for detecting valid mathematical reasoning in large language models through spectral analysis of attention patterns. By treating attention matrices as adjacency matrices of dynamic graphs over tokens, we extract four interpretable spectral diagnostics, the Fiedler value (algebraic connectivity), high-frequency energy ratio (HFER), graph signal smoothness, and spectral entropy, that exhibit statistically significant differences between valid and invalid mathematical proofs. Experiments across seven transformer models from four independent architectural families (Meta Llama, Alibaba Qwen, Microsoft Phi, and Mistral AI) demonstrate that this spectral signature produces effect sizes up to Cohen's $d = 3.30$ ($p < 10^{-116}$), enabling 85.0--95.6\% classification accuracy under rigorous evaluation, with calibrated thresholds reaching 93--95\% on the full dataset. The method requires no training data, fine-tuning, or learned classifiers: a single threshold on a spectral metric suffices for high accuracy. Through systematic label correction, we discover that the spectral method detects logical coherence rather than compiler acceptance, identifying mathematically valid proofs that formal verifiers reject due to technical failures. We further identify an architectural dependency: Mistral-7B's Sliding Window Attention shifts the discriminative signal from HFER to late-layer Smoothness ($d = 2.09$, $p_{\text{MW}} = 1.16 \times 10^{-48}$), revealing that attention mechanism design affects which spectral features capture reasoning validity. These findings establish spectral graph analysis as a principled framework for reasoning verification with immediate applications to hallucination detection and AI safety monitoring.
Fonte: arXiv cs.CL
RL • Score 96
IA Generativa Nativa em Nuvem para Síntese Automatizada de Planogramas: Uma Abordagem de Modelo de Difusão para Otimização de Varejo em Múltiplas Lojas
A criação de planogramas é um desafio significativo para o varejo, exigindo em média 30 horas por layout complexo. Este artigo apresenta uma arquitetura nativa em nuvem utilizando modelos de difusão para gerar automaticamente planogramas específicos para cada loja, aprendendo com arranjos de prateleiras bem-sucedidos em várias localizações de varejo.
Fonte: arXiv cs.LG
RL • Score 95
TeleDoCTR: Domain-Specific and Contextual Troubleshooting for Telecommunications
arXiv:2601.00691v1 Announce Type: cross
Abstract: Ticket troubleshooting refers to the process of analyzing and resolving problems that are reported through a ticketing system. In large organizations offering a wide range of services, this task is highly complex due to the diversity of submitted tickets and the need for specialized domain knowledge. In particular, troubleshooting in telecommunications (telecom) is a very time-consuming task as it requires experts to interpret ticket content, consult documentation, and search historical records to identify appropriate resolutions. This human-intensive approach not only delays issue resolution but also hinders overall operational efficiency. To enhance the effectiveness and efficiency of ticket troubleshooting in telecom, we propose TeleDoCTR, a novel telecom-related, domain-specific, and contextual troubleshooting system tailored for end-to-end ticket resolution in telecom. TeleDoCTR integrates both domain-specific ranking and generative models to automate key steps of the troubleshooting workflow which are: routing tickets to the appropriate expert team responsible for resolving the ticket (classification task), retrieving contextually and semantically similar historical tickets (retrieval task), and generating a detailed fault analysis report outlining the issue, root cause, and potential solutions (generation task). We evaluate TeleDoCTR on a real-world dataset from a telecom infrastructure and demonstrate that it achieves superior performance over existing state-of-the-art methods, significantly enhancing the accuracy and efficiency of the troubleshooting process.
Fonte: arXiv cs.CL
RL • Score 96
Rumo a uma Teoria Física da Inteligência
Apresentamos uma teoria física da inteligência fundamentada no processamento irreversível de informações em sistemas sujeitos a leis de conservação. Um sistema inteligente é modelado como um processo acoplado agente-ambiente, cuja evolução transforma informações em trabalho direcionado a objetivos. Introduzimos o framework Conservation-Congruent Encoding (CCE) para conectar informações ao estado físico.
Fonte: arXiv cs.AI
NLP/LLMs • Score 95
Comparative Efficiency Analysis of Lightweight Transformer Models: A Multi-Domain Empirical Benchmark for Enterprise NLP Deployment
arXiv:2601.00444v1 Announce Type: new
Abstract: In the rapidly evolving landscape of enterprise natural language processing (NLP), the demand for efficient, lightweight models capable of handling multi-domain text automation tasks has intensified. This study conducts a comparative analysis of three prominent lightweight Transformer models - DistilBERT, MiniLM, and ALBERT - across three distinct domains: customer sentiment classification, news topic classification, and toxicity and hate speech detection. Utilizing datasets from IMDB, AG News, and the Measuring Hate Speech corpus, we evaluated performance using accuracy-based metrics including accuracy, precision, recall, and F1-score, as well as efficiency metrics such as model size, inference time, throughput, and memory usage. Key findings reveal that no single model dominates all performance dimensions. ALBERT achieves the highest task-specific accuracy in multiple domains, MiniLM excels in inference speed and throughput, and DistilBERT demonstrates the most consistent accuracy across tasks while maintaining competitive efficiency. All results reflect controlled fine-tuning under fixed enterprise-oriented constraints rather than exhaustive hyperparameter optimization. These results highlight trade-offs between accuracy and efficiency, recommending MiniLM for latency-sensitive enterprise applications, DistilBERT for balanced performance, and ALBERT for resource-constrained environments.
Fonte: arXiv cs.CL
NLP/LLMs • Score 95
Knowledge Distillation for Temporal Knowledge Graph Reasoning with Large Language Models
arXiv:2601.00202v1 Announce Type: new
Abstract: Reasoning over temporal knowledge graphs (TKGs) is fundamental to improving the efficiency and reliability of intelligent decision-making systems and has become a key technological foundation for future artificial intelligence applications. Despite recent progress, existing TKG reasoning models typically rely on large parameter sizes and intensive computation, leading to high hardware costs and energy consumption. These constraints hinder their deployment on resource-constrained, low-power, and distributed platforms that require real-time inference. Moreover, most existing model compression and distillation techniques are designed for static knowledge graphs and fail to adequately capture the temporal dependencies inherent in TKGs, often resulting in degraded reasoning performance. To address these challenges, we propose a distillation framework specifically tailored for temporal knowledge graph reasoning. Our approach leverages large language models as teacher models to guide the distillation process, enabling effective transfer of both structural and temporal reasoning capabilities to lightweight student models. By integrating large-scale public knowledge with task-specific temporal information, the proposed framework enhances the student model's ability to model temporal dynamics while maintaining a compact and efficient architecture. Extensive experiments on multiple publicly available benchmark datasets demonstrate that our method consistently outperforms strong baselines, achieving a favorable trade-off between reasoning accuracy, computational efficiency, and practical deployability.
Fonte: arXiv cs.CL
NLP/LLMs • Score 96
A Coleira Agente: Extraindo Mapas Cognitivos Fuzzy de Feedback Causal com LLMs
Desenvolvemos um agente de modelo de linguagem grande (LLM) que extrai mapas cognitivos fuzzy de feedback causal (FCMs) a partir de texto bruto. O processo de aprendizado ou extração causal é agente tanto pela semi-autonomia do LLM quanto pela dinâmica do sistema FCM, que orienta os agentes LLM a buscar e processar texto causal.
Fonte: arXiv cs.AI
Vision • Score 96
Detecção Adaptativa de Coordenação Causal para Mídias Sociais: Um Framework Guiado por Memória com Aprendizado Semi-Supervisionado
Detectar comportamentos inautênticos coordenados em mídias sociais é um desafio crítico. Propomos o framework Adaptive Causal Coordination Detection (ACCD), que utiliza uma arquitetura progressiva em três estágios para aprender e reter configurações de detecção otimizadas. O ACCD melhora a identificação de relações causais e reduz a necessidade de rotulagem manual, alcançando um F1-score de 87,3% em detecção de ataques coordenados.
Fonte: arXiv cs.AI
NLP/LLMs • Score 96
Os Chatbots LLMs Falam Demais? O Benchmark YapBench
Modelos de Linguagem de Grande Escala (LLMs) como ChatGPT, Claude e Gemini atuam cada vez mais como copilotos de propósito geral, mas frequentemente respondem com excessiva extensão em solicitações simples, aumentando a carga cognitiva e inflacionando o custo de inferência baseado em tokens. Apresentamos o YapBench, um benchmark leve para quantificar a sobregeração visível ao usuário em prompts de brevidade ideal.
Fonte: arXiv cs.LG
Vision • Score 96
Do Barro ao Código: Raciocínio Tipológico e Material nas Interpretações de IA das Torres de Pombos Iranianas
Este estudo investiga como sistemas de IA generativa interpretam a inteligência arquitetônica embutida na forma vernacular. Usando a torre de pombos iraniana como estudo de caso, a pesquisa testa três modelos de difusão: Midjourney v6, DALL-E 3 e DreamStudio baseado em Stable Diffusion XL (SDXL), em três estágios de prompt: referencial, adaptativo e especulativo.
Fonte: arXiv cs.AI
RL • Score 92
Aprendizado ativo para modelos reduzidos baseados em dados de sistemas diferenciais paramétricos com inferência bayesiana de operadores
Este trabalho desenvolve um framework de aprendizado ativo para enriquecer de forma inteligente modelos reduzidos de ordem (ROMs) de sistemas dinâmicos paramétricos, que podem servir como base para ativos virtuais em um digital twin. Os ROMs baseados em dados são modelos de machine learning científicos explicáveis e computacionalmente eficientes que visam preservar a física subjacente de simulações dinâmicas complexas.
Fonte: arXiv stat.ML
NLP/LLMs • Score 96
JP-TL-Bench: Avaliação Ancorada de LLM em Par para Tradução Bidirecional Japonês-Inglês
Apresentamos o JP-TL-Bench, um benchmark leve e aberto projetado para guiar o desenvolvimento iterativo de sistemas de tradução Japonês-Inglês. O desafio muitas vezes é 'qual dessas duas boas traduções é melhor?' em vez de 'esta tradução é aceitável?'. Essa distinção é crucial para o Japonês-Inglês, onde escolhas sutis em polidez, implicatura, elipse e registro afetam fortemente a naturalidade percebida.
Fonte: arXiv cs.AI
NLP/LLMs • Score 96
Trajectory Guard -- Um Modelo Leve e Consciente de Sequência para Detecção de Anomalias em Tempo Real em AI Agente
Agentes autônomos de LLM geram planos de ação de múltiplos passos que podem falhar devido a desalinhamento contextual ou incoerência estrutural. Métodos existentes de detecção de anomalias não são adequados para esse desafio. Apresentamos o Trajectory Guard, um Autoencoder Recorrente Siamês que aprende alinhamento de tarefa e trajetória, permitindo a detecção unificada de planos incorretos e estruturas de planos malformadas.
Fonte: arXiv cs.LG
NLP/LLMs • Score 96
Rumo a Sistemas de IA Potencializados por Fotônica em Grande Escala: Da Automação de Design Físico à Coexploração de Sistema e Algoritmo
Neste trabalho, identificamos três considerações essenciais para a realização de sistemas práticos de IA fotônica em escala: (1) suporte a operações tensorais dinâmicas para modelos modernos; (2) gerenciamento sistemático de sobrecargas de conversão, controle e movimentação de dados; e (3) robustez sob não idealidades de hardware. Desenvolvemos uma ferramenta de suporte ao design de IA fotônica desde a exploração inicial até a realização física.
Fonte: arXiv cs.AI
NLP/LLMs • Score 96
O Cavalo de Troia no Vocabulário: Sabotagem Sutil da Composição de LLM
O ecossistema de LLM de pesos abertos é cada vez mais definido por técnicas de composição de modelos que remixam capacidades de diversas fontes. Um pré-requisito crítico para aplicar esses métodos é o transplante de tokenizers, que alinha vocabulários incompatíveis a um espaço de embedding compartilhado. Demonstramos que esse passo de interoperabilidade introduz uma vulnerabilidade na cadeia de suprimentos.
Fonte: arXiv cs.LG
NLP/LLMs • Score 95
StockBot 2.0: Vanilla LSTMs Outperform Transformer-based Forecasting for Stock Prices
arXiv:2601.00197v1 Announce Type: cross
Abstract: Accurate forecasting of financial markets remains a long-standing challenge due to complex temporal and often latent dependencies, non-linear dynamics, and high volatility. Building on our earlier recurrent neural network framework, we present an enhanced StockBot architecture that systematically evaluates modern attention-based, convolutional, and recurrent time-series forecasting models within a unified experimental setting. While attention-based and transformer-inspired models offer increased modeling flexibility, extensive empirical evaluation reveals that a carefully constructed vanilla LSTM consistently achieves superior predictive accuracy and more stable buy/sell decision-making when trained under a common set of default hyperparameters. These results highlight the robustness and data efficiency of recurrent sequence models for financial time-series forecasting, particularly in the absence of extensive hyperparameter tuning or the availability of sufficient data when discretized to single-day intervals. Additionally, these results underscore the importance of architectural inductive bias in data-limited market prediction tasks.
Fonte: arXiv cs.CL
NLP/LLMs • Score 96
FlashInfer-Bench: Construindo o Ciclo Virtuoso para Sistemas LLM Impulsionados por IA
Avanços recentes mostram que modelos de linguagem de grande escala (LLMs) podem atuar como agentes autônomos capazes de gerar kernels de GPU, mas integrar esses kernels gerados por IA em sistemas de inferência do mundo real continua sendo um desafio. O FlashInfer-Bench aborda essa lacuna ao estabelecer um framework padronizado e de ciclo fechado que conecta geração de kernels, benchmarking e implantação.
Fonte: arXiv cs.AI
Vision • Score 95
Compressed Map Priors for 3D Perception
arXiv:2601.00139v1 Announce Type: new
Abstract: Human drivers rarely travel where no person has gone before. After all, thousands of drivers use busy city roads every day, and only one can claim to be the first. The same holds for autonomous computer vision systems. The vast majority of the deployment area of an autonomous vision system will have been visited before. Yet, most autonomous vehicle vision systems act as if they are encountering each location for the first time. In this work, we present Compressed Map Priors (CMP), a simple but effective framework to learn spatial priors from historic traversals. The map priors use a binarized hashmap that requires only $32\text{KB}/\text{km}^2$, a $20\times$ reduction compared to the dense storage. Compressed Map Priors easily integrate into leading 3D perception systems at little to no extra computational costs, and lead to a significant and consistent improvement in 3D object detection on the nuScenes dataset across several architectures.
