Visão computacional

Veja os papers deste label, com traduções para PT-BR.

Ver todos os labels

Artigos

👁️Visão computacional • 60 artigos encontrados

Limpar filtro

NLP/LLMs • Score 85

Expanding the Quality-Coverage Frontier with Competitive Flow Matching

arXiv:2611.07055v1 Announce Type: new Abstract: Flow matching (FM) generators often face a quality-coverage tradeoff. Inference-time techniques such as classifier-free guidance raise quality, but at the cost of coverage. We hypothesize this limitation stems from a basic property of the objective: an intermediate noisy image could correspond to many clean images, yet the model can only predict a single velocity, at best averaging over the multiple possibilities. To mitigate this, we introduce competition among predictions during training. We achieve this by augmenting the predictor with a randomly drawn low-dimensional conditioning code $z$. For each training example, we sample $K$ values of $z$ to produce $K$ candidate velocities that compete to explain the target, and apply the loss only to the best-matching candidate. This winner-take-all objective allows different modes to shape different predictions, rather than being averaged into a single compromise. Furthermore, this term naturally enables a new form of guidance, auxiliary conditioning scaling, which complements traditional guidance methods. Together, these two guidance mechanisms show that our method substantially improves the quality-coverage frontier. We validate on ImageNet-256, using two different testbeds, SiT and RAEv2. Given less than 3% of the original SiT pretraining compute for post-training, at the 67% Recall point, our method reduces $\mathrm{FD}_{r,6}$ from 19.22 to 5.91. On RAEv2, at the 70% Recall point, it reduces $\mathrm{FD}_{r,6}$ from 16.83 to 3.18.

Fonte: arXiv cs.CV

NLP/LLMs • Score 85

TraCE: Trajectory-Aware Concepts for Explainable Video Understanding

arXiv:2611.07009v1 Announce Type: new Abstract: Video understanding models often rely on motion, yet their explanations can obscure which motion sources support a prediction. We identify motion-source under-specification as a limitation of existing video XAI: region-centric explanations can be source-ambiguous, while motion vocabularies restricted to single-person pose sequences are source-incomplete. We propose TraCE (Trajectory-Aware Concepts for Explainable Video Understanding), a concept-based framework that discovers source-flexible motion concepts by clustering optical-flow trajectories from training videos. These concepts represent dynamic evidence from people, objects, and interactions, while object and scene concepts account for static context. The resulting typed trajectory/object/scene interface supports class prediction for action recognition and question-conditioned concept matching for video question answering (VQA). We evaluate TraCE across five random seeds on six benchmarks: NTU RGB+D Mutual, Chiral SSv2, UCF-101, KTH, TOMATO, and STAR. Relative to non-interpretable baselines, TraCE maintains competitive task performance, with an average accuracy drop of 1.0 points for action recognition and a nominal gain of 0.4 points for VQA. Motion perturbation and concept-removal tests provide complementary evidence of directional semantic alignment and decision faithfulness, while sample-level interventions illustrate targeted model debugging. Our project page is available at https://leewooil.github.io/TraCE_project_page/.

Fonte: arXiv cs.CV

NLP/LLMs • Score 85

TrustMix: Graceful Degradation for Pretrained Models under Distribution Shift

arXiv:2611.07206v1 Announce Type: new Abstract: Predicting beyond the training domain necessarily requires assumptions about how the ground truth extrapolates, yet in most neural networks these assumptions are made only implicit through the architecture. We propose TrustMix, a lightweight post-hoc method that makes a pretrained model's extrapolative behaviour explicit and controllable. TrustMix combines the predictive distribution produced by a pretrained model with a user-specified fallback distribution $p_0(y|x)$, such that as the out-of-distribution (OOD) deviation statistic grows, we collapse towards $p_0(y|x)$. TrustMix provides graceful degradation: the predictive distribution converges toward the fallback distribution as the OOD signal grows. The fallback distribution $p_0(y|x)$ can reflect domain knowledge, if available, or rely on a domain-agnostic stationarity assumption. TrustMix does not require retraining of the base model and can be applied to both regression and classification problems. We evaluated TrustMix on several synthetic and real-world distribution shifts, including tabular, image, and natural language processing tasks. We tested TrustMix on datasets such as CIFAR-10/100 and ImageNet and on numerous architectures including Convolutional Neural Networks (CNNs) and Transformers. TrustMix remains competitive in-distribution while improving predictive uncertainty under distribution shift, with gains in predictive likelihood for regression and calibration for classification. Finally, we showed that TrustMix can provide useful predictive distributions for decision-making applications by utilizing it as a surrogate for Bayesian Optimisation.

Fonte: arXiv cs.LG

Vision • Score 85

Gaussians Can Subtract: Neural Dissolve Fields for Hybrid Scene Rendering

arXiv:2611.07049v1 Announce Type: new Abstract: Hybrid Mesh-Gaussian rendering combines compact textured surfaces with flexible 3D Gaussian primitives, offering an efficient alternative to purely Gaussian scene representations for structured environments. Existing scene-reconstruction hybrids commonly follow an additive formulation, where Gaussian residuals compensate for errors left by the mesh. However, not every Mesh-Gaussian conflict is caused by missing content: residual geometry errors, occlusion mismatch, texture-projection artifacts, and view-dependent appearance can make the same mesh content consistent in one view but inconsistent in another. We therefore formulate hybrid rendering as a multi-view inconsistency problem and present Gaussolve, a subtract-and-refill framework that selectively dissolves inconsistent mesh content before residual Gaussians refill the revealed regions. We introduce a lightweight Neural Dissolve Field, parameterized by scalar spherical-harmonic Gaussians, to learn where and from which viewing directions mesh content should be dissolved. A continuous transmittance fusion rule progressively exposes residual Gaussians behind the dissolved mesh, preserving their reconstruction gradients and avoiding hard visibility discontinuities. Experiments on structured and semi-structured scenes demonstrate higher visual fidelity with fewer Gaussian primitives and faster rendering. Project page: https://ooosn.github.io/gaussians-can-subtract/

Fonte: arXiv cs.CV

NLP/LLMs • Score 85

Shaping & Monitoring Models through their Internal Representations

arXiv:2611.07071v1 Announce Type: new Abstract: We propose Mechanistic Shaping, a unified framework for shaping models through their internal representations. Mechanistic Shaping is applied during training so that models follow specifications (rules) about which concepts they express, measured via their outputs or internal representations (e.g., no harmful content), and also which concepts they rely on, i.e., what they use to make their decisions (e.g., not a candidate's gender when screening a r\'esum\'e). Across multiple domains (vision, medical imaging, language), scales (up to 32B parameters), and training paradigms (classification, SFT, DPO, GRPO), we find that Mechanistic Shaping substantially reduces targeted behaviors while preserving task performance. Since training against a representation can also modify it, we ask whether shaped concepts remain monitorable, a question that depends on the class of monitors considered. We therefore introduce a hierarchy of such classes, which separates a concept that escapes one probe from a concept that is truly gone. We characterize three geometric mechanisms of circumvention: the concept can drift away from the monitor, be erased from the layer, or persist in higher-order statistics as a nonlinear encoding, which we explain through a product-code construction. Although other mechanisms may arise in different settings or at larger scales, these three account for all of our observations, and each can be detected by a matching monitor. In practice, we find that shaped concepts largely remain monitorable: refitted linear probes recover the concept in most settings, and the original probe remains reliable whenever gradients do not flow through it. Taken together, these results point to the potential of using interpretability as a tool for training, and call for a correspondingly rigorous science of interpretability-based training.