Fonte: arXiv cs.CV
NLP/LLMs • Score 95
Adapting Natural Language Processing Models Across Jurisdictions: A pilot Study in Canadian Cancer Registries
arXiv:2601.00787v1 Announce Type: new
Abstract: Population-based cancer registries depend on pathology reports as their primary diagnostic source, yet manual abstraction is resource-intensive and contributes to delays in cancer data. While transformer-based NLP systems have improved registry workflows, their ability to generalize across jurisdictions with differing reporting conventions remains poorly understood. We present the first cross-provincial evaluation of adapting BCCRTron, a domain-adapted transformer model developed at the British Columbia Cancer Registry, alongside GatorTron, a biomedical transformer model, for cancer surveillance in Canada. Our training dataset consisted of approximately 104,000 and 22,000 de-identified pathology reports from the Newfoundland & Labrador Cancer Registry (NLCR) for Tier 1 (cancer vs. non-cancer) and Tier 2 (reportable vs. non-reportable) tasks, respectively. Both models were fine-tuned using complementary synoptic and diagnosis focused report section input pipelines. Across NLCR test sets, the adapted models maintained high performance, demonstrating transformers pretrained in one jurisdiction can be localized to another with modest fine-tuning. To improve sensitivity, we combined the two models using a conservative OR-ensemble achieving a Tier 1 recall of 0.99 and reduced missed cancers to 24, compared with 48 and 54 for the standalone models. For Tier 2, the ensemble achieved 0.99 recall and reduced missed reportable cancers to 33, compared with 54 and 46 for the individual models. These findings demonstrate that an ensemble combining complementary text representations substantially reduce missed cancers and improve error coverage in cancer-registry NLP. We implement a privacy-preserving workflow in which only model weights are shared between provinces, supporting interoperable NLP infrastructure and a future pan-Canadian foundation model for cancer pathology and registry workflows.
Fonte: arXiv cs.CL
NLP/LLMs • Score 96
Democratizando Sistemas de IA Eletrônico-Fotônicos: Um Fluxo de Ferramentas de Co-Projeto e Automação de Design Infundido com IA e Código Aberto
A fotônica está se tornando uma tecnologia fundamental para sistemas de IA de alto desempenho e computação científica, oferecendo velocidade, paralelismo e eficiência energética incomparáveis. No entanto, o design e a implementação de sistemas de IA eletrônico-fotônicos permanecem desafiadores devido a uma curva de aprendizado acentuada. Apresentamos um framework de co-design e automação de múltiplas camadas para democratizar o desenvolvimento de sistemas de IA fotônicos.
Fonte: arXiv cs.AI
NLP/LLMs • Score 96
Uma Avaliação Empírica de Abordagens Baseadas em LLM para Detecção de Vulnerabilidades de Código: RAG, SFT e Sistemas de Agentes Duplos
O rápido avanço dos Large Language Models (LLMs) apresenta novas oportunidades para a detecção automatizada de vulnerabilidades de software, uma tarefa crucial para a segurança de bases de código modernas. Este artigo apresenta um estudo comparativo sobre a eficácia de técnicas baseadas em LLM para detectar vulnerabilidades de software, avaliando três abordagens: Retrieval-Augmented Generation (RAG), Supervised Fine-Tuning (SFT) e um framework de LLM de Agente Duplo.
Fonte: arXiv cs.AI
NLP/LLMs • Score 93
Mortar: Mecânicas em Evolução para Design Automático de Jogos
arXiv:2601.00105v1 Tipo de Anúncio: novo
Resumo: Apresentamos o Mortar, um sistema para evoluir mecanicamente de forma autônoma para o design automático de jogos. As mecânicas de jogo definem as regras e interações que governam a jogabilidade, e projetá-las manualmente é um processo que consome tempo e requer expertise. O Mortar combina um algoritmo de qualidade-diversidade com um modelo de linguagem grande para explorar um conjunto diversificado de mecânicas, que são avaliadas pela síntese de jogos completos que incorporam tanto mecânicas evoluídas quanto aquelas extraídas de um arquivo. As mecânicas são avaliadas pela composição de jogos completos através de um procedimento de busca em árvore, onde os jogos resultantes são avaliados pela sua capacidade de preservar uma ordenação baseada em habilidades entre os jogadores -- ou seja, se jogadores mais fortes superam consistentemente os mais fracos. Avaliamos as mecânicas com base em sua contribuição para a pontuação de ordenação baseada em habilidades no jogo. Demonstramos que o Mortar produz jogos que parecem diversos e jogáveis, e mecânicas que contribuem mais para a pontuação de ordenação baseada em habilidades no jogo. Realizamos estudos de ablação para avaliar o papel de cada componente do sistema e um estudo com usuários para avaliar os jogos com base no feedback humano.
Fonte: arXiv cs.AI
NLP/LLMs • Score 95
Language as Mathematical Structure: Examining Semantic Field Theory Against Language Games
arXiv:2601.00448v1 Announce Type: new
Abstract: Large language models (LLMs) offer a new empirical setting in which long-standing theories of linguistic meaning can be examined. This paper contrasts two broad approaches: social constructivist accounts associated with language games, and a mathematically oriented framework we call Semantic Field Theory. Building on earlier work by the author, we formalize the notions of lexical fields (Lexfelder) and linguistic fields (Lingofelder) as interacting structures in a continuous semantic space. We then analyze how core properties of transformer architectures-such as distributed representations, attention mechanisms, and geometric regularities in embedding spaces-relate to these concepts. We argue that the success of LLMs in capturing semantic regularities supports the view that language exhibits an underlying mathematical structure, while their persistent limitations in pragmatic reasoning and context sensitivity are consistent with the importance of social grounding emphasized in philosophical accounts of language use. On this basis, we suggest that mathematical structure and language games can be understood as complementary rather than competing perspectives. The resulting framework clarifies the scope and limits of purely statistical models of language and motivates new directions for theoretically informed AI architectures.
Fonte: arXiv cs.CL
NLP/LLMs • Score 96
Cadeias Neurais e Sistemas Dinâmicos Discretos
Neste trabalho, inspecionamos a analogia entre aplicações de machine learning (ML) baseadas na arquitetura transformer sem autoatenção, denominadas { t cadeias neurais}, e sistemas dinâmicos discretos associados a versões discretizadas de equações integrais e diferenciais parciais neurais (NIE, PDE). Apresentamos uma análise comparativa da solução numérica das equações de Burgers e Eikonal via discretização numérica padrão e aprendizado PINN.
Fonte: arXiv cs.LG
Vision • Score 96
Avaliação de Detectores de Anomalias para Problemas de Classificação Industrial Altamente Desequilibrados Simulados
O machine learning oferece soluções potenciais para problemas atuais em sistemas industriais, como controle de qualidade e manutenção preditiva, mas enfrenta barreiras únicas em aplicações industriais. Este artigo apresenta uma avaliação abrangente de algoritmos de detecção de anomalias usando um conjunto de dados simulado que reflete restrições de engenharia do mundo real.
Fonte: arXiv cs.AI
RL • Score 96
Computação de Reservatório Sequencial para Previsão Espacial e Temporal de Alta Dimensionalidade de Forma Eficiente
A previsão de sistemas espaciais e temporais de alta dimensionalidade continua sendo um desafio computacional para redes neurais recorrentes (RNNs) e modelos de memória de longo e curto prazo (LSTM). Introduzimos uma arquitetura de Computação de Reservatório Sequencial (Sequential RC) que decompõe um grande reservatório em uma série de reservatórios menores e interconectados, melhorando a eficiência e reduzindo custos computacionais.
Fonte: arXiv cs.LG
RL • Score 96
Uma abordagem multi-algoritmo para o balanceamento da carga de trabalho operacional de recursos humanos em um sistema de entrega urbana de última milha
A atribuição eficiente de carga de trabalho à força de trabalho é crucial em sistemas de entrega de pacotes de última milha. Este artigo aborda o problema do balanceamento da carga de trabalho operacional em sistemas de entrega urbana, propondo uma abordagem multi-algoritmo que otimiza o tempo de entrega e garante uma distribuição equilibrada da carga de trabalho entre os trabalhadores.
Fonte: arXiv cs.AI
NLP/LLMs • Score 95
Talk Less, Verify More: Improving LLM Assistants with Semantic Checks and Execution Feedback
arXiv:2601.00224v1 Announce Type: new
Abstract: As large language model (LLM) assistants become increasingly integrated into enterprise workflows, their ability to generate accurate, semantically aligned, and executable outputs is critical. However, current conversational business analytics (CBA) systems often lack built-in verification mechanisms, leaving users to manually validate potentially flawed results. This paper introduces two complementary verification techniques: Q*, which performs reverse translation and semantic matching between code and user intent, and Feedback+, which incorporates execution feedback to guide code refinement. Embedded within a generator-discriminator framework, these mechanisms shift validation responsibilities from users to the system. Evaluations on three benchmark datasets, Spider, Bird, and GSM8K, demonstrate that both Q* and Feedback+ reduce error rates and task completion time. The study also identifies reverse translation as a key bottleneck, highlighting opportunities for future improvement. Overall, this work contributes a design-oriented framework for building more reliable, enterprise-grade GenAI systems capable of trustworthy decision support.
Fonte: arXiv cs.CL
NLP/LLMs • Score 95
A Language-Agnostic Hierarchical LoRA-MoE Architecture for CTC-based Multilingual ASR
arXiv:2601.00557v1 Announce Type: new
Abstract: Large-scale multilingual ASR (mASR) models such as Whisper achieve strong performance but incur high computational and latency costs, limiting their deployment on resource-constrained edge devices. In this study, we propose a lightweight and language-agnostic multilingual ASR system based on a CTC architecture with domain adaptation. Specifically, we introduce a Language-agnostic Hierarchical LoRA-MoE (HLoRA) framework integrated into an mHuBERT-CTC model, enabling end-to-end decoding via LID-posterior-driven LoRA routing. The hierarchical design consists of a multilingual shared LoRA for learning language-invariant acoustic representations and language-specific LoRA experts for modeling language-dependent characteristics. The proposed routing mechanism removes the need for prior language identity information or explicit language labels during inference, achieving true language-agnostic decoding. Experiments on MSR-86K and the MLC-SLM 2025 Challenge datasets demonstrate that HLoRA achieves competitive performance with state-of-the-art two-stage inference methods using only single-pass decoding, significantly improving decoding efficiency for low-resource mASR applications.
Fonte: arXiv cs.CL
NLP/LLMs • Score 95
The Role of Mixed-Language Documents for Multilingual Large Language Model Pretraining
arXiv:2601.00364v1 Announce Type: new
Abstract: Multilingual large language models achieve impressive cross-lingual performance despite largely monolingual pretraining. While bilingual data in pretraining corpora is widely believed to enable these abilities, details of its contributions remain unclear. We investigate this question by pretraining models from scratch under controlled conditions, comparing the standard web corpus with a monolingual-only version that removes all multilingual documents. Despite constituting only 2% of the corpus, removing bilingual data causes translation performance to drop 56% in BLEU, while behaviour on cross-lingual QA and general reasoning tasks remains stable, with training curves largely overlapping the baseline. To understand this asymmetry, we categorize bilingual data into parallel (14%), code-switching (72%), and miscellaneous documents (14%) based on the semantic relevance of content in different languages. We then conduct granular ablations by reintroducing parallel or code-switching data into the monolingual-only corpus. Our experiments reveal that parallel data almost fully restores translation performance (91% of the unfiltered baseline), whereas code-switching contributes minimally. Other cross-lingual tasks remain largely unaffected by either type. These findings reveal that translation critically depends on systematic token-level alignments from parallel data, whereas cross-lingual understanding and reasoning appear to be achievable even without bilingual data.
Fonte: arXiv cs.CL
RL • Score 96
O Transporte Ótimo Pode Melhorar o Aprendizado por Reforço Inverso Federado?
Neste artigo, introduzimos uma abordagem baseada em transporte ótimo para o aprendizado por reforço inverso federado (IRL). Cada cliente realiza localmente um IRL de Máxima Entropia, respeitando suas limitações computacionais e de privacidade. As funções de recompensa resultantes são fundidas via um barycenter de Wasserstein, que considera sua estrutura geométrica subjacente. Este trabalho oferece um framework eficiente em comunicação para derivar uma recompensa compartilhada que se generaliza entre agentes e ambientes heterogêneos.
Fonte: arXiv cs.LG
MLOps/Systems • Score 93
Compreendendo Emoção no Discurso: Insights de Reconhecimento e Padrões Linguísticos para Geração
O reconhecimento de emoções em conversas (ERC) alcançou alta precisão, mas duas lacunas críticas permanecem: uma compreensão limitada das escolhas arquitetônicas que realmente importam e a falta de análise linguística conectando reconhecimento à geração. Abordamos ambas as lacunas por meio de uma análise sistemática do conjunto de dados IEMOCAP.
Fonte: arXiv cs.AI
Vision • Score 96
Engenharia de Recursos Híbridos Otimizada para Detecção de Arritmias Eficiente em Recursos em Sinais de ECG: Um Framework de Otimização
As doenças cardiovasculares, especialmente as arritmias, continuam a ser uma das principais causas de mortalidade global, exigindo monitoramento contínuo via Internet das Coisas Médicas (IoMT). Este estudo propõe um framework centrado em dados e eficiente em recursos que prioriza a engenharia de características em vez da complexidade, alcançando alta precisão diagnóstica com um modelo leve.
Fonte: arXiv cs.LG
NLP/LLMs • Score 95
From Evidence-Based Medicine to Knowledge Graph: Retrieval-Augmented Generation for Sports Rehabilitation and a Domain Benchmark
arXiv:2601.00216v1 Announce Type: new
Abstract: In medicine, large language models (LLMs) increasingly rely on retrieval-augmented generation (RAG) to ground outputs in up-to-date external evidence. However, current RAG approaches focus primarily on performance improvements while overlooking evidence-based medicine (EBM) principles. This study addresses two key gaps: (1) the lack of PICO alignment between queries and retrieved evidence, and (2) the absence of evidence hierarchy considerations during reranking. We present a generalizable strategy for adapting EBM to graph-based RAG, integrating the PICO framework into knowledge graph construction and retrieval, and proposing a Bayesian-inspired reranking algorithm to calibrate ranking scores by evidence grade without introducing predefined weights. We validated this framework in sports rehabilitation, a literature-rich domain currently lacking RAG systems and benchmarks. We released a knowledge graph (357,844 nodes and 371,226 edges) and a reusable benchmark of 1,637 QA pairs. The system achieved 0.830 nugget coverage, 0.819 answer faithfulness, 0.882 semantic similarity, and 0.788 PICOT match accuracy. In a 5-point Likert evaluation, five expert clinicians rated the system 4.66-4.84 across factual accuracy, faithfulness, relevance, safety, and PICO alignment. These findings demonstrate that the proposed EBM adaptation strategy improves retrieval and answer quality and is transferable to other clinical domains. The released resources also help address the scarcity of RAG datasets in sports rehabilitation.