Fonte: arXiv cs.LG

Vision • Score 85

Wide View Synthesis from Overlapping Perspective Cameras in Autonomous Driving

arXiv:2611.07081v1 Announce Type: new Abstract: Multi-perspective-camera systems are widely adopted since they provide broad visual coverage for autonomous driving, motivating the synthesis of a unified wide view from spatially separated observations. In this work, we formulate wide view synthesis (WVS), which aims to synthesize a geometrically consistent wide view at a specified virtual viewpoint from multiple perspective cameras. Unlike conventional image stitching, WVS requires reasoning about 3D geometry and visibility to handle depth-dependent parallax and occlusions arising from spatially separated camera centers. While vanilla 3D Gaussian Splatting (3DGS) enables high-fidelity view synthesis, its reliance on per-scene optimization limits its applicability to driving scenes. Furthermore, WVS introduces additional challenges, *e.g.*, peripheral stretching under perspective projection and photometric inconsistencies across cameras. To address these challenges, we propose **Wide-View Gaussian Splatting (WV-GS)**, a feed-forward Gaussian-splatting framework that synthesizes wide views without per-scene optimization. Specifically, we introduce Piecewise Perspective Rendering (PPR) to mitigate peripheral stretching through local perspective projections sharing a common camera center, and Spatial Affine Photometric Modeling (SAPM) to account for camera-dependent photometric variations during training. We further introduce **WideDrive**, a synthetic benchmark providing dense ground-truth wide views and adapt a LiDAR-projected sparse-reference protocol to real-world datasets. Extensive experiments on multiple datasets demonstrate the effectiveness of WV-GS for WVS. Dataset and code will be publicly released.

Fonte: arXiv cs.CV

NLP/LLMs • Score 85

Householder Motion Embedding: Noise Modulation for Motion-Controllable Video Generation

arXiv:2611.07294v1 Announce Type: new Abstract: Diffusion models for video generation have achieved remarkable success, yet precise motion control under explicit user guidance remains challenging. Recent noise-warping methods introduce temporal correlations by warping the noise according to the user-provided motion signal. However, standard spatial warping generally disrupts the noise's i.i.d. Gaussian structure, requiring distribution correction, such as Jacobian-based correction, but at a substantial computational overhead. We propose Householder Motion Embedding (HME), which encodes the motion signal into the noise through a sequence of Householder reflections that together form an orthogonal transformation applied to each location's channel vector. HME exactly preserves the spatial Gaussian structure within each frame while introducing cross-frame correlations that promote temporally consistent video. HME is agnostic to the network architecture and integrates directly into standard video diffusion fine-tuning pipelines. Experiments on different scenarios show that HME matches or outperforms the state of the art, while achieving a 2.7x speedup over noise warping. These results demonstrate that channel-space Householder transformations offer a principled and efficient alternative to noise warping for motion-controllable video generation.

Fonte: arXiv cs.CV

NLP/LLMs • Score 85

KG-Neighbor: Knowledge-Guided Neighborhood Construction for Embedding Visualization

arXiv:2611.07246v1 Announce Type: new Abstract: In embedding visualizations, nearby instances are interpreted as semantically related, although neighborhoods derived from input embeddings may not reflect content relationships. Neighborhood-based dimensionality reduction (DR) methods can propagate this limitation by optimizing layouts from embedding-based neighborhood graphs. We propose Knowledge-Guided Neighborhood Graph Construction (KGN), which represents relational knowledge derived from each instance as a set of knowledge graph (KG) triples. It uses the degree of triple sharing as pairwise semantic evidence to adjust embedding distances and reconstruct the top-k neighborhood graph; neither KG extraction nor neighborhood construction uses class labels. We also introduce IDProfile (IDP), which interprets residual mismatches by independently assessing whether the source content supports the assigned class label and the neighborhood-majority class. Across eight text and image dataset-encoder conditions, we characterize KGN over the full guidance-strength sweep and four KG similarity measures. Across this sweep, the maximum NMI and LT_2D each exceed the corresponding kNN baseline in all eight conditions, with the largest gains reaching 0.68 and 1.35, respectively. The gains and the extent of neighborhood reconfiguration vary across conditions and are larger under encoder conditions with lower kNN baseline scores. The IDP analysis shows that the largest reductions are concentrated in Placement Issue candidates, whereas Label Issue and Unresolved Case instances account for a larger share of the remaining review set. These results indicate that KGN can narrow the evaluated gap between embedding-based neighborhoods and content-supported semantic relations, while IDP shows that a residual mismatch should not automatically be interpreted as a projection failure.

Fonte: arXiv cs.LG

Vision • Score 85

Batch-Conditioned Semantic Anchors for Robust Transductive Adaptation of Vision--Language Models

arXiv:2611.06993v1 Announce Type: new Abstract: Transductive adaptation improves vision-language models at test time by refining predictions on an unlabeled batch, but current methods face a key trade-off. Aggressive approaches exploit batch structure but can drift when batches are sparse, have prior shift, or cover little of the label space. Conservative methods better preserve CLIP text semantics, but fixed semantic references can under-adapt even when the batch provides strong corrective evidence. We propose JPTA (Joint Prior and Transport Adaptation), a prior-aware framework that casts transductive VLM adaptation as batch-conditioned semantic reference estimation. Instead of treating CLIP text prototypes as fixed priors or freely replaceable, JPTA views them as semantic references that shift toward image-side batch structure only under calibrated evidence. It estimates batch priors and soft image-side prototypes to form transported semantic references whose impact is scaled by batch reliability. Across standard benchmarks, low effective-class regimes, all-class evaluation, and online streams, JPTA consistently outperforms TransCLIP and StatA, with the largest gains on sparse and prior-shifted batches. Anchor-drift, active-support, and absent-class-mass diagnostics show that JPTA fixes effective-class mismatch without unconstrained transductive drift, indicating that robust transductive VLM adaptation should recalibrate semantic references using reliable batch evidence rather than choose between unrestricted transduction and fixed prototypes. Code is available at https://github.com/MR-Sherif/JPTA.git.

Fonte: arXiv cs.CV

NLP/LLMs • Score 85

SD-LoRA: Training-Time Structural Distillation into LoRA for Few-Shot Vision-Language Adaptation

arXiv:2611.07063v1 Announce Type: new Abstract: Few-shot adaptation of vision-language models must balance two competing goals: learning fine-grained visual distinctions from very limited supervision and preserving the efficiency that makes frozen CLIP-like models attractive for deployment. Existing lightweight adaptation methods, including prompt tuning, LoRA, and cache-based adapters, typically supervise global image embeddings and therefore underuse token-level structure. Conversely, structure-aware methods exploit local evidence but often introduce additional inference-time computation. We propose SD-LoRA, a structural distillation framework that uses token-level graph reasoning only during training and transfers its effects into a lightweight LoRA-adapted CLIP model. During training, a heterogeneous graph teacher models patch-patch, global-local, and visual-text relations over high-resolution ViT tokens. Rather than retaining this graph at test time, SD-LoRA transfers its structural bias into the shared CLIP-LoRA backbone through implicit distillation and Prototype Predictive Alignment, which aligns graph-conditioned representations with support-derived class prototypes. At inference, the graph teacher is discarded; prediction requires only a single CLIP-LoRA forward pass and a cache-based classifier. Across 11 few-shot benchmarks, SD-LoRA improves over a strong CLIP-LoRA baseline by 2.4/1.8/3.0/2.4/2.0 percentage points in the 1/2/4/8/16-shot settings, respectively, without additional graph computation at test time. Results on base-to-novel generalization, cross-dataset transfer, out-of-distribution robustness, and calibration further show that training-time structural supervision improves both accuracy and transfer reliability. Code is available at https://github.com/MR-Sherif/SD-LoRA.git.

Fonte: arXiv cs.CV

Vision • Score 85

VINO: Revisiting 3D Representation Learning with Volume Transformers

arXiv:2611.07176v1 Announce Type: new Abstract: Self-supervised learning has given rise to vision foundation models that learn general-purpose image representations transferable across downstream tasks, yet representation learning for 3D scenes has not achieved comparable success. Motivated by this, we identify key limitations of current 3D representation learning approaches and revisit their core design choices. We first replace the commonly used hierarchical PTv3 backbone with the Volume Transformer, a ViT-like architecture for 3D scenes. We then redesign two core objectives of modern approaches built around student-teacher networks: matching representations across views and predicting masked content from visible context. For the first objective, we separate the roles of teacher and student: the teacher provides clean, consistent targets while the student learns invariance to stronger perturbations. For the second objective, we prevent the student from accessing the masked geometry and instead require it to infer missing representations from visible context only. Finally, we redesign 2D-to-3D knowledge distillation, replacing direct regression of view-dependent image features with view-consistent supervision. Together, these changes form VINO, a framework that learns semantic representations of 3D scenes without labels. VINO substantially improves dense linear probing across indoor and outdoor benchmarks and transfers strongly to out-of-domain settings.

Fonte: arXiv cs.CV

NLP/LLMs • Score 85

Perceptual Distortion for Overfitted Video Coding: Sliced Matching in Space, Error Alignment in Time

arXiv:2611.07148v1 Announce Type: new Abstract: Recent works in neural video coding have increasingly been trading off perceptual quality against reconstruction fidelity at a fixed bitrate. Wasserstein Distortion (WD) offers a principled approach to balancing these objectives by relaxing spatial correspondences in feature matching, enabling lightweight overfitted image codecs to compete with computationally intensive generative decoders. Extending vanilla WD to video, however, presents two challenges: its independent Gaussian approximation limits the expressiveness of feature distribution matching, while unconstrained texture resampling across frames introduces temporal inconsistencies. We address these challenges by distinguishing between the correspondences that can be relaxed and those that must be preserved. Spatially, we introduce a local sliced Wasserstein distortion (SWD) that matches empirical feature distributions through one-dimensional optimal transport, capturing cross-channel dependencies without enforcing exact spatial alignment. Temporally, we employ a novel flow residual that constrains coding errors along motion trajectories, preserving temporal consistency without imposing additional reconstruction fidelity constraints. Evaluated on UVG and HEVC Class B with the overfitted codec COOL-CHIC, our framework achieves BD-rate reductions of 9.2% in DISTS and 3.0% in LPIPS relative to frame-wise WD, averaged over test sequences, while lowering tOF by 10.2% at matched rate.

Fonte: arXiv cs.CV

NLP/LLMs • Score 85

Segment What It Can Draw: Querying a Text-to-Image Generator with Its Own Images for Skin Lesion Segmentation

arXiv:2611.07061v1 Announce Type: new Abstract: Skin lesion segmentation without annotated masks requires the target to be specified through other cues. Existing approaches rely on dermoscopy-specific rules, annotation-derived model priors, or user-selected regions. A general text-to-image diffusion transformer offers a text interface to the target, but its concept-word attention is unreliable on dermoscopy images: in the model's attention-output space, the word-derived skin-to-lesion direction is poorly aligned with the direction separating real skin from real lesions. We show that the direction derived from generated healthy-skin and lesion images is substantially better aligned. Based on this finding, we propose GENIQ, a training-free method that constructs initial skin and lesion prototypes from generated images and refines them using the most skin-like and lesion-like patches from unlabelled dermoscopy images. It scores test patches along the refined direction and applies a gated threshold to suppress contextual spill-over around small lesions. Without inference-time annotations or additional models, GENIQ achieves Dice scores of 0.85-0.88 on three dermoscopy test sets. It outperforms zero-shot and word-based attention methods on all three sets, and a hand-designed dermoscopy pipeline in Dice and IoU on two.

Fonte: arXiv cs.CV

Vision • Score 85

T$^2$-Splat: Adaptive Topology Mesh Splatting with Texture Residuals

arXiv:2611.06974v1 Announce Type: new Abstract: Triangle-based splatting connects novel view synthesis with conventional graphics pipelines, but often requires excessive tessellation to preserve appearance details. We present T$^2$-Splat, which decouples topology adaptation from appearance refinement. Safe Restricted Delaunay Triangulation (Safe RDT) initializes mesh connectivity. Dynamic Topology Evolution (DTE) then adapts triangle allocation through edge collapse and vertex split operations. Residual per-face Mip-textures then refine appearance on the fixed mesh using scale-adaptive filtering. Experiments on Mip-NeRF 360, Tanks & Temples, and DTU demonstrate competitive results with compact meshes. T$^2$-Splat improves PSNR by 0.71dB over MeshSplatting on Mip-NeRF 360. Additional compression experiments demonstrate flexible control of mesh complexity, supporting face budgets as low as 10% of the original face count. Project page: https://t2-splat.github.io/.

Fonte: arXiv cs.CV

NLP/LLMs • Score 85

Compositional Unalignment: Auditing Safety in Large Vision-Language Models

arXiv:2611.07216v1 Announce Type: new Abstract: Large vision-language models (LVLMs) are vulnerable to compositional harm: an image and a prompt that are benign in isolation become harmful through the model's cross-modal reasoning. Recent alignment methods report strong scores on compositional safety benchmarks, but an LLM judge only measures observed behavior and cannot reveal how robustly safety is integrated into the model. We argue that un-alignment provides a complementary audit of alignment robustness. We first show that minimal supervised fine-tuning reaches an LLM-judge score comparable to a multi-stage reinforcement-learning pipeline, so similar benchmark scores cannot establish robustness by themselves. We then show that recognition and refusal of compositional harm are decoupled: nine standard direction-finding methods detect compositional harm with up to AUC=0.99, yet ablating the recovered directions either leaves refusal intact or destroys model coherence. We therefore propose CMaG, a training-free un-alignment method for compositional safety. CMaG measures refusal intention with a refusal-versus-compliance log-probability margin, takes its gradient with respect to mid-layer activations, and contrasts it against partially benign pairs to isolate the cross-modal interaction term. A single backward pass over 80 examples yields a direction along which steering monotonically converts refusal into compliance. On Qwen2.5-VL-7B and LLaVA-1.5-7B, CMaG reduces compositional safety scores by up to 65 points while over 98% of outputs remain coherent, outperforming gradient-based baselines; the direction also transfers to text-explicit harm and un-aligns models hardened by defensive training. Compositional safety can thus appear behaviorally strong while remaining fragile to targeted internal intervention. Warning: this paper contains unsafe model outputs, including references to self-harm.