Fonte: arXiv cs.CL
MLOps/Systems • Score 96
Avatar Forcing: Geração Interativa de Avatares de Cabeça em Tempo Real para Conversação Natural
A geração de cabeças falantes cria avatares realistas a partir de retratos estáticos para comunicação virtual e criação de conteúdo. No entanto, modelos atuais não transmitem a sensação de comunicação verdadeiramente interativa, gerando respostas unidimensionais que carecem de engajamento emocional. Propomos o Avatar Forcing, um novo framework para geração de avatares que modela interações em tempo real entre usuários e avatares através de difusão forçada.
Fonte: arXiv cs.LG
NLP/LLMs • Score 95
Universal Adaptive Constraint Propagation: Scaling Structured Inference for Large Language Models via Meta-Reinforcement Learning
arXiv:2601.00095v1 Announce Type: new
Abstract: Large language models increasingly require structured inference, from JSON schema enforcement to multi-lingual parsing, where outputs must satisfy complex constraints. We introduce MetaJuLS, a meta-reinforcement learning approach that learns universal constraint propagation policies applicable across languages and tasks without task-specific retraining. By formulating structured inference as adaptive constraint propagation and training a Graph Attention Network with meta-learning, MetaJuLS achieves 1.5--2.0$\times$ speedups over GPU-optimized baselines while maintaining within 0.2\% accuracy of state-of-the-art parsers. On Universal Dependencies across 10 languages and LLM-constrained generation (LogicBench, GSM8K-Constrained), MetaJuLS demonstrates rapid cross-domain adaptation: a policy trained on English parsing adapts to new languages and tasks with 5--10 gradient steps (5--15 seconds) rather than requiring hours of task-specific training. Mechanistic analysis reveals the policy discovers human-like parsing strategies (easy-first) and novel non-intuitive heuristics. By reducing propagation steps in LLM deployments, MetaJuLS contributes to Green AI by directly reducing inference carbon footprint.
Fonte: arXiv cs.CL
RL • Score 96
Predição Precoce de Cirrose Hepática com Antecedência de Até Três Anos: Um Estudo de Machine Learning Comparando com o FIB-4
Objetivo: Desenvolver e avaliar modelos de machine learning (ML) para prever a cirrose hepática incidente um, dois e três anos antes do diagnóstico, utilizando dados de registros eletrônicos de saúde (EHR) coletados rotineiramente, e comparar seu desempenho com o escore FIB-4. Métodos: Realizamos um estudo de coorte retrospectivo usando dados de EHR desidentificados de um grande sistema de saúde acadêmico.
Fonte: arXiv cs.LG
MLOps/Systems • Score 96
Benchmarking de Métodos de Pré-processamento e Integração em Genômica de Células Únicas
A análise de dados de células únicas tem o potencial de revolucionar a medicina personalizada ao caracterizar mudanças moleculares associadas a doenças em nível celular. Este estudo examina um pipeline geral para análise de dados de células únicas, avaliando diferentes métodos de normalização, redução de dimensionalidade e integração, utilizando seis conjuntos de dados variados.
Fonte: arXiv cs.AI
RL • Score 96
Dominação Quântica King-Ring no Xadrez: Uma Abordagem QAOA
O Quantum Approximate Optimization Algorithm (QAOA) é amplamente testado em instâncias aleatórias sintéticas, mas carece de estrutura semântica e interpretabilidade humana. Apresentamos a Dominação Quântica King-Ring (QKRD), um benchmark em escala NISQ derivado de posições táticas de xadrez, oferecendo 5.000 instâncias estruturadas. Usando QKRD, avaliamos escolhas de design do QAOA e mostramos que técnicas informadas por problemas revelam vantagens ocultas em instâncias aleatórias.
Fonte: arXiv cs.LG
RL • Score 96
Uma Análise Comparativa de Métodos de Machine Learning Interpretabéis
Nos últimos anos, o Machine Learning (ML) tem sido amplamente adotado em diversos setores, incluindo áreas críticas como saúde, finanças e direito. Essa dependência crescente levantou preocupações sobre a interpretabilidade e a responsabilidade dos modelos, especialmente com a imposição de restrições legais e regulatórias sobre o uso de modelos black-box. Este estudo apresenta uma avaliação comparativa de 16 métodos inerentemente interpretabéis, abrangendo 216 conjuntos de dados tabulares do mundo real.
Fonte: arXiv cs.LG
Vision • Score 96
Um Estudo Comparativo de Estratégias de Adaptação para Modelos Fundamentais de Séries Temporais na Detecção de Anomalias
A detecção de anomalias em séries temporais é essencial para a operação confiável de sistemas complexos, mas a maioria dos métodos existentes requer treinamento extenso e específico. Este estudo investiga se modelos fundamentais de séries temporais (TSFMs), pré-treinados em grandes dados heterogêneos, podem servir como bases universais para detecção de anomalias.
Fonte: arXiv cs.LG
NLP/LLMs • Score 96
Além de APIs Perfeitas: Uma Avaliação Abrangente de Agentes LLM Sob a Complexidade Real de APIs
Apresentamos o WildAGTEval, um benchmark projetado para avaliar as capacidades de chamada de função de agentes de modelos de linguagem grande (LLM) sob a complexidade realista de APIs. Ao contrário de trabalhos anteriores que assumem um sistema de API idealizado, WildAGTEval considera a especificação e a execução de APIs, oferecendo cenários de complexidade variados para avaliar o desempenho dos LLMs.
Fonte: arXiv cs.AI
RL • Score 93
Quando a Aprendizagem Renormaliza? Condições Suficientes para Dinâmicas Espectrais em Lei de Potência
A escalabilidade empírica em lei de potência tem sido amplamente observada em sistemas modernos de deep learning, mas suas origens teóricas e escopo de validade permanecem incompletamente compreendidos. O framework Generalized Resolution-Shell Dynamics (GRSD) modela a aprendizagem como transporte de energia espectral através de camadas de resolução logarítmica, oferecendo uma descrição dinâmica da formação.
Fonte: arXiv cs.LG
NLP/LLMs • Score 93
CodeGEMM: Uma Abordagem Centrada em Codebook para GEMM Eficiente em LLMs Quantizados
A quantização apenas de pesos é amplamente utilizada para mitigar a natureza limitada da memória na inferência de LLM. Métodos baseados em codebook alcançam alta precisão em regimes de bits extremamente baixos (por exemplo, 2 bits). Apresentamos o CodeGEMM, um kernel GEMM centrado em codebook que substitui a dequantização por produtos internos pré-computados, melhorando a eficiência computacional e a utilização do subsistema de memória.
Fonte: arXiv cs.LG
RL • Score 96
Extensão de Base Contrafactual e Geometria Representacional: Um Modelo de Crescimento Conceitual com Restrições de MDL
O aprendizado de conceitos se torna possível apenas quando representações existentes falham em contabilizar a experiência. Este artigo propõe um framework geométrico onde o crescimento conceitual é modelado como extensão de base admissível avaliada sob um critério de Minimum Description Length (MDL). A experiência é representada como vetores em relação a um subespaço conceitual atual.
Fonte: arXiv cs.AI
Vision • Score 95
Teste para estrutura latente via a matriz aleatória de Wilcoxon--Wigner de estatísticas de classificação normalizadas
Este artigo considera o problema de testar a estrutura latente em grandes matrizes de dados simétricas. O objetivo é desenvolver uma metodologia estatisticamente fundamentada que seja flexível em sua aplicabilidade, computacionalmente eficiente e insensível a variações extremas nos dados, superando assim as limitações das abordagens existentes.
Fonte: arXiv stat.ML
RL • Score 96
LeJOT: Uma Solução Inteligente de Orquestração de Custos de Trabalho para a Plataforma Databricks
Com os avanços rápidos em tecnologias de big data, a plataforma Databricks tornou-se fundamental para empresas e instituições de pesquisa. No entanto, gerenciar os custos operacionais crescentes associados à execução de trabalhos é um desafio crítico. Apresentamos o LeJOT, um framework de orquestração de custos de trabalho que utiliza machine learning para previsão de tempo de execução e um modelo de otimização baseado em solver para alocação de recursos em tempo real.
Fonte: arXiv cs.LG
MLOps/Systems • Score 89
Universalidade dos limites de escalonamento de alta dimensão do stochastic gradient descent
Consideramos tarefas estatísticas em altas dimensões cuja perda depende dos dados apenas através de sua projeção em um subespaço de dimensão fixa. Isso inclui a classificação de distribuições mistas com perda de cross-entropy usando redes de uma e duas camadas. Nosso principal resultado é que os limites de ODE são universais, desde que a inicialização e os vetores de verdade fundamental sejam deslocalizados em coordenadas.
Fonte: arXiv stat.ML
RL • Score 96
APC-GNN++: Uma GNN Adaptativa Centrada no Paciente com Atenção Consciente do Contexto e Explicabilidade de Mini-Grafos para Classificação de Diabetes
Propomos o APC-GNN++, uma Rede Neural Gráfica centrada no paciente para classificação de diabetes. Nosso modelo integra atenção de arestas consciente do contexto, mistura guiada por confiança de características de nós e representações gráficas, e regularização de consistência de vizinhança para capturar melhor relações clinicamente significativas entre pacientes.
Fonte: arXiv cs.LG
RL • Score 95
AraMix: Recycling, Refiltering, and Deduplicating to Deliver the Largest Arabic Pretraining Corpus
arXiv:2512.18834v1 Announce Type: new
Abstract: We present AraMix, a deduplicated Arabic pretraining corpus containing approximately 178 billion tokens across 179 million documents. Rather than scraping the web again, AraMix demonstrates that substantial value lies in systematically reusing and curating existing pretraining datasets: we combine seven publicly available Arabic web datasets, apply quality filtering designed specifically for Arabic text to re-filter some datasets, and perform cross-dataset deduplication, both MinHash and sentence-level. This approach reveals that nearly 60% of tokens across these independently collected corpora are duplicates, redundancy that any new scraping efforts will reproduce. Our work suggests that for lower resource languages, investment in curation pipelines for existing data yields greater returns than additional web crawls, an approach that allowed us to curate the largest heavily filtered publicly available Arabic pretraining corpus.
Fonte: arXiv cs.CL
NLP/LLMs • Score 95
FASTRIC: Linguagem de Especificação de Prompt para Interações LLM Verificáveis
Modelos de Linguagem de Grande Escala (LLMs) executam protocolos complexos de interação, mas carecem de especificações formais para verificar a execução em relação à intenção do designer. Apresentamos o FASTRIC, uma Linguagem de Especificação de Prompt que torna Máquinas de Estados Finitos (FSMs) implícitas explícitas em prompts de linguagem natural, permitindo a verificação de conformidade por meio da análise de rastreamento de execução.
Fonte: arXiv cs.CL
RL • Score 96
Aprendizado Profundo de Reforço Confiável e Explicável para Controle de Processos Seguro e Eficiente em Energia: Um Caso de Uso em Sistemas Industriais de Ar Comprimido
Este artigo apresenta uma abordagem confiável de aprendizado por reforço para o controle de sistemas industriais de ar comprimido. Desenvolvemos um framework que possibilita operação segura e eficiente em energia sob condições de contorno realistas e introduzimos um pipeline de explicabilidade em múltiplos níveis. Uma avaliação empírica mostra que a política aprendida é fisicamente plausível e respeita consistentemente os limites do sistema.
Fonte: arXiv cs.LG
RL • Score 93
Serviço Eficiente de Mistura de Agentes via Roteamento em Estruturas de Árvore, Poda Adaptativa e Sobreposição de Pré-preenchimento e Decodificação Consciente de Dependências
arXiv:2512.18126v1 Tipo de Anúncio: novo
Resumo: A inferência de Mistura de Agentes (MoA) pode sofrer com comunicação densa entre agentes e baixa utilização de hardware, o que, em conjunto, aumenta a latência de serviço. Apresentamos um design de serviço que visa esses gargalos por meio de um co-design de algoritmo e sistema. Primeiro, substituímos gráficos de interação densa entre agentes por uma topologia hierárquica em árvore que induz esparsidade estruturada na comunicação entre agentes. Em segundo lugar, introduzimos um mecanismo adaptativo em tempo de execução que termina ou ignora seletivamente invocações de agentes a jusante usando sinais de acordo semântico e confiança a partir de saídas intermediárias. Por fim, realizamos a execução de agentes em pipeline, sobrepondo o pré-preenchimento incremental com a decodificação entre agentes relacionados a dependências, melhorando a utilização e reduzindo a latência de inferência. Em tarefas representativas, essa abordagem reduz substancialmente a latência de ponta a ponta (em até 90%) enquanto mantém uma precisão comparável (dentro de $m{ ext{ extpm}}$1%) em relação às bases de MoA de conectividade densa e pode melhorar a precisão em certos contextos.
Fonte: arXiv cs.AI
RL • Score 92
Aprendizado de atratores para sistemas dinâmicos caóticos espaciotemporais usando redes de estado de eco com aprendizado por transferência
Neste artigo, exploramos as capacidades preditivas das redes de estado de eco (ESNs) para a equação de Kuramoto-Sivashinsky generalizada (gKS), uma PDE não linear arquetípica que exibe caos espaciotemporal. Nossa pesquisa foca na previsão de mudanças em padrões estatísticos de longo prazo do modelo gKS resultantes da variação da relação de dispersão ou do comprimento do domínio espacial.