Fonte: arXiv cs.LG

Vision • Score 85

MammoSeek: A Mammography Agent with selective zooming for grounded reports

arXiv:2611.07188v1 Announce Type: new Abstract: Radiologists read a screening mammogram by first forming a global impression of the four views and then selectively magnifying suspicious regions before assigning a BI-RADS assessment. MLLMs, in contrast, see the whole image at a fixed, reduced resolution, which makes sub-millimeter calcifications invisible, and they perform close to chance on mammography. Therefore, we present MammoSeek, a mammography agent that reproduces this reading process. After forming an impression of each breast, the agent performs selective zooming: it decides by itself which detector candidates deserve a closer look and inspects only those on full-resolution views. Guided by a BI-RADS assessment skill, it then assigns a category and generates a localized, lexicon-structured report for each breast; its assessment is combined with image-model scores in a decision layer to decide recall. On an internal (EMBED) and an external (VinDr-Mammo) dataset, \ours reaches exam-level AUCs of 0.824 and 0.818, far above other MLLMs, mammography agent and CNN classifiers. Selective zooming also outperforms both no zooming and forced zooming in localization, structured-report F1 and recall decisions at low cost.

Fonte: arXiv cs.CV

Vision • Score 85

Progressively Refining SAM for Accurate Phytoplankton Segmentation

arXiv:2610.36722v1 Announce Type: new Abstract: Accurate phytoplankton segmentation is essential for ecological monitoring, yet it remains largely underexplored due to the subtle visual characteristics of phytoplankton and the scarcity of pixel-level annotations. To address these challenges, we propose PhySeg, a SAM-based segmentation framework equipped with a lightweight refinement module that progressively restores fine-grained details through multi-scale feature fusion. In addition, we construct a phytoplankton segmentation dataset by manually annotating instance-level masks for an existing dataset, providing a valuable resource for future research. Experimental results demonstrate that PhySeg improves segmentation accuracy, validating the effectiveness of the proposed module. Code is available at https://github.com/lijialin404/PhySeg.

Fonte: arXiv cs.CV

NLP/LLMs • Score 85

SpeeDiff: Scalable Pixel-Anchored End-to-End Latent Diffusion Model

arXiv:2610.36419v1 Announce Type: new Abstract: We present Scalable Pixel-anchored End-to-end Diffusion (SpeeDiff), a latent diffusion method that jointly trains the VAE and the diffusion model from scratch. In principle, joint training allows the diffusion loss gradient to directly guide the VAE encoder, encouraging the formation of a generation-friendly latent space and potentially yielding faster convergence than the conventional two-stage approach with a pretrained frozen VAE. However, a naive end-to-end implementation severely degrades performance, as unrestricted backpropagation of the diffusion loss leads to latent space collapse. Our main technical contribution is a simple yet effective Tweedie Pixel Reconstruction (TPR) loss, which provides additional pixel-level feedback by decoding a predicted clean latent from an intermediate noisy state using Tweedie's formula, thereby alleviating collapse. Furthermore, our method enables jointly scaling a fully transformer-based architecture and enhances representation alignment within the end-to-end framework. Our SpeeDiff-XL model achieves over 140x and 61x faster training compared to Vanilla SiT and REPA, respectively, while attaining an FID of 1.50 without guidance on ImageNet 256x256 generation. With a more efficient 32x compressed VAE, our model further reaches an FID of 1.53 without guidance on ImageNet 512x512 generation.

Fonte: arXiv cs.CV

NLP/LLMs • Score 85

Learning and Reasoning with Geometry: How Generation Helps Spatial Understanding

arXiv:2610.36022v1 Announce Type: new Abstract: Image and video generators can produce spatially consistent visual content, but how to use this capability to improve spatial understanding remains underexplored. We study this problem from two perspectives: geometric supervision during training and explicit geometric evidence during inference. To this end, we introduce a unified geometric understanding and generation model (GeoUG) that integrates depth and multi-view generation with spatial understanding. First, we design a multi-scale depth codec that enables metric-depth generation using a pretrained visual autoencoder, and show that joint training yields task-dependent gains in spatial understanding. Second, we introduce 3DCueBench to control geometric difficulty while balancing selected 2D cues, and find that generated depth provides larger reasoning gains on questions requiring fine-grained geometric discrimination. Building on this finding, we develop adaptive interleaved reasoning, in which GeoUG first drafts an answer and then decides whether to generate geometric evidence to confirm or revise it. We train this decision through reinforcement learning, balancing accuracy gains over retaining the draft against generation cost. GeoUG achieves circular accuracies of 97.9%, 90.8%, and 94.2% on CV-Bench-3D, 3DCueBench, and DA-2K with fewer generation calls than always generating.

Fonte: arXiv cs.CV

Vision • Score 85

Efficient Remote Sensing Image-Text Retrieval via Interaction-Free Recall and Text-Guided Reranking

arXiv:2610.36756v1 Announce Type: new Abstract: Remote sensing (RS) image-text retrieval plays a critical role in understanding massive RS imagery. However, the dense multi-object distribution and complex backgrounds in RS imagery make it difficult to simultaneously achieve fine-grained cross-modal alignment and efficient retrieval. Existing methods either rely on complex cross-modal interactions that lead to low retrieval efficiency, or depend on large-scale vision-language adaptation, which requires massive data and computational resources. To address these issues, we develop a fast-then-fine (FTF) retrieval framework centered on interaction-free multi-granular recall and parameter-free text-guided cross-modal reranking with the Balanced Text-guided Interaction Block (BTIB). Specifically, interaction-free multi-granular recall pre-computes gallery embeddings and matches them with the corresponding query embedding without full-gallery token-level text-image interaction, while text-guided cross-modal reranking with BTIB refines local semantic correspondence within the top-K candidate set. Furthermore, an inter- and intra-modal loss is designed to jointly optimize cross-modal alignment across multi-granular representations. Extensive experiments on public benchmarks demonstrate that the FTF achieves competitive retrieval accuracy while significantly improving retrieval efficiency compared with existing methods.

Fonte: arXiv cs.CV

Vision • Score 85

GarmentSegAgent: Autonomous Garment Segmentation for Web Fashion Images via Textual Self-Refinement

arXiv:2610.36506v1 Announce Type: new Abstract: Web fashion images support applications such as visual product search and consumer-to-shop matching, yet their visual heterogeneity makes reliable garment segmentation challenging. Despite advances in promptable segmentation, autonomously identifying and correcting garment-specific errors without human-provided spatial prompts remains difficult. We propose GarmentSegAgent, an autonomous framework that integrates semantic planning, spatial execution, and visual evaluation through iterative textual self-refinement. At its core, we introduce CAST (Constrained Attribution-guided Selective TextGrad), which connects visual error attribution with targeted textual optimization. CAST identifies instruction components responsible for segmentation errors, selectively updates them through textual gradients, and validates the resulting instructions against garment-specific constraints. This enables image-specific error correction at inference time while keeping the underlying foundation models frozen. Experiments on DeepFashion2, ModaNet, and Fashionpedia demonstrate consistent improvements in region overlap and boundary accuracy, alongside more reliable refinement than conventional TextGrad. By enabling visual feedback to guide controlled instruction updates, GarmentSegAgent offers a promising direction for autonomous garment understanding, with potential applications in scalable fashion content analysis, visual retrieval, and consumer-to-shop matching on the Web.