Fonte: arXiv stat.ML
NLP/LLMs • Score 95
Generalization Gaps in Political Fake News Detection: An Empirical Study on the LIAR Dataset
arXiv:2512.18533v1 Announce Type: new
Abstract: The proliferation of linguistically subtle political disinformation poses a significant challenge to automated fact-checking systems. Despite increasing emphasis on complex neural architectures, the empirical limits of text-only linguistic modeling remain underexplored. We present a systematic diagnostic evaluation of nine machine learning algorithms on the LIAR benchmark. By isolating lexical features (Bag-of-Words, TF-IDF) and semantic embeddings (GloVe), we uncover a hard "Performance Ceiling", with fine-grained classification not exceeding a Weighted F1-score of 0.32 across models. Crucially, a simple linear SVM (Accuracy: 0.624) matches the performance of pre-trained Transformers such as RoBERTa (Accuracy: 0.620), suggesting that model capacity is not the primary bottleneck. We further diagnose a massive "Generalization Gap" in tree-based ensembles, which achieve more than 99% training accuracy but collapse to approximately 25% on test data, indicating reliance on lexical memorization rather than semantic inference. Synthetic data augmentation via SMOTE yields no meaningful gains, confirming that the limitation is semantic (feature ambiguity) rather than distributional. These findings indicate that for political fact-checking, increasing model complexity without incorporating external knowledge yields diminishing returns.
Fonte: arXiv cs.CL
NLP/LLMs • Score 96
Rumo à Avaliação de Vulnerabilidades de Privacidade no Esquecimento Seletivo com Modelos de Linguagem de Grande Escala
Os avanços rápidos em inteligência artificial (IA) têm se concentrado no aprendizado a partir de dados para desenvolver sistemas de aprendizado informados. Com a implementação desses sistemas em áreas críticas, garantir sua privacidade e alinhamento com valores humanos é essencial. O esquecimento seletivo, ou machine unlearning, surge como uma abordagem promissora, mas também levanta preocupações significativas de privacidade, especialmente em domínios sensíveis.
Fonte: arXiv cs.LG
NLP/LLMs • Score 95
De Palavra a Mundo: Podem Modelos de Linguagem Grande Servir como Modelos de Mundo Baseados em Texto Implicitamente?
O aprendizado por reforço agente depende cada vez mais de escalabilidade orientada pela experiência, mas ambientes do mundo real continuam sendo não adaptativos e difíceis de escalar. Este estudo investiga se modelos de linguagem grande (LLMs) podem melhorar a eficiência do aprendizado em ambientes baseados em texto, apresentando um framework de três níveis para avaliação de modelos de mundo baseados em LLMs.
Fonte: arXiv cs.CL
NLP/LLMs • Score 95
CoPE: A Small Language Model for Steerable and Scalable Content Labeling
arXiv:2512.18027v1 Announce Type: new
Abstract: This paper details the methodology behind CoPE, a policy-steerable small language model capable of fast and accurate content labeling. We present a novel training curricula called Contradictory Example Training that enables the model to learn policy interpretation rather than mere policy memorization. We also present a novel method for generating content policies, called Binocular Labeling, which enables rapid construction of unambiguous training datasets. When evaluated across seven different harm areas, CoPE exhibits equal or superior accuracy to frontier models at only 1% of their size. We openly release a 9 billion parameter version of the model that can be run on a single consumer-grade GPU. Models like CoPE represent a paradigm shift for classifier systems. By turning an ML task into a policy writing task, CoPE opens up new design possibilities for the governance of online platforms.
Fonte: arXiv cs.CL
NLP/LLMs • Score 95
AraToken: Optimizing Arabic Tokenization with Normalization Pipeline and Language Extension for Qwen3
arXiv:2512.18399v1 Announce Type: new
Abstract: Tokenization is a critical preprocessing step for large language models (LLMs), directly impacting training efficiency and downstream performance. General-purpose tokenizers trained predominantly on English and Latin-script languages exhibit suboptimal performance on morphologically rich languages such as Arabic, resulting in inflated token sequences and reduced compression efficiency. In this work, we present AraToken, an Arabic-optimized tokenizer built on SentencePiece Unigram algorithm with a comprehensive normalization pipeline addressing Arabic-specific orthographic variations including Alif variants, diacritics, and Arabic-Indic numerals. We systematically compare BPE, WordPiece, and SentencePiece algorithms across multiple configurations, demonstrating that SentencePiece with normalization achieves 18% lower fertility (1.199 vs 1.35 tokens/word) compared to unnormalized baselines. Furthermore, we introduce the Language Extension Pipeline (LEP), a method for integrating the optimized tokenizer into Qwen3-0.6B through vocabulary extension with mean subtoken initialization and selective transformer layer unfreezing. Our experiments show that LEP reduces evaluation loss from 8.28 to 2.43 within 800 training steps on 100K Arabic samples. We release our tokenizer, training scripts, and model checkpoints to facilitate Arabic NLP research.
Fonte: arXiv cs.CL
NLP/LLMs • Score 96
MoE-TransMov: Um Modelo Baseado em Transformer para Previsão do Próximo Ponto de Interesse (POI) em Movimentos Familiares e Não Familiares
A previsão precisa do próximo ponto de interesse (POI) nas trajetórias de mobilidade humana é crucial para serviços baseados em localização, permitindo recomendações mais oportunas e personalizadas. Propomos o MoE-TransMov, um modelo baseado em Transformer com arquitetura Mixture-of-Experts (MoE) que captura padrões de mobilidade distintos em diferentes contextos de movimento, melhorando a precisão das previsões.
Fonte: arXiv cs.LG
NLP/LLMs • Score 95
Research on a hybrid LSTM-CNN-Attention model for text-based web content classification
arXiv:2512.18475v1 Announce Type: new
Abstract: This study presents a hybrid deep learning architecture that integrates LSTM, CNN, and an Attention mechanism to enhance the classification of web content based on text. Pretrained GloVe embeddings are used to represent words as dense vectors that preserve semantic similarity. The CNN layer extracts local n-gram patterns and lexical features, while the LSTM layer models long-range dependencies and sequential structure. The integrated Attention mechanism enables the model to focus selectively on the most informative parts of the input sequence. A 5-fold cross-validation setup was used to assess the robustness and generalizability of the proposed solution. Experimental results show that the hybrid LSTM-CNN-Attention model achieved outstanding performance, with an accuracy of 0.98, precision of 0.94, recall of 0.92, and F1-score of 0.93. These results surpass the performance of baseline models based solely on CNNs, LSTMs, or transformer-based classifiers such as BERT. The combination of neural network components enabled the model to effectively capture both fine-grained text structures and broader semantic context. Furthermore, the use of GloVe embeddings provided an efficient and effective representation of textual data, making the model suitable for integration into systems with real-time or near-real-time requirements. The proposed hybrid architecture demonstrates high effectiveness in text-based web content classification, particularly in tasks requiring both syntactic feature extraction and semantic interpretation. By combining presented mechanisms, the model addresses the limitations of individual architectures and achieves improved generalization. These findings support the broader use of hybrid deep learning approaches in NLP applications, especially where complex, unstructured textual data must be processed and classified with high reliability.
Fonte: arXiv cs.CL
NLP/LLMs • Score 92
SRS-Stories: Vocabulary-constrained multilingual story generation for language learning
arXiv:2512.18362v1 Announce Type: new
Abstract: In this paper, we use large language models to generate personalized stories for language learners, using only the vocabulary they know. The generated texts are specifically written to teach the user new vocabulary by simply reading stories where it appears in context, while at the same time seamlessly reviewing recently learned vocabulary. The generated stories are enjoyable to read and the vocabulary reviewing/learning is optimized by a Spaced Repetition System. The experiments are conducted in three languages: English, Chinese and Polish, evaluating three story generation methods and three strategies for enforcing lexical constraints. The results show that the generated stories are more grammatical, coherent, and provide better examples of word usage than texts generated by the standard constrained beam search approach
Fonte: arXiv cs.CL
NLP/LLMs • Score 92
LIR$^3$AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generation
arXiv:2512.18329v1 Announce Type: new
Abstract: Retrieval-Augmented Generation (RAG) effectively enhances Large Language Models (LLMs) by incorporating retrieved external knowledge into the generation process. Reasoning models improve LLM performance in multi-hop QA tasks, which require integrating and reasoning over multiple pieces of evidence across different documents to answer a complex question. However, they often introduce substantial computational costs, including increased token consumption and inference latency. To better understand and mitigate this trade-off, we conduct a comprehensive study of reasoning strategies for reasoning models in RAG multi-hop QA tasks. Our findings reveal that reasoning models adopt structured strategies to integrate retrieved and internal knowledge, primarily following two modes: Context-Grounded Reasoning, which relies directly on retrieved content, and Knowledge-Reconciled Reasoning, which resolves conflicts or gaps using internal knowledge. To this end, we propose a novel Lightweight Rerank Reasoning Strategy Framework for RAG (LiR$^3$AG) to enable non-reasoning models to transfer reasoning strategies by restructuring retrieved evidence into coherent reasoning chains. LiR$^3$AG significantly reduce the average 98% output tokens overhead and 58.6% inferencing time while improving 8B non-reasoning model's F1 performance ranging from 6.2% to 22.5% to surpass the performance of 32B reasoning model in RAG, offering a practical and efficient path forward for RAG systems.
Fonte: arXiv cs.CL
RL • Score 96
O Challenger: Quando Novas Fontes de Dados Justificam a Troca de Modelos de Machine Learning?
Estudamos o problema de decidir se e quando uma organização deve substituir um modelo incumbente treinado por um challenger que utiliza novas características disponíveis. Desenvolvemos um framework econômico e estatístico unificado que relaciona dinâmicas de curva de aprendizado, custos de aquisição de dados e re-treinamento, e desconto de ganhos futuros.
Fonte: arXiv cs.LG
NLP/LLMs • Score 95
Reliable Decision Support with LLMs: A Framework for Evaluating Consistency in Binary Text Classification Applications
arXiv:2505.14918v2 Announce Type: replace-cross
Abstract: This study introduces a framework for evaluating consistency in large language model (LLM) binary text classification, addressing the lack of established reliability assessment methods. Adapting psychometric principles, we determine sample size requirements, develop metrics for invalid responses, and evaluate intra- and inter-rater reliability. Our case study examines financial news sentiment classification across 14 LLMs (including claude-3-7-sonnet, gpt-4o, deepseek-r1, gemma3, llama3.2, phi4, and command-r-plus), with five replicates per model on 1,350 articles. Models demonstrated high intra-rater consistency, achieving perfect agreement on 90-98% of examples, with minimal differences between expensive and economical models from the same families. When validated against StockNewsAPI labels, models achieved strong performance (accuracy 0.76-0.88), with smaller models like gemma3:1B, llama3.2:3B, and claude-3-5-haiku outperforming larger counterparts. All models performed at chance when predicting actual market movements, indicating task constraints rather than model limitations. Our framework provides systematic guidance for LLM selection, sample size planning, and reliability assessment, enabling organizations to optimize resources for classification tasks.
Fonte: arXiv stat.ML
MLOps/Systems • Score 96
A Cama Procrusteana das Séries Temporais: O Viés de Otimização da Função de Perda Pontual
Otimizar modelos de séries temporais por meio de funções de perda pontuais (por exemplo, MSE) baseando-se em uma suposição falha de independência e distribuição idêntica pontual (i.i.d.) que desconsidera a estrutura temporal causal. Este artigo analisa o Expectation of Optimization Bias (EOB) e revela que quanto mais determinística e estruturada a série temporal, mais severo é o viés causado pela função de perda pontual.
Fonte: arXiv cs.LG
RL • Score 96
Previsão e Prognóstico dos Impactos de Secas de Curto Prazo Usando Machine Learning para Apoiar Esforços de Mitigação e Adaptação
A seca é um risco natural complexo que afeta sistemas ecológicos e humanos, resultando em perdas ambientais e econômicas significativas. Este estudo aplica técnicas de machine learning para vincular índices de seca a registros históricos de impactos, gerando previsões de curto prazo. Os resultados indicam que os impactos de incêndios e alívio foram previstos com maior precisão, apoiando o desenvolvimento de um Sistema de Comunicação de Informação Ecológica sobre Secas (EcoDri) para o Novo México.
Fonte: arXiv cs.LG
NLP/LLMs • Score 95
Q-KVComm: Comunicação Multi-Agente Eficiente Via Compressão Adaptativa de Cache KV
Sistemas multi-agente de Large Language Model (LLM) enfrentam um gargalo crítico: a transmissão redundante de informações contextuais entre agentes consome largura de banda e recursos computacionais excessivos. Apresentamos o Q-KVComm, um novo protocolo que permite a transmissão direta de representações comprimidas de cache key-value (KV) entre agentes LLM.
Fonte: arXiv cs.CL
NLP/LLMs • Score 96
Aprendizado por transferência baseado em operador neural convolucional para resolver PDEs
O operador neural convolucional é uma arquitetura baseada em CNN recentemente proposta para garantir equivalência contínua-discreta que preserva a estrutura e possibilitar o aprendizado genuíno e sem aliasing de operadores de solução de PDEs. Este operador neural demonstrou superar, em certos casos, modelos de referência como DeepONet e Fourier neural operator em termos de precisão de surrogates.
Fonte: arXiv cs.LG
RL • Score 95
Neural CDEs como Corretores para Modelos de Séries Temporais Aprendidos
Modelos de séries temporais aprendidos, sejam contínuos ou discretos, são amplamente utilizados para prever os estados de um sistema dinâmico. Propomos um mecanismo de Predictor-Corrector, onde o Predictor é um modelo de série temporal aprendido e o Corrector é uma equação diferencial controlada neuralmente. A adição de erros às previsões melhora o desempenho das previsões.
Fonte: arXiv stat.ML
RL • Score 95
ReGal: A First Look at PPO-based Legal AI for Judgment Prediction and Summarization in India
arXiv:2512.18014v1 Announce Type: new
Abstract: This paper presents an early exploration of reinforcement learning methodologies for legal AI in the Indian context. We introduce Reinforcement Learning-based Legal Reasoning (ReGal), a framework that integrates Multi-Task Instruction Tuning with Reinforcement Learning from AI Feedback (RLAIF) using Proximal Policy Optimization (PPO). Our approach is evaluated across two critical legal tasks: (i) Court Judgment Prediction and Explanation (CJPE), and (ii) Legal Document Summarization. Although the framework underperforms on standard evaluation metrics compared to supervised and proprietary models, it provides valuable insights into the challenges of applying RL to legal texts. These challenges include reward model alignment, legal language complexity, and domain-specific adaptation. Through empirical and qualitative analysis, we demonstrate how RL can be repurposed for high-stakes, long-document tasks in law. Our findings establish a foundation for future work on optimizing legal reasoning pipelines using reinforcement learning, with broader implications for building interpretable and adaptive legal AI systems.