Fonte: arXiv cs.CV

Vision • Score 85

Spatial-Frequency Learning for Scanning Transmission Electron Microscopy Image Enhancement

arXiv:2610.36487v1 Announce Type: new Abstract: Scanning Transmission Electron Microscopy (STEM) enables the observation of atomic arrangements at sub-angstrom resolution and plays a key role in the discovery and characterization of advanced materials. Raw STEM images are often noisy and blurred due to multiple degradations. Although recent deep learning methods improve STEM images, their performance remains limited under severe degradations. In this work, we propose a spatial-frequency learning framework for STEM image enhancement. Specifically, we design a spatial-frequency fusion network that exploits periodic atomic arrangements in the frequency domain and restores local atomic details in the spatial domain. Spatial- and frequency-domain features are enhanced separately and then fused. We also present a STEM noise calibration method for synthesizing more realistic STEM images. The parameters of scan noise, pointwise noise, and background noise are estimated through statistical analysis and fitting of real STEM images. Using these calibrated parameters, we construct a diverse dataset containing a wider range of atomic arrangements, imaging modes, and degradations. Random masks combine different atomic arrangements to simulate interfaces between multiple materials. Experimental results demonstrate that our method achieves state-of-the-art enhancement performance on synthetic datasets and real images of advanced materials while improving atomic localization accuracy.

Fonte: arXiv cs.CV

Vision • Score 85

FORESEE-MS: Toward Prospective Spatial Forecasting of Future Multiple Sclerosis Lesions from Baseline FLAIR MRI

arXiv:2610.36428v1 Announce Type: new Abstract: Traditional multiple sclerosis (MS) image analysis has primarily focused on retrospectively detecting and segmenting lesions. This study investigates whether baseline FLAIR MRI can identify regions at risk for future lesion formation beyond population-level spatial patterns. We introduce FORESEE-MS, an evaluation protocol that uses a fold-specific population-prior atlas as a baseline and assesses predictions using pooled voxel-level discrimination (AUROC and AUPRC) and within-patient lesion localization (Recall@Top-K%), with patient-level bootstrap confidence intervals. We evaluated five deep learning models (3D U-Net, Attn+ResBlock+VAE, ViT, and two SwinUNETR variants) using 5-fold cross-validation on 39 subjects from the MSSEG-2 dataset. The atlas achieved the highest pooled voxel-level AUROC and AUPRC, with no deep learning model reliably outperforming it on either metric. However, the 3D U-Net and Attn+ResBlock+VAE achieved higher mean voxel-level within-patient Recall@Top-K% than the atlas at all evaluated thresholds, although most paired confidence intervals for the differences included zero. These findings suggest that baseline FLAIR may contain patient-specific predictive information, but in this small cohort, it remains uncertain whether this information improves lesion forecasting beyond a population-prior atlas.

Fonte: arXiv cs.CV

NLP/LLMs • Score 85

LabWorld: Learning Interactive 4D Worlds for Scientific Experimentation

arXiv:2610.36592v1 Announce Type: new Abstract: Autonomous scientific agents must not only reason about experiments but also interact with the physical environments in which they are executed. Existing laboratory simulators typically rely on manually constructed assets and predefined procedures, while laboratory videos capture real equipment, layouts, and interactions but leave this information implicit in pixels. We introduce LabWorld, an agent-driven Real2Sim framework for reconstructing interactive 4D laboratory worlds from monocular RGB video. LabWorld recovers reusable 3D assets, a metric scene, time-varying object states, and procedure events. Multi-frame observations provide complementary evidence for asset and scene reconstruction, while motion reconstruction combines visual and geometric observations with event constraints encoding the spatial and temporal requirements of laboratory interactions. We evaluate LabWorld on real pipetting and vortexing videos collected in our laboratory against general-purpose agentic and dedicated reconstruction baselines. For pipetting, LabWorld achieves a mean Mask IoU of 0.501, exceeding the strongest baseline by 0.033. For vortexing, it achieves a mean Tube-Length-Normalized PCK-AUC of 0.638, exceeding the strongest baseline by 0.035. On five pipetting videos, event-conditioned reconstruction increases the fraction of modeled physical constraints satisfied from 14.3% (5/35) to 100% (35/35). The resulting worlds expose geometry, motion, articulation, and events as explicit, editable state for replay, inspection, and future embodied scientific systems.

Fonte: arXiv cs.CV

Vision • Score 85

Physiognomy Revisited: How Vision-Language Models Encode Sensitive Attributes Through Image Transformation

arXiv:2610.35910v1 Announce Type: new Abstract: Emergent generative AI technologies, while remarkably beneficial across several tasks and domains, can suffer from unforeseen vulnerabilities and difficult-to-anticipate failure modes. Such failure modes can disparately affect vulnerable communities. This paper investigates two well-known vision language models (VLMs) and inspects how these models encode protected identities while generating images. We show that when VLMs are requested to transform human face images to reflect race identities (e.g., Hispanic, Black, White, or Asian) and sexual orientation (e.g., gay or straight), VLMs often comply with such requests. We demonstrate that compliance (and refusal) is non-deterministic, group-sensitive, and generated images are statistically distinguishable, often accentuating deep-seated stereotypes. We further show that representation biases introduced during image generation can re-emerge in textual reasoning and characterization tasks. Finally, we show that this worrisome finding is not limited to racial identity or sexual orientation, image generation can perpetuate bias around criminality, raising concerning possibilities of AI-assisted profiling.

Fonte: arXiv cs.CV

NLP/LLMs • Score 85

Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs

arXiv:2610.36671v1 Announce Type: new Abstract: Diffusion vision-language models (DVLMs) process their entire input at every denoising step. Since visual tokens make up 89-97% of this input on the benchmarks we study, most of the decoding computation is spent repeatedly processing the same image. Visual token pruning methods partially relieve this burden by removing part of the visual tokens, but they lose the removed information and still process the remaining image at every step. To measure how often the image is actually needed, we compare LLaDA-V's predictions with and without the image at every decoding step and find that removing the image changes a token being unmasked at only 22.8% of steps on average and at as few as 7.9%. We therefore propose LOWN, a decoding method that decides at every step whether to process the image and how many tokens to unmask. LOWN predicts the masked tokens without the image and processes the image only when this prediction disagrees with the last image-conditioned prediction. Agreement certifies the earlier prediction for reuse, and the number of certified tokens sets how many are unmasked in that step. We further observe that the need for the image differs across benchmarks, so LOWN's adaptive decision is needed rather than a fixed schedule. Without training or a tuned threshold, LOWN retains 99.6% of LLaDA-V's score on ten benchmarks at 35.3% of the decoding FLOPs on average. LOWN also generalizes across LLaDA-based DVLMs, composes orthogonally with visual token pruning, and runs under key-value caching for further efficiency gains. Code and project page are available at https://hyeon9698.github.io/LOWN/

Fonte: arXiv cs.CV

NLP/LLMs • Score 85

Evaluating Federated Vision-Language and Vision-Only Models for Privacy-Aware Breast Cancer Imaging

arXiv:2610.36379v1 Announce Type: new Abstract: Artificial intelligence (AI) shows promise for breast imaging, but limited labeled data, institutional data fragmentation, and privacy concerns hinder centralized training. We investigate a privacy-aware federated learning framework combining pretrained vision-language models (VLMs) with client-level differential privacy. We compare general-purpose CLIP models, biomedical BiomedCLIP, and an ImageNet-pretrained ViT-B/16 baseline on two public breast imaging datasets, with and without differential privacy. We also evaluate a CLIP ViT-B/16 ablation that removes the text pathway. Evaluation includes patient-level ROC-AUC with bootstrap 95% confidence intervals, baseline comparisons, threshold sensitivity, inter-model agreement, and communication cost. Under federated learning, all five models achieve high normal-versus-sick discrimination (ROC-AUC: 0.940-0.990). However, acquisition year alone achieves 0.974 on the same test partition, raising concerns about confounding rather than genuine pathology recognition. Benign-versus-malignant discrimination remains uncertain (ROC-AUC: 0.504-0.637), with all confidence intervals including 0.50. Removing the text pathway preserves classification accuracy while halving communication cost. Differential privacy reduces ROC-AUC by 0.375, attributable to perturbing the full model state rather than only trainable parameters. These findings highlight the importance of evaluating confounding, predictive reliability, privacy implementation, and deployment efficiency when developing federated AI systems for breast imaging.