Fonte: arXiv cs.CL
NLP/LLMs • Score 94
LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text Generators
arXiv:2512.18360v1 Announce Type: new
Abstract: We present a novel neurosymbolic framework for RDF-to-text generation, in which the model is "trained" through collaborative interactions among multiple LLM agents rather than traditional backpropagation. The LLM agents produce rule-based Python code for a generator for the given domain, based on RDF triples only, with no in-domain human reference texts. The resulting system is fully interpretable, requires no supervised training data, and generates text nearly instantaneously using only a single CPU. Our experiments on the WebNLG and OpenDialKG data show that outputs produced by our approach reduce hallucination, with only slight fluency penalties compared to finetuned or prompted language models
Fonte: arXiv cs.CL
MLOps/Systems • Score 95
GenUQ: Estimativas de Incerteza Preditiva via Redes Hiper-Geradoras
O aprendizado de operadores é uma generalização recente da regressão para mapeamentos entre funções. Ele promete reduzir drasticamente a integração numérica cara de PDEs para avaliações rápidas de mapeamentos entre estados funcionais de um sistema. Neste artigo, apresentamos o GenUQ, uma abordagem teórica de medida para UQ que evita a construção de uma verossimilhança ao introduzir um modelo de rede hiper-geradora que produz distribuições de parâmetros consistentes com dados observados.
Fonte: arXiv stat.ML
NLP/LLMs • Score 92
Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction
arXiv:2512.18880v1 Announce Type: new
Abstract: Accurate estimation of item (question or task) difficulty is critical for educational assessment but suffers from the cold start problem. While Large Language Models demonstrate superhuman problem-solving capabilities, it remains an open question whether they can perceive the cognitive struggles of human learners. In this work, we present a large-scale empirical analysis of Human-AI Difficulty Alignment for over 20 models across diverse domains such as medical knowledge and mathematical reasoning. Our findings reveal a systematic misalignment where scaling up model size is not reliably helpful; instead of aligning with humans, models converge toward a shared machine consensus. We observe that high performance often impedes accurate difficulty estimation, as models struggle to simulate the capability limitations of students even when being explicitly prompted to adopt specific proficiency levels. Furthermore, we identify a critical lack of introspection, as models fail to predict their own limitations. These results suggest that general problem-solving capability does not imply an understanding of human cognitive struggles, highlighting the challenge of using current models for automated difficulty prediction.
Fonte: arXiv cs.CL
Vision • Score 96
EIA-SEC: Framework Melhorado de Actor-Critic para Controle Colaborativo de Multi-UAV na Agricultura Inteligente
A aplicação generalizada da tecnologia de comunicação sem fio tem promovido o desenvolvimento da agricultura inteligente, onde veículos aéreos não tripulados (UAVs) desempenham um papel multifuncional. Neste trabalho, modelamos um processo de decisão de Markov para resolver o problema de planejamento de trajetória de multi-UAV e propomos o novo framework Elite Imitation Actor-Shared Ensemble Critic (EIA-SEC). Resultados experimentais mostram que o EIA-SEC supera as referências de ponta em desempenho de recompensa, estabilidade de treinamento e velocidade de convergência.
Fonte: arXiv cs.LG
NLP/LLMs • Score 96
Benchmarking de substitutos neurais em fluxos multifísicos espaço-temporais realistas
Prever dinâmicas multifísicas é computacionalmente caro e desafiador devido ao acoplamento severo de processos físicos heterogêneos e multiescala. Apresentamos o REALM (REalistic AI Learning for Multiphysics), um framework rigoroso de benchmarking para testar substitutos neurais em fluxos reativos desafiadores, com 11 conjuntos de dados de alta fidelidade e um protocolo padronizado de treinamento e avaliação.
Fonte: arXiv cs.LG
NLP/LLMs • Score 95
GeoSense-AI: Fast Location Inference from Crisis Microblogs
arXiv:2512.18225v1 Announce Type: new
Abstract: This paper presents an applied AI pipeline for realtime geolocation from noisy microblog streams, unifying statistical hashtag segmentation, part-of-speech-driven proper-noun detection, dependency parsing around disaster lexicons, lightweight named-entity recognition, and gazetteer-grounded disambiguation to infer locations directly from text rather than sparse geotags. The approach operationalizes information extraction under streaming constraints, emphasizing low-latency NLP components and efficient validation against geographic knowledge bases to support situational awareness during emergencies. In head to head comparisons with widely used NER toolkits, the system attains strong F1 while being engineered for orders-of-magnitude faster throughput, enabling deployment in live crisis informatics settings. A production map interface demonstrates end-to-end AI functionality ingest, inference, and visualization--surfacing locational signals at scale for floods, outbreaks, and other fastmoving events. By prioritizing robustness to informal text and streaming efficiency, GeoSense-AI illustrates how domain-tuned NLP and knowledge grounding can elevate emergency response beyond conventional geo-tag reliance.
Fonte: arXiv cs.CL
Vision • Score 95
Statistical laws and linguistics inform meaning in naturalistic and fictional conversation
arXiv:2512.18072v1 Announce Type: new
Abstract: Conversation is a cornerstone of social connection and is linked to well-being outcomes. Conversations vary widely in type with some portion generating complex, dynamic stories. One approach to studying how conversations unfold in time is through statistical patterns such as Heaps' law, which holds that vocabulary size scales with document length. Little work on Heaps's law has looked at conversation and considered how language features impact scaling. We measure Heaps' law for conversations recorded in two distinct mediums: 1. Strangers brought together on video chat and 2. Fictional characters in movies. We find that scaling of vocabulary size differs by parts of speech. We discuss these findings through behavioral and linguistic frameworks.
Fonte: arXiv cs.CL
NLP/LLMs • Score 95
Ensinando e Criticando a Conceituação e Operacionalização em NLP
Pesquisadores de NLP frequentemente invocam conceitos abstratos como 'interpretabilidade', 'viés', 'raciocínio' e 'estereótipos' sem defini-los. Este artigo descreve um seminário criado para estudantes explorarem questões de conceituação e operacionalização, com uma lista de leitura interdisciplinar e ênfase em discussão e crítica.
Fonte: arXiv cs.CL
MLOps/Systems • Score 89
Misturas de cadeias de Markov variacionais com seleção automática de componentes
A modelagem de estados de Markov ganhou popularidade em diversos campos científicos, pois reduz conjuntos de dados de séries temporais complexas em transições entre poucos estados. Este artigo propõe um modelo de dados de séries temporais usando uma mistura de cadeias de Markov, determinando automaticamente o número de componentes da mistura com o algoritmo variacional de expectativa-maximização.
Fonte: arXiv stat.ML
NLP/LLMs • Score 95
Rumo ao Desaprendizado que Preserva o Raciocínio em Modelos de Linguagem Grande Multimodal
O desaprendizado de máquinas visa apagar dados solicitados de modelos treinados sem re-treinamento completo. Para Modelos de Linguagem Grande Multimodal com Raciocínio (RMLLMs), isso é desafiador, pois etapas intermediárias podem vazar informações sensíveis. Apresentamos o RMLLMU-Bench, o primeiro benchmark para desaprendizado de RMLLM que avalia o vazamento de raciocínio e a retenção de raciocínio.
Fonte: arXiv cs.CL
MLOps/Systems • Score 93
Comparando Modelos Dinâmicos Através do Alinhamento de Campos Vetoriais Difeomórficos
Modelos de sistemas dinâmicos, como redes neurais recorrentes (RNNs), são cada vez mais populares na neurociência teórica para geração de hipóteses e análise de dados. Avaliar a dinâmica nesses modelos é crucial para entender seus mecanismos generativos aprendidos, mas enfrenta desafios significativos relacionados à comparação de dinâmicas e identificação de motivos importantes em modelos não lineares de alta dimensão.
Fonte: arXiv cs.LG
NLP/LLMs • Score 95
Does It Tie Out? Towards Autonomous Legal Agents in Venture Capital
arXiv:2512.18658v1 Announce Type: new
Abstract: Before closing venture capital financing rounds, lawyers conduct diligence that includes tying out the capitalization table: verifying that every security (for example, shares, options, warrants) and issuance term (for example, vesting schedules, acceleration triggers, transfer restrictions) is supported by large sets of underlying legal documentation. While LLMs continue to improve on legal benchmarks, specialized legal workflows, such as capitalization tie-out, remain out of reach even for strong agentic systems. The task requires multi-document reasoning, strict evidence traceability, and deterministic outputs that current approaches fail to reliably deliver. We characterize capitalization tie-out as an instance of a real-world benchmark for legal AI, analyze and compare the performance of existing agentic systems, and propose a world model architecture toward tie-out automation-and more broadly as a foundation for applied legal intelligence.
Fonte: arXiv cs.CL
NLP/LLMs • Score 95
Training LLMs with LogicReward for Faithful and Rigorous Reasoning
arXiv:2512.18196v1 Announce Type: new
Abstract: Although LLMs exhibit strong reasoning capabilities, existing training methods largely depend on outcome-based feedback, which can produce correct answers with flawed reasoning. Prior work introduces supervision on intermediate steps but still lacks guarantees of logical soundness, which is crucial in high-stakes scenarios where logical consistency is paramount. To address this, we propose LogicReward, a novel reward system that guides model training by enforcing step-level logical correctness with a theorem prover. We further introduce Autoformalization with Soft Unification, which reduces natural language ambiguity and improves formalization quality, enabling more effective use of the theorem prover. An 8B model trained on data constructed with LogicReward surpasses GPT-4o and o4-mini by 11.6\% and 2\% on natural language inference and logical reasoning tasks with simple training procedures. Further analysis shows that LogicReward enhances reasoning faithfulness, improves generalizability to unseen tasks such as math and commonsense reasoning, and provides a reliable reward signal even without ground-truth labels. We will release all data and code at https://llm-symbol.github.io/LogicReward.
Fonte: arXiv cs.CL
MLOps/Systems • Score 96
Mecanismos de Memória Dependentes de Modalidade em Computação Neuromórfica Cross-Modal
As redes neurais spiking (SNNs) com memória prometem computação neuromórfica energeticamente eficiente, mas sua generalização entre modalidades sensoriais permanece inexplorada. Apresentamos o primeiro estudo abrangente de ablação cross-modal dos mecanismos de memória em SNNs, avaliando redes de Hopfield, Redes Recorrentes Gated Hierárquicas (HGRNs) e aprendizado contrastivo supervisionado (SCL) em conjuntos de dados neuromórficos visuais (N-MNIST) e auditivos (SHD).
Fonte: arXiv cs.LG
NLP/LLMs • Score 95
A Comparative Study of Light-weight Language Models for PII Masking and their Deployment for Real Conversational Texts
arXiv:2512.18608v1 Announce Type: new
Abstract: Automated masking of Personally Identifiable Information (PII) is critical for privacy-preserving conversational systems. While current frontier large language models demonstrate strong PII masking capabilities, concerns about data handling and computational costs motivate exploration of whether lightweight models can achieve comparable performance. We compare encoder-decoder and decoder-only architectures by fine-tuning T5-small and Mistral-Instruct-v0.3 on English datasets constructed from the AI4Privacy benchmark. We create different dataset variants to study label standardization and PII representation, covering 24 standardized PII categories and higher-granularity settings. Evaluation using entity-level and character-level metrics, type accuracy, and exact match shows that both lightweight models achieve performance comparable to frontier LLMs for PII masking tasks. Label normalization consistently improves performance across architectures. Mistral achieves higher F1 and recall with greater robustness across PII types but incurs significantly higher generation latency. T5, while less robust in conversational text, offers more controllable structured outputs and lower inference cost, motivating its use in a real-time Discord bot for real-world PII redaction. Evaluation on live messages reveals performance degradation under informal inputs. These results clarify trade-offs between accuracy, robustness, and computational efficiency, demonstrating that lightweight models can provide effective PII masking while addressing data handling concerns associated with frontier LLMs.
Fonte: arXiv cs.CL
RL • Score 96
Inteligência Alinhada à Segurança Embutida via Embeddings de Alinhamento Interno Diferenciáveis
Apresentamos a Inteligência Alinhada à Segurança Embutida (ESAI), um framework teórico para aprendizado por reforço multi-agente que incorpora restrições de alinhamento diretamente nas representações internas dos agentes usando embeddings de alinhamento interno diferenciáveis. Este trabalho analisa condições de estabilidade e propriedades teóricas, posicionando o ESAI como uma contribuição conceitual para mecanismos de alinhamento diferenciáveis em sistemas multi-agente.
Fonte: arXiv cs.LG
NLP/LLMs • Score 96
Vibe Reasoning: Extraindo Capacidades Matemáticas de IA de Fronteira -- Um Estudo de Caso sobre o Problema 6 do IMO 2025
Apresentamos o Vibe Reasoning, um paradigma colaborativo entre humanos e IA para resolver problemas matemáticos complexos. Nossa principal percepção é que modelos de IA de fronteira já possuem o conhecimento necessário para resolver problemas desafiadores, mas não sabem como, o que ou quando aplicá-lo. Este trabalho demonstra essa abordagem através do Problema 6 do IMO 2025.
Fonte: arXiv cs.AI
NLP/LLMs • Score 96
Gabliteration: Modificação Adaptativa de Pesos Neurais Multi-Direcional para Alteração Comportamental Seletiva em Grandes Modelos de Linguagem
Apresentamos o Gabliteration, uma nova técnica de modificação de pesos neurais que avança além dos métodos tradicionais de abliteration, implementando projeções multi-direcionais adaptativas com seleção de camadas regularizada. Nossa abordagem supera limitações fundamentais dos métodos existentes, mantendo a qualidade do modelo ao modificar padrões comportamentais específicos.
Fonte: arXiv cs.AI
NLP/LLMs • Score 96
Raciocínio Híbrido Aumentado por Ferramentas com Destilação para Resolução Bilingue de Problemas Matemáticos
A resolução bilíngue de problemas matemáticos requer uma ligação clara entre raciocínio linguístico e cálculo simbólico. Este artigo apresenta o HERALD (Hybrid Ensemble Reasoning with Adaptive Learning and Distillation), um framework que integra raciocínio e cálculo utilizando NuminaMath-7B-TIR, GPT-4o e Mistral-7B, oferecendo uma solução prática para raciocínio matemático multilíngue com melhor precisão e clareza.