Fonte: arXiv cs.CV

Vision • Score 85

WithinVAE: Compact Visual Autoencoding with Self-Distilled Semantics

arXiv:2610.36593v1 Announce Type: new Abstract: Visual autoencoders must balance reconstruction fidelity, compactness, and semantic structure. Existing semantic tokenizers typically inherit semantics from pretrained recognition encoders, whose invariances can discard the appearance detail required for inversion. We show that this inheritance is unnecessary: semantic structure can be learned inside an autoencoder's own reconstructive representation. We introduce WithinVAE, a compact variational visual autoencoder with a sequential bottleneck, DINO/iBOT-style self-distillation from an exponential-moving-average copy of the autoencoder itself, and position-dependent token masking to achieve a 4-fold compression ratio, which is free of pretrained representation encoder or external semantic target. On ImageNet-1K at $256\times256$, WithinVAE improves all four reported reconstruction metrics over RPiAE including PSNR by 1.36 dB, while using half its latent scalar capacity. Under frozen evaluation, the same latents improve linear probing by 6.5 points over RPiAE and 5.1 points over our reconstruction-only baseline, attributing the semantic gains to self-distillation rather than architecture or external supervision. An auxiliary latent-to-latent model reproduces the ordered-compression trend, and a pixel-to-latent model transfers the objective to a pretrained generative space. These results separate the origin of semantic supervision from its use: a compact visual autoencoder can organize semantic structure without borrowing a recognition representation.

Fonte: arXiv cs.CV

Privacy/Security/Fairness • Score 85

PrinGS: Privacy Preservation in Gaussian Splatting

arXiv:2610.36168v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has rapidly become the preferred representation for high-fidelity novel view synthesis and 3D scene reconstruction. However, the learned representation encodes sensitive visual information including human faces, license plates, documents, and computer screens, raising significant privacy concerns when trained splats are shared or deployed. In this work, we address the underexplored problem of privacy preservation in Gaussian Splatting by proposing a representation-level anonymization framework that directly anonymizes a trained splat. Given a trained splat and a user-provided reference view identifying sensitive content, our method localizes the corresponding regions in the underlying 3D representation and directly anonymizes them, ensuring that the sensitive information is absent from all subsequently rendered novel views while preserving the overall scene geometry and visual fidelity. We achieve this post-training anonymization in less than 1 second. Furthermore, we extend our framework with a privacy-by-design training strategy that prevents sensitive content from being embedded into the representation during optimization, enabling the generation of privacy-preserving splats directly from training images. Our method achieves a remarkably low Face Similarity Measure (FSM) of 9.79% at a retained Face Detection Rate (FDR) of 39.47% and makes sensitive text completely unreadable with an OCR Character Error Rate of 1.00. Our work aims to serve as the primary stepping stone towards privacy-aware 3D representations and motivates further research along these directions.

Fonte: arXiv cs.CV

Multimodal • Score 92

Nemotron-Labs-Diffusion-Uni: Elastic Self-Refining Unified Diffusion LLM with Cross-Paradigm On-Policy Distillation

arXiv:2610.36466v1 Announce Type: new Abstract: We propose Nemotron-Labs-Diffusion-Uni (NLD-Uni), a unified discrete diffusion large language model (DLLM) for visual understanding and generation tasks. Compared with prior unified diffusion models, NLD-Uni introduces two major innovations. First, we propose a unified cross-paradigm on-policy distillation (OPD) framework that successfully transfers the visual understanding ability of autoregressive VLMs and visual generation ability of continuous flow models, to a unified DLLM. Second, NLD-Uni incorporates a novel progressive self-refining diffusion process that gradually corrupts each token across multiple steps during training, as opposed to adopting the conventional masked diffusion formulation that directly corrupts a clean image token to an uninformative mask token. At inference, this design allows NLD-Uni to make intermediate commit to a token, enabling progressive self-refinement for better visual quality. Through extensive experiments, we show that NLD-Uni achieves state-of-the-art performance among unified DLLMs on diverse tasks including visual question-answering, multi-modal reasoning, object grounding, text-to-image generation, and image editing.

Fonte: arXiv cs.CV

NLP/LLMs • Score 85

Training-Free Inference Acceleration for Video Large Language Models: Methods, Trade-offs, and Evaluation

arXiv:2610.36327v1 Announce Type: new Abstract: Video Large Language Models (VLMs) have demonstrated strong capabilities in video understanding and reasoning, but processing long visual sequences incurs substantial computational, latency, and memory overhead. This survey examines training-free inference acceleration, focusing on reducing inference costs while preserving task-relevant spatiotemporal evidence. We organize existing methods by their intervention stages in the inference pipeline, covering input, visual encoding, projector, prefill, and decoding. Post-training quantization (PTQ) is discussed separately as a cross-stage extension with varying calibration requirements. We analyze how intervention position affects evidence preservation and computational savings, and why local efficiency improvements may not translate into end-to-end acceleration. We complement this analysis with quantitative evidence from prior studies and our own experiments under a shared evaluation setting to assess accuracy-latency trade-offs.

Fonte: arXiv cs.CV

Vision • Score 85

Learning to Read Braille: Benchmarking and Improving Braille Recognition Capabilities of VLMs

arXiv:2610.36195v1 Announce Type: new Abstract: Despite rapid progress in visual understanding and document transcription, modern vision-language models (VLMs) struggle with a fundamental accessibility task: reading Braille from images. We introduce BrailleBench, a manually curated benchmark of 259 real-world Grade-1 and Grade-2 Braille images. We evaluate proprietary, open-weight, OCR-specialized, and tool-assisted multimodal systems and find that standalone general-purpose models perform poorly at directly transcribing Braille images, whereas tool-assisted systems perform much better. We design a synthetic Braille generation pipeline with diverse layouts and image perturbations. A 2B VLM model trained on our synthetic data reaches 87% exact match on Grade-1 and 61% on Grade-2 BrailleBench, outperforming standalone VLMs and achieving the highest Grade-2 exact match score among the evaluated systems. We further show that high accuracy on synthetic validation data does not guarantee high accuracy on real photographs in our experiments: models trained on prior synthetic data reach up to 96% on their synthetic validation set but at most 3.26% on Grade-1 BrailleBench. Our results identify an accessibility-relevant capability gap in multimodal systems and show that targeted synthetic supervision can improve real-world Braille transcription.