Fonte: arXiv cs.AI
NLP/LLMs • Score 93
Conceitos abstratos de LLM podem melhorar o desempenho de SLM?
Modelos de linguagem grandes (LLMs) se destacam em diversas tarefas, mas sua implementação em dispositivos com recursos limitados continua desafiadora. Investigamos a transferibilidade de conceitos de alto nível extraídos de modelos maiores para modelos de linguagem menores (SLM) durante a inferência, demonstrando melhorias de desempenho em uma ampla gama de tarefas.
Fonte: arXiv cs.AI
NLP/LLMs • Score 96
Population-Evolve: um Método de Amostragem Paralela e Evolutiva para Raciocínio Matemático em LLMs
O escalonamento em tempo de teste surgiu como uma direção promissora para aprimorar as capacidades de raciocínio de Large Language Models nos últimos anos. Neste trabalho, propomos o Population-Evolve, um método livre de treinamento inspirado em Algoritmos Genéticos para otimizar o raciocínio em LLMs, mantendo uma população dinâmica de soluções candidatas.
Fonte: arXiv cs.AI
NLP/LLMs • Score 96
IntelliCode: Um Sistema de Tutoria com LLM Multi-Agente e Modelagem Centralizada do Aprendiz
Os tutores baseados em LLM geralmente são assistentes de turno único que não possuem representações persistentes do conhecimento do aprendiz, dificultando o suporte pedagógico a longo prazo. Apresentamos o IntelliCode, um sistema de tutoria LLM multi-agente que integra estimativas de domínio, equívocos, cronogramas de revisão e sinais de engajamento em um estado de aprendiz centralizado e versionado.
Fonte: arXiv cs.AI
NLP/LLMs • Score 96
Vox Deorum: Uma Arquitetura Híbrida de LLM para IA em Jogos 4X / de Grande Estratégia -- Lições de Civilization V
A capacidade dos Large Language Models de raciocinar em linguagem natural os torna promissores para jogos 4X e de grande estratégia, facilitando interações mais naturais entre humanos e IA. No entanto, a complexidade desses jogos e fatores como latência e custo podem dificultar a implementação real dos LLMs. Apresentamos Vox Deorum, uma arquitetura híbrida LLM+X, validada por meio de 2.327 jogos completos.
Fonte: arXiv cs.AI
Vision • Score 96
Detecção de Drift de Saída Baseada em Agentes para Previsão de Resposta ao Câncer de Mama em um Sistema de Suporte à Decisão Clínica Multissite
Os sistemas modernos de suporte à decisão clínica podem atender simultaneamente várias instituições independentes de imagem médica, mas seu desempenho preditivo pode se degradar entre os sites devido a variações nas populações de pacientes, hardware de imagem e protocolos de aquisição. Propomos um framework baseado em agentes para detectar drift e avaliar sua gravidade em sistemas de IA clínica multissite.
Fonte: arXiv cs.AI
NLP/LLMs • Score 96
Parceria Inteligente Homem-Máquina para Manufatura: Aprimorando o Planejamento de Armazém através de Grafos de Conhecimento Baseados em Simulação e Colaboração de LLM
Os planejadores de manufatura enfrentam desafios operacionais complexos que exigem colaboração entre a expertise humana e sistemas inteligentes. Nosso framework integra Grafos de Conhecimento e agentes baseados em Large Language Models (LLMs) para capacitar profissionais da manufatura, permitindo interações em linguagem natural com dados operacionais, melhorando a análise e a tomada de decisões.
Fonte: arXiv cs.AI
NLP/LLMs • Score 96
MSC-180: Um Benchmark para Prova Formal Automatizada de Teoremas a partir da Classificação de Assuntos Matemáticos
O Automated Theorem Proving (ATP) é uma direção de pesquisa central em inteligência artificial para alcançar raciocínio formal e verificação. Propomos o MSC-180, um benchmark baseado na classificação de assuntos matemáticos MSC2020, que compreende 180 problemas de verificação formal, abrangendo níveis de graduação e pós-graduação, para avaliar e impulsionar o desenvolvimento de sistemas de IA com habilidades genuínas de raciocínio matemático.
Fonte: arXiv cs.AI
Vision • Score 96
Aprendizado de Cláusulas Direcionado por Conflito com Heurísticas VSIDS para Layout Discreto de Instalações
Este artigo estuda o uso de Aprendizado de Cláusulas Direcionado por Conflito (CDCL) com heurísticas VSIDS como um motor computacional para problemas de layout discreto de instalações. O problema de layout é modelado como um problema de atribuição combinatória com uma estrutura lógica densa, resultante de restrições de adjacência, separação e disponibilidade de slots.
Fonte: arXiv cs.AI
Vision • Score 95
Data-driven particle dynamics: Structure-preserving coarse-graining for emergent behavior in non-equilibrium systems
arXiv:2508.12569v2 Announce Type: replace-cross
Abstract: Multiscale systems are ubiquitous in science and technology, but are notoriously challenging to simulate as short spatiotemporal scales must be appropriately linked to emergent bulk physics. When expensive high-dimensional dynamical systems are coarse-grained into low-dimensional models, the entropic loss of information leads to emergent physics which are dissipative, history-dependent, and stochastic. To machine learn coarse-grained dynamics from time-series observations of particle trajectories, we propose a framework using the metriplectic bracket formalism that preserves these properties by construction; most notably, the framework guarantees discrete notions of the first and second laws of thermodynamics, conservation of momentum, and a discrete fluctuation-dissipation balance crucial for capturing non-equilibrium statistics. We introduce the mathematical framework abstractly before specializing to a particle discretization. As labels are generally unavailable for entropic state variables, we introduce a novel self-supervised learning strategy to identify emergent structural variables. We validate the method on benchmark systems and demonstrate its utility on two challenging examples: (1) coarse-graining star polymers at challenging levels of coarse-graining while preserving non-equilibrium statistics, and (2) learning models from high-speed video of colloidal suspensions that capture coupling between local rearrangement events and emergent stochastic dynamics. We provide open-source implementations in both PyTorch and LAMMPS, enabling large-scale inference and extensibility to diverse particle-based systems.
Fonte: arXiv stat.ML
Vision • Score 96
Mapas auto-organizáveis para avaliação da qualidade da água em reservatórios e lagos: Uma revisão sistemática da literatura
A qualidade da água sustentável é fundamental para o equilíbrio ecológico e a segurança hídrica. Esta revisão examina a aplicação do Self-Organizing Map (SOM), uma técnica de IA não supervisionada, na avaliação da qualidade da água, abordando seleção de parâmetros, estratégias de amostragem e abordagens de agrupamento.
Fonte: arXiv cs.LG
NLP/LLMs • Score 95
MemEvolve: Meta-Evolution of Agent Memory Systems
arXiv:2512.18746v1 Announce Type: new
Abstract: Self-evolving memory systems are unprecedentedly reshaping the evolutionary paradigm of large language model (LLM)-based agents. Prior work has predominantly relied on manually engineered memory architectures to store trajectories, distill experience, and synthesize reusable tools, enabling agents to evolve on the fly within environment interactions. However, this paradigm is fundamentally constrained by the staticity of the memory system itself: while memory facilitates agent-level evolving, the underlying memory architecture cannot be meta-adapted to diverse task contexts. To address this gap, we propose MemEvolve, a meta-evolutionary framework that jointly evolves agents' experiential knowledge and their memory architecture, allowing agent systems not only to accumulate experience but also to progressively refine how they learn from it. To ground MemEvolve in prior research and foster openness in future self-evolving systems, we introduce EvolveLab, a unified self-evolving memory codebase that distills twelve representative memory systems into a modular design space (encode, store, retrieve, manage), providing both a standardized implementation substrate and a fair experimental arena. Extensive evaluations on four challenging agentic benchmarks demonstrate that MemEvolve achieves (I) substantial performance gains, improving frameworks such as SmolAgent and Flash-Searcher by up to $17.06\%$; and (II) strong cross-task and cross-LLM generalization, designing memory architectures that transfer effectively across diverse benchmarks and backbone models.
Fonte: arXiv cs.CL
RL • Score 96
Unificando Aprendizado por Reforço Causal: Revisão, Taxonomia, Algoritmos e Aplicações
Integrar inferência causal (CI) com aprendizado por reforço (RL) se tornou um paradigma poderoso para abordar limitações críticas no RL clássico, como baixa explicabilidade e falta de robustez. Este trabalho revisa avanços recentes na interseção entre CI e RL, categorizando abordagens existentes e discutindo desafios, sucessos empíricos e direções futuras de pesquisa.
Fonte: arXiv cs.AI
Vision • Score 96
Um Conjunto de Dados e Benchmarks para Detecção de Fibrilação Atrial a partir de Eletrocardiogramas de Pacientes em Unidades de Terapia Intensiva
Objetivo: A fibrilação atrial (AF) é a arritmia cardíaca mais comum entre pacientes em unidades de terapia intensiva (UTI) e pode causar efeitos adversos à saúde. Neste estudo, publicamos um conjunto de dados rotulado da UTI e benchmarks para detecção de AF, comparando modelos de machine learning em três abordagens de inteligência artificial (IA) baseadas em dados.
Fonte: arXiv cs.LG
MLOps/Systems • Score 92
Uma Perspectiva de Otimização Riemanniana do Método Gauss-Newton para Redes Neurais Feedforward
Neste trabalho, estabelecemos limites de convergência não assintóticos para o método Gauss-Newton no treinamento de redes neurais com ativações suaves. No regime subparametrizado, o fluxo de gradiente Gauss-Newton induz um fluxo de gradiente Riemanniano em uma subvariedade embutida de baixa dimensão do espaço de funções.
Fonte: arXiv stat.ML
RL • Score 96
Monitoramento da Monitorabilidade
A observabilidade na tomada de decisões de sistemas de IA modernos pode ser necessária para implantar com segurança agentes cada vez mais capazes. Monitorar a cadeia de pensamento (CoT) dos modelos de raciocínio atuais tem se mostrado eficaz na detecção de comportamentos inadequados. No entanto, essa 'monitorabilidade' pode ser frágil sob diferentes procedimentos de treinamento e fontes de dados.
Fonte: arXiv cs.AI
RL • Score 93
A Geometria da Abstração: Aprendizado Contínuo via Quotienting Recursivo
Sistemas de aprendizado contínuo que operam em espaços de dimensão fixa enfrentam uma barreira geométrica fundamental: o problema do manifold plano. Neste trabalho, propomos uma resolução geométrica para esse paradoxo com base na Contração Métrica Recursiva, formalizando a abstração como uma deformação topológica.
Fonte: arXiv cs.LG
RL • Score 95
From Natural Language to Control Signals: A Conceptual Framework for Semantic Channel Finding in Complex Experimental Infrastructure
arXiv:2512.18779v1 Announce Type: new
Abstract: Modern experimental platforms such as particle accelerators, fusion devices, telescopes, and industrial process control systems expose tens to hundreds of thousands of control and diagnostic channels accumulated over decades of evolution. Operators and AI systems rely on informal expert knowledge, inconsistent naming conventions, and fragmented documentation to locate signals for monitoring, troubleshooting, and automated control, creating a persistent bottleneck for reliability, scalability, and language-model-driven interfaces. We formalize semantic channel finding-mapping natural-language intent to concrete control-system signals-as a general problem in complex experimental infrastructure, and introduce a four-paradigm framework to guide architecture selection across facility-specific data regimes. The paradigms span (i) direct in-context lookup over curated channel dictionaries, (ii) constrained hierarchical navigation through structured trees, (iii) interactive agent exploration using iterative reasoning and tool-based database queries, and (iv) ontology-grounded semantic search that decouples channel meaning from facility-specific naming conventions. We demonstrate each paradigm through proof-of-concept implementations at four operational facilities spanning two orders of magnitude in scale-from compact free-electron lasers to large synchrotron light sources-and diverse control-system architectures, from clean hierarchies to legacy environments. These implementations achieve 90-97% accuracy on expert-curated operational queries.
Fonte: arXiv cs.CL
RL • Score 92
Algoritmo Garantido de Regret a Qualquer Momento para Controle de Sistemas Lineares Quadráticos
Propomos um algoritmo computacionalmente eficiente que alcança um regret a qualquer momento de ordem $ extmath{O}( extmath{ extsqrt{t}})$, com dependência explícita nas dimensões do sistema e na solução da Equação de Riccati Algébrica Discreta (DARE). Nossa abordagem utiliza uma regularização adequadamente ajustada e uma estimativa inicial suficientemente precisa para construir elipsóides de confiança para o design de controle.
Fonte: arXiv stat.ML
NLP/LLMs • Score 96
DeliveryBench: Agentes Podem Lucrar no Mundo Real?
arXiv:2512.19234v1 Tipo de Anúncio: novo. Resumo: LLMs e VLMs estão sendo cada vez mais utilizados como agentes incorporados, mas os benchmarks existentes se concentram em tarefas simples de curto prazo e têm dificuldade em capturar as ricas restrições realistas que moldam a tomada de decisão no mundo real. Para fechar essa lacuna, propomos o DeliveryBench, um benchmark incorporado em escala de cidade baseado na profissão real de entrega de alimentos.
Fonte: arXiv cs.AI
NLP/LLMs • Score 95
Evaluating the Challenges of LLMs in Real-world Medical Follow-up: A Comparative Study and An Optimized Framework
arXiv:2512.18999v1 Announce Type: new
Abstract: When applied directly in an end-to-end manner to medical follow-up tasks, Large Language Models (LLMs) often suffer from uncontrolled dialog flow and inaccurate information extraction due to the complexity of follow-up forms. To address this limitation, we designed and compared two follow-up chatbot systems: an end-to-end LLM-based system (control group) and a modular pipeline with structured process control (experimental group). Experimental results show that while the end-to-end approach frequently fails on lengthy and complex forms, our modular method-built on task decomposition, semantic clustering, and flow management-substantially improves dialog stability and extraction accuracy. Moreover, it reduces the number of dialogue turns by 46.73% and lowers token consumption by 80% to 87.5%. These findings highlight the necessity of integrating external control mechanisms when deploying LLMs in high-stakes medical follow-up scenarios.
Fonte: arXiv cs.CL
NLP/LLMs • Score 95
O Número de Condição como um Proxy Invariante de Escala para Codificação de Informação em Unidades Neurais
Este artigo explora a relação entre o número de condição do tensor de pesos de uma rede neural e a extensão da informação codificada pela unidade de processamento associada, sob a perspectiva da teoria da informação. Argumenta-se que um número de condição elevado pode indicar que a unidade aprendeu a amplificar e comprimir informações de forma seletiva.
Fonte: arXiv stat.ML
NLP/LLMs • Score 95
Supplementary Resources and Analysis for Automatic Speech Recognition Systems Trained on the Loquacious Dataset
arXiv:2512.17915v1 Announce Type: new
Abstract: The recently published Loquacious dataset aims to be a replacement for established English automatic speech recognition (ASR) datasets such as LibriSpeech or TED-Lium. The main goal of the Loquacious dataset is to provide properly defined training and test partitions across many acoustic and language domains, with an open license suitable for both academia and industry. To further promote the benchmarking and usability of this new dataset, we present additional resources in the form of n-gram language models (LMs), a grapheme-to-phoneme (G2P) model and pronunciation lexica, with open and public access. Utilizing those additional resources we show experimental results across a wide range of ASR architectures with different label units and topologies. Our initial experimental results indicate that the Loquacious dataset offers a valuable study case for a variety of common challenges in ASR.
Fonte: arXiv cs.CL
NLP/LLMs • Score 95
Separating Constraint Compliance from Semantic Accuracy: A Novel Benchmark for Evaluating Instruction-Following Under Compression
arXiv:2512.17920v1 Announce Type: new
Abstract: Large language models (LLMs) exhibit degraded performance under prompt compression, but the mechanisms remain poorly understood. We introduce the Compression-Decay Comprehension Test (CDCT), a benchmark that independently measures constraint compliance (CC) and semantic accuracy (SA) across compression levels. We evaluate 9 frontier LLMs across 8 concepts using 5 compression levels from extreme (c=0.0, ~2 words) to none (c=1.0, ~135 words). A three-judge LLM jury achieves almost perfect inter-rater agreement on CC (Fleiss' \k{appa}=0.90).
We observe a universal U-curve pattern in constraint compliance (97.2% prevalence), with violations peaking at medium compression (c=0.5, ~27 words). Counterintuitively, models perform better at extreme compression than medium lengths. The dimensions are statistically orthogonal (r=0.193, p=0.084), with constraint effects 2.9x larger than semantic effects.
Experimental validation via RLHF ablation confirms our constraint salience hypothesis: removing "helpfulness" signals improves CC by 598% on average (71/72 trials, p<0.001), with 79% achieving perfect compliance. This demonstrates that RLHF-trained helpfulness behaviors are the dominant cause of constraint violations at medium compression. Reasoning models outperform efficient models by 27.5% (Cohen's d=0.96).
Our findings reveal a fundamental tension between RLHF alignment and instruction-following, providing actionable guidelines for improving deployed systems.
Fonte: arXiv cs.CL
NLP/LLMs • Score 96
Geração de Regras Programáticas para Detecção de Falsificação de Documentos Usando Modelos de Linguagem de Grande Escala
A falsificação de documentos representa uma ameaça crescente a processos legais, econômicos e governamentais, exigindo mecanismos de verificação cada vez mais sofisticados. Este trabalho investiga como modelos de linguagem de grande escala (LLMs) podem ser adaptados para gerar verificações de plausibilidade baseadas em regras para detecção de falsificações, utilizando recursos de hardware limitados.
Fonte: arXiv cs.AI
NLP/LLMs • Score 96
Grandes Modelos de Linguagem como Filtros Bayesianos Descontados
Os Grandes Modelos de Linguagem (LLMs) demonstram forte generalização em poucos exemplos através do aprendizado em contexto, mas seu raciocínio em ambientes dinâmicos e estocásticos permanece opaco. Introduzimos um framework de filtragem bayesiana para avaliar a inferência online em LLMs, revelando como as atualizações de crença se comportam como filtros de esquecimento exponencial.
Fonte: arXiv cs.AI
NLP/LLMs • Score 96
Observador, Não Jogador: Simulando a Teoria da Mente em LLMs através da Observação de Jogos
Apresentamos um framework interativo para avaliar se modelos de linguagem grandes (LLMs) exibem um verdadeiro 'entendimento' em um ambiente simples, mas estratégico. Utilizando o jogo Pedra-Papel-Tesoura (RPS) como exemplo, nosso sistema posiciona o LLM como um Observador, cuja tarefa é identificar as estratégias em jogo e articular o raciocínio por trás desse julgamento.
Fonte: arXiv cs.AI
RL • Score 93
ORPR: Um Modelo de Aprendizado Guiado por OR para Gestão de Estoque com Pré-treinamento e Reforço
À medida que a busca por sinergia entre Inteligência Artificial (AI) e Pesquisa Operacional (OR) avança na gestão de sistemas de estoque complexos, um desafio crítico permanece: como reconciliar efetivamente a percepção adaptativa da AI com o rigor estrutural da OR. Propomos um novo framework 'Pré-treinamento e Reforço' guiado por OR.
Fonte: arXiv cs.AI
RL • Score 96
Podemos Testar Teorias da Consciência em IA? Ablations, Marcadores e Robustez
A busca por indicadores confiáveis de consciência se fragmentou em campos teóricos concorrentes (Global Workspace Theory (GWT), Integrated Information Theory (IIT) e Higher-Order Theories (HOT)), cada um propondo assinaturas neurais distintas. Adotamos uma abordagem de neuro-fenomenologia sintética, construindo agentes artificiais para testar as consequências funcionais dessas teorias através de ablações arquitetônicas precisas. Relatamos dissociações que sugerem que essas teorias descrevem camadas funcionais complementares.
Fonte: arXiv cs.AI
Vision • Score 96
Rede Bayesiana Multimodal para Avaliação Robusta de Vítimas em Triagem Autônoma
Incidentes de Múltiplas Vítimas podem sobrecarregar sistemas médicos de emergência, e atrasos ou erros na avaliação das vítimas podem resultar em mortes evitáveis. Apresentamos um framework de suporte à decisão que combina saídas de múltiplos modelos de computer vision, estimando sinais de hemorragia severa, dificuldade respiratória, alerta físico ou trauma visível, em uma rede Bayesiana construída inteiramente a partir de regras definidas por especialistas.
Fonte: arXiv cs.AI
NLP/LLMs • Score 96
ASTIF: Integração Semântica-Temporal Adaptativa para Previsão de Preços de Criptomoedas
A previsão de séries temporais financeiras é um desafio de fusão de informações, mas a maioria dos modelos existentes depende de arquiteturas estáticas que têm dificuldade em integrar fontes de conhecimento heterogêneas. Propomos o ASTIF, um sistema híbrido inteligente que adapta sua estratégia de previsão em tempo real através de meta-aprendizado baseado em confiança, integrando componentes complementares para melhorar a precisão das previsões.
Fonte: arXiv cs.AI
NLP/LLMs • Score 96
Repensando a Inteligência Multi-Agente Através da Lente de Redes de Pequeno Mundo
Modelos de linguagem grandes (LLMs) possibilitaram sistemas multi-agente (MAS) onde múltiplos agentes argumentam, criticam e coordenam para resolver tarefas complexas, tornando a topologia de comunicação uma escolha de design fundamental. Neste trabalho, revisitamos a teoria clássica sobre redes de pequeno mundo (SW) e investigamos como a conectividade SW pode ser utilizada como um princípio de design para MAS.
Fonte: arXiv cs.AI
NLP/LLMs • Score 96
Sophia: Um Framework de Agente Persistente de Vida Artificial
O desenvolvimento de LLMs elevou os agentes de IA de ferramentas específicas para entidades de tomada de decisão de longa duração. No entanto, a maioria das arquiteturas permanece estática e reativa, limitadas a cenários definidos manualmente. Propomos um terceiro estrato, o Sistema 3, que supervisiona a identidade narrativa do agente e a adaptação a longo prazo, culminando em Sophia, um wrapper de 'Agente Persistente' que integra um ciclo contínuo de autoaperfeiçoamento.
Fonte: arXiv cs.AI
Vision • Score 93
Os Salmões Mortos da Interpretabilidade em IA
Neste estudo de neurociência, os autores colocaram um salmão morto em um scanner de MRI e mostraram imagens de humanos em situações sociais, revelando artefatos de 'salmão morto' em análises de IA. Este trabalho propõe uma reinterpretação estatística-causal, tratando explicações de sistemas computacionais como parâmetros de um modelo estatístico, enfatizando a importância de testar hipóteses alternativas.
Fonte: arXiv cs.AI
NLP/LLMs • Score 92
From Scratch to Fine-Tuned: A Comparative Study of Transformer Training Strategies for Legal Machine Translation
arXiv:2512.18593v1 Announce Type: new
Abstract: In multilingual nations like India, access to legal information is often hindered by language barriers, as much of the legal and judicial documentation remains in English. Legal Machine Translation (L-MT) offers a scalable solution to this challenge by enabling accurate and accessible translations of legal documents. This paper presents our work for the JUST-NLP 2025 Legal MT shared task, focusing on English-Hindi translation using Transformer-based approaches. We experiment with 2 complementary strategies, fine-tuning a pre-trained OPUS-MT model for domain-specific adaptation and training a Transformer model from scratch using the provided legal corpus. Performance is evaluated using standard MT metrics, including SacreBLEU, chrF++, TER, ROUGE, BERTScore, METEOR, and COMET. Our fine-tuned OPUS-MT model achieves a SacreBLEU score of 46.03, significantly outperforming both baseline and from-scratch models. The results highlight the effectiveness of domain adaptation in enhancing translation quality and demonstrate the potential of L-MT systems to improve access to justice and legal transparency in multilingual contexts.
Fonte: arXiv cs.CL
RL • Score 96
FairExpand: Justiça Individual em Grafos com Informações de Similaridade Parcial
A justiça individual, que exige que indivíduos semelhantes sejam tratados de forma semelhante por sistemas algorítmicos, é um princípio central em machine learning justo. Este trabalho apresenta o FairExpand, um framework flexível que promove a justiça individual em cenários de informações parciais, superando a limitação de métodos existentes que requerem informações de similaridade pré-definidas para todos os pares de nós.
Fonte: arXiv cs.LG
NLP/LLMs • Score 95
Rumo a Agentes Eficientes: Um Co-Design da Arquitetura de Inferência e do Sistema
O rápido desenvolvimento de agentes baseados em large language models (LLMs) abriu novas possibilidades para raciocínio autônomo em múltiplas interações e tomada de decisão com ferramentas. No entanto, sua implementação no mundo real é dificultada por ineficiências severas que surgem não da inferência isolada do modelo, mas da latência sistêmica acumulada ao longo dos ciclos de raciocínio, crescimento de contexto e interações heterogêneas com ferramentas.
Fonte: arXiv cs.CL
NLP/LLMs • Score 95
A Benchmark and Agentic Framework for Omni-Modal Reasoning and Tool Use in Long Videos
arXiv:2512.16978v1 Announce Type: new
Abstract: Long-form multimodal video understanding requires integrating vision, speech, and ambient audio with coherent long-range reasoning. Existing benchmarks emphasize either temporal length or multimodal richness, but rarely both and while some incorporate open-ended questions and advanced metrics, they mostly rely on single-score accuracy, obscuring failure modes. We introduce LongShOTBench, a diagnostic benchmark with open-ended, intent-driven questions; single- and multi-turn dialogues; and tasks requiring multimodal reasoning and agentic tool use across video, audio, and speech. Each item includes a reference answer and graded rubric for interpretable, and traceable evaluation. LongShOTBench is produced via a scalable, human-validated pipeline to ensure coverage and reproducibility. All samples in our LongShOTBench are human-verified and corrected. Furthermore, we present LongShOTAgent, an agentic system that analyzes long videos via preprocessing, search, and iterative refinement. On LongShOTBench, state-of-the-art MLLMs show large gaps: Gemini-2.5-Flash achieves 52.95%, open-source models remain below 30%, and LongShOTAgent attains 44.66%. These results underscore the difficulty of real-world long-form video understanding. LongShOTBench provides a practical, reproducible foundation for evaluating and improving MLLMs. All resources are available on GitHub: https://github.com/mbzuai-oryx/longshot.
Fonte: arXiv cs.CV
NLP/LLMs • Score 95
Towards Safer Chatbots: Automated Policy Compliance Evaluation of Custom GPTs
arXiv:2502.01436v3 Announce Type: replace
Abstract: User-configured chatbots built on top of large language models are increasingly available through centralized marketplaces such as OpenAI's GPT Store. While these platforms enforce usage policies intended to prevent harmful or inappropriate behavior, the scale and opacity of customized chatbots make systematic policy enforcement challenging. As a result, policy-violating chatbots continue to remain publicly accessible despite existing review processes. This paper presents a fully automated method for evaluating the compliance of Custom GPTs with its marketplace usage policy using black-box interaction. The method combines large-scale GPT discovery, policy-driven red-teaming prompts, and automated compliance assessment using an LLM-as-a-judge. We focus on three policy-relevant domains explicitly addressed in OpenAI's usage policies: Romantic, Cybersecurity, and Academic GPTs. We validate our compliance assessment component against a human-annotated ground-truth dataset, achieving an F1 score of 0.975 for binary policy violation detection. We then apply the method in a large-scale empirical study of 782 Custom GPTs retrieved from the GPT Store. The results show that 58.7% of the evaluated GPTs exhibit at least one policy-violating response, with substantial variation across policy domains. A comparison with the base models (GPT-4 and GPT-4o) indicates that most violations originate from model-level behavior, while customization tends to amplify these tendencies rather than create new failure modes. Our findings reveal limitations in current review mechanisms for user-configured chatbots and demonstrate the feasibility of scalable, behavior-based policy compliance evaluation.
Fonte: arXiv cs.CL
RL • Score 92
Computational analysis reveals historical trajectory of East-Polynesian lunar calendars
arXiv:2512.17525v1 Announce Type: cross
Abstract: We investigate a type of lunar calendar known as lists of the 'nights of the moon', found throughout East Polynesia, including Rapa Nui (Easter Island). Using computational methods, we analyzed the lexical and structural divergence of 49 calendric lists from all major archipelagos, each containing about 30 night names. Our results, presented as a rooted phylogenetic tree, show a clear split into two main groups: one including lists from Rapa Nui, Mangareva, and the Marquesas; the other comprising lists from New Zealand, Hawaii, the Cook Islands, the Austral Islands, Tahiti, and the Tuamotu. This pattern aligns with a recent alternative classification of East Polynesian languages into 'Distal' (Marquesan, Mangarevan, Rapanui) and 'Proximal' (Maori, Hawaiian, Tahitian, etc.) subgroups. Since both language and lunar calendars are symbolic systems passed down and changed within communities - and given the geographic isolation of many archipelagos - we interpret this correspondence as evidence that the early divergence of East Polynesian lunar calendars mirrors early population movements and language splits in the region.