Fonte: arXiv cs.CV

NLP/LLMs • Score 85

Diagnosing and Correcting Bias in MLLM for Long Video Understanding

arXiv:2610.36210v1 Announce Type: new Abstract: Long-video question answering is challenging since the answer often hinges on a few decisive moments scattered throughout the video, while memory constraints force Multimodal Large Language Models (MLLMs) to sample frames at extremely low rates, resulting in sparsity that risks omitting key evidence. Though aggressively enlarging the context size is intuitive, we argue that performance remains fundamentally constrained by the bias, \emph{i.e.}, the misleading cues caused by spurious \textit{linguistic} correlations and salient yet irrelevant \textit{visual} observations. In this paper, we first introduce {S-MME}, a benchmark designed to systematically diagnose shortcut-biased behavior in MLLMs. To mitigate this failure, we further propose a training-free framework, Counterfactual Long-video Evidence-Aware Reasoning (CLEAR). By treating the full video-question pair as a complete view, CLEAR estimates bias effects via augmented views by only keeping the question or locally salient visual clips. Then, we intervene hidden states to mitigate the discrepancy at inference such that the correct answer can be predicted confidently. With experimental studies across five benchmarks, we show that our method is generalizable and can be integrated in different MLLMs, yielding consistent gains in prediction and robustness. We hope CLEAR can offer a complementary direction in test-time scaling for long-video understanding.

Fonte: arXiv cs.CV

Vision • Score 85

Any3R: Feedforward 3D Reconstruction from Any Camera Type

arXiv:2610.36150v1 Announce Type: new Abstract: Geometry foundation models recover camera poses and dense geometry from a set of images with a feed-forward network, but they expect pinhole images. That assumption is inside the backbone too: the positional encoding and the training loss both bind an image position to a direction in space, and both depend on the lens. We condition both on the dense ray field, the unit direction through every pixel, which describes any central camera without a lens type, distortion coefficients or a bound on field of view. Angular coordinates give the rotary encoding the measured ray angle of each patch, evaluated per view, and solid-angle weighting scales the point loss by the area each pixel covers on the sphere, so neither the encoding nor the supervision depends on the lens. Any3R is therefore a feed-forward model that takes any central camera, and is robust to mixing many camera types per scene, with no retraining per lens. On a benchmark of thirteen central cameras across three datasets, where every method reconstructs with its own predicted camera poses, it is the most consistently accurate method. Any3R enables scalable 3D reconstruction from heterogeneous crowdsourced and archival imagery collections sourced across diverse camera types. Project page: https://jingong-chen.github.io/Any3R/

Fonte: arXiv cs.CV

NLP/LLMs • Score 85

CRLoMTL: Conflict-Resolution through Low-rank matrices for Multi-Task Learning

arXiv:2610.36337v1 Announce Type: new Abstract: Multi-task learning (MTL) improves model efficiency by sharing representations across related vision tasks, but it often suffers from negative transfer when task updates interfere with one another. Existing conflict-mitigation methods typically operate in gradient space, requiring explicit task-gradient manipulation and additional optimization steps. We propose Conflict-Resolution through Low-Rank Matrices for Multi-Task Learning (CRLoMTL), a parameter-efficient framework that mitigates task interference in the low-rank parameter-update space. CRLoMTL learns task-specific LoRA updates through task-specific passes, where each task updates its own low-rank matrices, and integrates these updates through global shared-subspace fusion. Specifically, we introduce a shared-subspace resolver based on singular value decomposition (SVD), referred to as the SVD resolver, which extracts a common low-dimensional orthonormal basis across task adapters and projects task updates into this shared space before merging them into a single deployment-time update. The resulting update can be folded into the backbone, preserving the inference structure of the original model without additional runtime branches. Experiments with Swin Transformer backbones on PASCAL-Context, NYUD-v2, and CelebA show that CRLoMTL achieves a favorable accuracy-parameter trade-off, improving over single-task baselines by up to 2.77% on PASCAL-Context, 5.03% on NYUD-v2, and 3.50% on CelebA, while training only a small fraction of the parameters used by single-task models.

Fonte: arXiv cs.CV

Vision • Score 85

UT-HMR: Uncertainty-Guided Temporal Modeling for Robust 3D Human Mesh Recovery

arXiv:2610.36203v1 Announce Type: new Abstract: Monocular 3D human mesh recovery (HMR) remains unreliable under weak observations caused by long camera-to-person distances, occlusion, and motion blur. In challenging scenarios such as sports, these factors make the problem highly ambiguous, as different 3D poses may yield similar 2D projections. This ambiguity is especially severe for one-stage HMR, which recovers all meshes directly from the full image without person crops or external 2D cues. To handle this ambiguity, we present UT-HMR ( Uncertainty-guided Temporal HMR), to our knowledge the first one-stage HMR framework to capture correlated pose uncertainty across joints. Each person query predicts a Gaussian distribution over the full SMPL pose with a compact low-rank-plus-diagonal covariance, which is converted into joint-wise precision weights for heteroscedastic supervision while keeping inference deterministic. Temporal early fusion further injects neighboring-frame evidence before pose decoding, supplying the visual evidence needed to resolve the ambiguity that the uncertainty captures. With a lightweight ViT-B backbone, UT-HMR achieves state-of-the-art results on VIP-HockeyPose-v2 (ice hockey) and WorldPose (soccer), reducing MPJPE, PA-MPJPE, and PVE by up to 4.7%, 3.8%, and 5.6%, and remains competitive on 3DPW against methods with larger backbones and higher input resolutions.

Fonte: arXiv cs.CV

Vision • Score 85

SAGE: Semantic-Augmented Geometric Experts for Point Cloud Registration

arXiv:2610.36658v1 Announce Type: new Abstract: Point cloud registration is an essential task for scene reconstruction, requiring the alignment of partially overlapping point clouds. Under low-overlap conditions, this task remains challenging because existing geometry-only methods cannot distinguish geometrically similar but semantically distinct structures (e.g., TV corners vs. desk corners and chair legs vs. table legs), resulting in incorrect correspondences. To address this geometric ambiguity, we present Semantic-Augmented Geometric Experts (SAGE), which integrates frozen pre-trained point cloud semantic representations into the registration pipeline without requiring additional sensors or fine-tuning the semantic encoder. To effectively leverage these semantic distinctions, SAGE employs a Semantic-Guided Mixture of Experts (SG-MoE) architecture. Through semantic-aware routing, SG-MoE enables each expert to specialize in distinct semantic-geometric patterns, reducing mismatches that confound geometry-only methods. With a structure-aware estimator, SAGE achieves the highest registration recall on 3DLoMatch while remaining competitive on 3DMatch. When evaluated with the same number of refinement iterations, SAGE further achieves the highest inlier ratio and registration recall on both benchmarks. These results indicate that frozen semantic representations provide effective cues for resolving geometric ambiguity in low-overlap registration.

Fonte: arXiv cs.CV

NLP/LLMs • Score 85

Beyond the Estimate: Wiener-Informed Decoding for Easier Training of Pixel-Space Flow Models

arXiv:2610.36192v1 Announce Type: new Abstract: Learning velocity fields directly in pixel space is difficult and slow. We show that coarse second-order image statistics can ease this task: frozen Wiener estimates improve velocity learning, with gains extending beyond the linear predictions they explicitly provide. Moreover, we observe similar but complementary gains from frozen bases and pixel decoding. These observations motivate Wiener-informed Decoding (WiD), which uses statistical knowledge both for direct prediction and to organize decoder computation without modifying native blocks. WiD combines a trainable Wiener prediction path with coefficient interfaces that inject features into the native decoder and return its predicted coefficient corrections, with these components initialized with data statistics. All introduced parameters, including the spectrum and coordinate transforms, are trained jointly under the original pixel-space velocity objective. Across model scales and decoder architectures, WiD accelerates training and improves generation quality with modest parameter overhead. It also yields smoother gradient trajectories and remains effective with representation alignment. WiD improves class-conditional and text-to-image generation across different resolutions. On ImageNet 256 x 256, PixelDiT-XL with WiD reaches FID 1.53 after 500 epochs, achieving comparable quality to PixelDiT with 37.5% fewer training epochs. Statistical denoisers contribute beyond the estimate: their computational structure can also ease pixel-space training.