Fonte: arXiv cs.CL
MLOps/Systems • Score 89
Modelagem generativa de distribuições de probabilidade condicionais nos conjuntos de nível de variáveis coletivas
Neste artigo, estudamos a modelagem generativa das distribuições de probabilidade condicionais de uma distribuição de probabilidade $
u$ em $ extbf{R}^d$, representada por dados. Propomos uma abordagem de aprendizado geral e eficiente que aprende modelos generativos em diferentes conjuntos de nível de $
u$ simultaneamente, melhorando a qualidade do aprendizado em regiões de baixa probabilidade.
Fonte: arXiv stat.ML
MLOps/Systems • Score 95
Mapping the Podcast Ecosystem with the Structured Podcast Research Corpus
arXiv:2411.07892v2 Announce Type: replace
Abstract: Podcasts provide highly diverse content to a massive listener base through a unique on-demand modality. However, limited data has prevented large-scale computational analysis of the podcast ecosystem. To fill this gap, we introduce a massive dataset of over 1.1M podcast transcripts that is largely comprehensive of all English language podcasts available through public RSS feeds from May and June of 2020. This data is not limited to text, but rather includes audio features and speaker turns for a subset of 370K episodes, and speaker role inferences and other metadata for all 1.1M episodes. Using this data, we also conduct a foundational investigation into the content, structure, and responsiveness of this ecosystem. Together, our data and analyses open the door to continued computational research of this popular and impactful medium.
Fonte: arXiv cs.CL
NLP/LLMs • Score 95
LLM-as-a-qualitative-judge: automating error analysis in natural language generation
arXiv:2506.09147v4 Announce Type: replace
Abstract: Prompting large language models (LLMs) to evaluate generated text, known as LLM-as-a-judge, has become a standard evaluation approach in natural language generation (NLG), but is primarily used as a quantitative tool, i.e. with numerical scores as main outputs. In this work, we propose LLM-as-a-qualitative-judge, an LLM-based evaluation approach with the main output being a structured report of common issue types in the NLG system outputs. Our approach is targeted at providing developers with meaningful insights on what improvements can be done to a given NLG system and consists of two main steps, namely open-ended per-instance issue analysis and clustering of the discovered issues using an intuitive cumulative algorithm. We also introduce a strategy for evaluating the proposed approach, coupled with ~300 annotations of issues in instances from 12 NLG datasets. Our results show that instance-specific issues output by LLM-as-a-qualitative-judge match those annotated by humans in 2/3 cases, and that LLM-as-a-qualitative-judge is capable of producing error type reports resembling the reports composed by human annotators. We also demonstrate in a case study how the use of LLM-as-a-qualitative-judge can substantially improve NLG systems performance. Our code and data are publicly available at https://github.com/tunde-ajayi/llm-as-a-qualitative-judge.
Fonte: arXiv cs.CL
RL • Score 96
Quando o Raciocínio Encontra Suas Leis
arXiv:2512.17901v1 Tipo de Anúncio: novo. Este artigo apresenta as Leis do Raciocínio (LoRe), um framework unificado que caracteriza padrões intrínsecos de raciocínio em Large Reasoning Models (LRMs). Propomos a lei de computação e uma lei de precisão suplementar, introduzindo o LoRe-Bench para medir essas propriedades em modelos de raciocínio. Avaliações mostram que a maioria dos modelos apresenta monotonicidade razoável, mas carece de composicionalidade.
Fonte: arXiv cs.AI
NLP/LLMs • Score 96
AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens
arXiv:2512.17375v1 Announce Type: new
Abstract: Reward models and LLM-as-a-Judge systems are central to modern post-training pipelines such as RLHF, DPO, and RLAIF, where they provide scalar feedback and binary decisions that guide model selection and RL-based fine-tuning. We show that these judge systems exhibit a recurring vulnerability: short sequences of low-perplexity control tokens can flip many binary evaluations from correct ``No'' judgments to incorrect ``Yes'' judgments by steering the last-layer logit gap. These control tokens are patterns that a policy model could plausibly generate during post-training, and thus represent realistic reward-hacking risks rather than worst-case adversarial strings. Our method, AdvJudge-Zero, uses the model's next-token distribution and beam-search exploration to discover diverse control-token sequences from scratch, and our analysis shows that the induced hidden-state perturbations concentrate in a low-rank ``soft mode'' that is anti-aligned with the judge's refusal direction. Empirically, these tokens cause very high false positive rates when large open-weight and specialized judge models score incorrect answers on math and reasoning benchmarks. Finally, we show that LoRA-based adversarial training on small sets of control-token-augmented examples can markedly reduce these false positives while preserving evaluation quality.
Fonte: arXiv cs.LG
NLP/LLMs • Score 96
PAACE: Um Framework de Engenharia de Contexto Automatizado e Consciente de Planejamento
Modelos de Linguagem de Grande Escala (LLM) estão sendo cada vez mais utilizados em fluxos de trabalho complexos que envolvem planejamento, uso de ferramentas, reflexão e interação com sistemas de conhecimento externos. Este trabalho apresenta o PAACE, um framework unificado para otimizar o estado evolutivo de agentes LLM através de modelagem de relevância de próximas tarefas, análise de estrutura de planejamento, co-refinamento de instruções e compressão que preserva funções.
Fonte: arXiv cs.AI
NLP/LLMs • Score 95
Strategic Planning and Rationalizing on Trees Make LLMs Better Debaters
arXiv:2505.14886v2 Announce Type: replace
Abstract: Winning competitive debates requires sophisticated reasoning and argument skills. There are unique challenges in the competitive debate: (1) The time constraints force debaters to make strategic choices about which points to pursue rather than covering all possible arguments; (2) The persuasiveness of the debate relies on the back-and-forth interaction between arguments, which a single final game status cannot evaluate. To address these challenges, we propose TreeDebater, a novel debate framework that excels in competitive debate. We introduce two tree structures: the Rehearsal Tree and Debate Flow Tree. The Rehearsal Tree anticipates the attack and defenses to evaluate the strength of the claim, while the Debate Flow Tree tracks the debate status to identify the active actions. TreeDebater allocates its time budget among candidate actions and uses the speech time controller and feedback from the simulated audience to revise its statement. The human evaluation on both the stage-level and the debate-level comparison shows that our TreeDebater outperforms the state-of-the-art multi-agent debate system, with a +15.6% improvement in stage-level persuasiveness with DeepSeek and +10% debate-level opinion shift win. Further investigation shows that TreeDebater shows better strategies in limiting time to important debate actions, aligning with the strategies of human debate experts.
Fonte: arXiv cs.CL
NLP/LLMs • Score 95
Generating Completions for Broca's Aphasic Sentences Using Large Language Models
arXiv:2412.17669v2 Announce Type: replace
Abstract: Broca's aphasia is a type of aphasia characterized by non-fluent, effortful and agrammatic speech production with relatively good comprehension. Since traditional aphasia treatment methods are often time-consuming, labour-intensive, and do not reflect real-world conversations, applying natural language processing based approaches such as Large Language Models (LLMs) could potentially contribute to improving existing treatment approaches. To address this issue, we explore the use of sequence-to-sequence LLMs for completing Broca's aphasic sentences. We first generate synthetic Broca's aphasic data using a rule-based system designed to mirror the linguistic characteristics of Broca's aphasic speech. Using this synthetic data (without authentic aphasic samples), we then fine-tune four pre-trained LLMs on the task of completing agrammatic sentences. We evaluate our fine-tuned models on both synthetic and authentic Broca's aphasic data. We demonstrate LLMs' capability for reconstructing agrammatic sentences, with the models showing improved performance with longer input utterances. Our result highlights the LLMs' potential in advancing communication aids for individuals with Broca's aphasia and possibly other clinical populations.
Fonte: arXiv cs.CL
NLP/LLMs • Score 96
Large Language Models as Pok\'emon Battle Agents: Strategic Play and Content Generation
arXiv:2512.17308v1 Announce Type: new
Abstract: Strategic decision-making in Pok\'emon battles presents a unique testbed for evaluating large language models. Pok\'emon battles demand reasoning about type matchups, statistical trade-offs, and risk assessment, skills that mirror human strategic thinking. This work examines whether Large Language Models (LLMs) can serve as competent battle agents, capable of both making tactically sound decisions and generating novel, balanced game content. We developed a turn-based Pok\'emon battle system where LLMs select moves based on battle state rather than pre-programmed logic. The framework captures essential Pok\'emon mechanics: type effectiveness multipliers, stat-based damage calculations, and multi-Pok\'emon team management. Through systematic evaluation across multiple model architectures we measured win rates, decision latency, type-alignment accuracy, and token efficiency. These results suggest LLMs can function as dynamic game opponents without domain-specific training, offering a practical alternative to reinforcement learning for turn-based strategic games. The dual capability of tactical reasoning and content creation, positions LLMs as both players and designers, with implications for procedural generation and adaptive difficulty systems in interactive entertainment.
Fonte: arXiv cs.AI
NLP/LLMs • Score 96
Investigando a Inteligência Geral Científica de LLMs com Fluxos de Trabalho Alinhados a Cientistas
Apesar dos avanços em IA científica, falta um framework coerente para Inteligência Geral Científica (SGI) — a capacidade de conceber, investigar e raciocinar autonomamente em domínios científicos. Apresentamos uma definição operacional de SGI baseada no Modelo de Investigação Prática (PIM) e a operacionalizamos através de quatro tarefas alinhadas a cientistas: pesquisa profunda, geração de ideias, experimentos secos/molhados e raciocínio experimental.
Fonte: arXiv cs.AI
Vision • Score 95
Stakeholder Suite: A Unified AI Framework for Mapping Actors, Topics and Arguments in Public Debates
arXiv:2512.17347v1 Announce Type: new
Abstract: Public debates surrounding infrastructure and energy projects involve complex networks of stakeholders, arguments, and evolving narratives. Understanding these dynamics is crucial for anticipating controversies and informing engagement strategies, yet existing tools in media intelligence largely rely on descriptive analytics with limited transparency. This paper presents Stakeholder Suite, a framework deployed in operational contexts for mapping actors, topics, and arguments within public debates. The system combines actor detection, topic modeling, argument extraction and stance classification in a unified pipeline. Tested on multiple energy infrastructure projects as a case study, the approach delivers fine-grained, source-grounded insights while remaining adaptable to diverse domains. The framework achieves strong retrieval precision and stance accuracy, producing arguments judged relevant in 75% of pilot use cases. Beyond quantitative metrics, the tool has proven effective for operational use: helping project teams visualize networks of influence, identify emerging controversies, and support evidence-based decision-making.
Fonte: arXiv cs.CL
NLP/LLMs • Score 95
DEER: A Comprehensive and Reliable Benchmark for Deep-Research Expert Reports
arXiv:2512.17776v1 Announce Type: new
Abstract: As large language models (LLMs) advance, deep research systems can generate expert-level reports via multi-step reasoning and evidence-based synthesis, but evaluating such reports remains challenging. Existing benchmarks often lack systematic criteria for expert reporting, evaluations that rely heavily on LLM judges can fail to capture issues that require expert judgment, and source verification typically covers only a limited subset of explicitly cited statements rather than report-wide factual reliability. We introduce DEER, a benchmark for evaluating expert-level deep research reports. DEER comprises 50 report-writing tasks spanning 13 domains and an expert-grounded evaluation taxonomy (7 dimensions, 25 sub-dimension) operationalized into 130 fine-grained rubric items. DEER further provides task-specific expert guidance to help LLM judges assess expert-level report quality more consistently. Complementing rubric-based assessment, we propose a document-level fact-checking architecture that extracts and verifies all claims across the entire report, including both cited and uncited ones, and quantifies external-evidence quality. DEER correlates closely with human expert judgments and yields interpretable diagnostics of system strengths and weaknesses.
Fonte: arXiv cs.CL
NLP/LLMs • Score 95
Toward Ethical AI Through Bayesian Uncertainty in Neural Question Answering
arXiv:2512.17677v1 Announce Type: new
Abstract: We explore Bayesian reasoning as a means to quantify uncertainty in neural networks for question answering. Starting with a multilayer perceptron on the Iris dataset, we show how posterior inference conveys confidence in predictions. We then extend this to language models, applying Bayesian inference first to a frozen head and finally to LoRA-adapted transformers, evaluated on the CommonsenseQA benchmark. Rather than aiming for state-of-the-art accuracy, we compare Laplace approximations against maximum a posteriori (MAP) estimates to highlight uncertainty calibration and selective prediction. This allows models to abstain when confidence is low. An ``I don't know'' response not only improves interpretability but also illustrates how Bayesian methods can contribute to more responsible and ethical deployment of neural question-answering systems.
Fonte: arXiv cs.CL
NLP/LLMs • Score 95
Are Vision Language Models Cross-Cultural Theory of Mind Reasoners?
arXiv:2512.17394v1 Announce Type: new
Abstract: Theory of Mind (ToM) -- the ability to attribute beliefs, desires, and emotions to others -- is fundamental for human social intelligence, yet remains a major challenge for artificial agents. Existing Vision-Language Models (VLMs) are increasingly applied in socially grounded tasks, but their capacity for cross-cultural ToM reasoning is largely unexplored. In this work, we introduce CulturalToM-VQA, a new evaluation benchmark containing 5095 questions designed to probe ToM reasoning across diverse cultural contexts through visual question answering. The dataset captures culturally grounded cues such as rituals, attire, gestures, and interpersonal dynamics, enabling systematic evaluation of ToM reasoning beyond Western-centric benchmarks. Our dataset is built through a VLM-assisted human-in-the-loop pipeline, where human experts first curate culturally rich images across traditions, rituals, and social interactions; a VLM then assist in generating structured ToM-focused scene descriptions, which are refined into question-answer pairs spanning a taxonomy of six ToM tasks and four graded complexity levels. The resulting dataset covers diverse theory of mind facets such as mental state attribution, false belief reasoning, non-literal communication, social norm violations, perspective coordination, and multi-agent reasoning.
Fonte: arXiv cs.CL