Fonte: arXiv cs.CV

Vision • Score 85

Task-Utility IQA: Rethinking Image Quality Assessment in Embodied Tasks

arXiv:2610.35905v1 Announce Type: new Abstract: Image quality assessment (IQA) underpins embodied imaging pipelines by judging whether visual quality satisfies downstream tasks, yet most existing methods learn task-agnostic scores aligned with generic human ratings on static benchmarks. This objective mismatches embodied and interactive settings, where image adequacy depends on task goals, context, and action requirements that shape an agent's decisions. We argue that IQA should shift from score regression to goal-conditioned judgment defined by embodied task utility. To this end, we propose an MLLM-based embodied IQA agent framework that reasons about task requirements, grounds quality evidence, and produces decision-facing assessments. A compact VisDrone evidence study shows that conventional perceptual metrics and generic MLLM-based IQA scores are weak proxies for downstream VLM task success, while a task-conditioned utility score better predicts whether visual input supports the target task. These findings support a task-utility-oriented reframing of IQA for embodied, explainable, and decision-aware visual perception.

Fonte: arXiv cs.CV

Vision • Score 85

BoxWorld: Let World Engines Control and Video Generators Render

arXiv:2610.36371v1 Announce Type: new Abstract: We tackle the challenge of building real-time interactive video worlds with user-defined behaviors. Such worlds must track object states, apply interaction rules, and render the resulting consequences as users act. Yet existing end-to-end video world models typically learn interaction dynamics within the generator, making it difficult to specify object-level rules and reason about their consequences. In this work, we introduce BoxWorld, which separates interaction reasoning from generative rendering. Given user-specified rules, a coding agent creates a Box World Engine that determines interaction outcomes and exposes the resulting object states through a lightweight interface of layout boxes, persistent object attributes, and dynamic status variables, leaving appearance and physical effects to generative rendering. A Box-State Generative Renderer then renders this evolving state stream into video autoregressively, enabling online control over object motion, state switches, and conditional events. Rendering this state stream is non-trivial: the renderer must respond to object-level state updates in real time while remaining coherent with the generated history. To this end, we introduce a three-stage training strategy that learns object grounding from open-domain videos and state transitions from gameplay videos, both annotated automatically, and finally performs rollout distillation on self-generated histories. We further propose PairedStateBench, a paired benchmark for fine-grained interaction control. BoxWorld substantially outperforms end-to-end world models and remains competitive across multiple public benchmarks. Project page: https://boxworld-web.github.io.

Fonte: arXiv cs.CV

Vision • Score 85

ObjectTwin: Measuring the Asset Correspondence Gap for Capture-Anchored Digital Twins

arXiv:2610.35904v1 Announce Type: new Abstract: Object-wise reconstruction increasingly inserts generated meshes into captured scenes as editable proxies for observed objects. This use creates a requirement absent from isolated-asset scores and pose estimates: at the captured metric state, the proxy should reproduce calibrated observations of the same instance. We present ObjectTwin, a scan-grounded measurement protocol that freezes the instance, cameras, scan-projected support and recorded depth, metric anchor, and evaluation denominator, then replaces only the object representation. The resulting asset correspondence gap measures lost observation agreement relative to scan-derived visible geometry without treating the scan as complete physical ground truth. Across two indoor RGB-D capture domains and two generation backends, visible, anchored generated assets lose 0.302-0.497 MaskIoU under this replacement. Every tested scene-level estimate is positive, while same-input generator preference reverses across capture domains. Coverage and overlap-depth analyses locate disagreement in both visible support and surface placement; the evaluated conservative pose refinement does not systematically recover it. These results establish capture correspondence as a separately measurable interface between generated-asset quality and stronger physical or task-level evaluation.

Fonte: arXiv cs.CV

NLP/LLMs • Score 85

Variational Atlas Autoencoders and Self-Supervised Chart Selection

arXiv:2610.33577v1 Announce Type: new Abstract: Complex, high-dimensional data lie on manifolds that a single global latent coordinate system cannot represent without distortion. We introduce Variational Atlas Autoencoders, a mixture-of-charts framework that learns an atlas of local latent representations, each responsible for one region of the data manifold. The central difficulty in learning an atlas is deciding which chart should be responsible for which data point without labels. We show that this decision need not be a heuristic. By treating the chart index as a latent variable, the evidence lower bound yields the training objective and casts chart assignment as posterior inference, valid for any routing distribution. Within this framework, we propose latent-evidence routing, which assigns a point to a chart in proportion to the evidence of its encoding under that chart's latent prior. This has a simple interpretation: the closer a point lands to the center of a chart's latent space, and the more confidently it is placed there, the more likely it is to belong to that chart. Chart assignment thus emerges as posterior inference, depends on the encoder alone, and is fully self-supervised, so the charts discover structure in the data on their own, separating classes and subclasses such as distinct types of shoes or faces without access to labels. We further recover an atlas from the trained charts by identifying their overlaps and transition maps, enabling continuous interpolation within and across charts that stays close to the data manifold rather than traversing unsupported regions of latent space. Compared to capacity-matched baselines, Variational Atlas Autoencoders yields better-structured latent spaces and higher sample quality on image datasets including CelebA, while sampling requires evaluating only a single chart's decoder.

Fonte: arXiv cs.LG

NLP/LLMs • Score 85

OmniBrain-0: A Unified Agentic Model for Embodied Intelligence

arXiv:2610.36013v1 Announce Type: new Abstract: General-purpose embodied intelligence requires robots to coordinate diverse skills over long horizons, track task progress, and recover from failures. Specialist policies alone do not ensure task-level reliability, while powerful multimodal agents rely on costly reasoning and external experience that compact models struggle to reproduce. We introduce OmniBrain-0, a lightweight unified embodied agent that coordinates manipulation and navigation through a shared high-level decision model, integrating task understanding, planning, progress tracking, and feedback-driven recovery. Our progressive training framework combines embodied pretraining, domain-specialized agent distillation, and multi-teacher on-policy distillation (MOPD). It distills powerful teachers' interaction experience into manipulation and navigation experts, then consolidates their decision capabilities into OmniBrain-0. Unification therefore occurs within the learned decision model rather than only at the tool interface. We further introduce Rubric-Guided Recursive Self-Improvement (RSI), a data flywheel in which a Meta-Agent turns execution evidence into refined rubrics, step-level reminders, and verified trajectories for domain-expert updates before their reconsolidation into OmniBrain-0 through MOPD. We evaluate OmniBrain-0 on LIBERO-Pro, LIBERO-Plus, RoboCasa365, RoboTwin 2.0, and R2R-CE Val-Unseen, as well as multiple real-world manipulation tasks. OmniBrain-0 combines strong cross-domain task performance with substantially lower inference and execution overhead than its closed-source teacher, demonstrating efficient transfer and consolidation of embodied capabilities into a compact unified agent.

Fonte: arXiv cs.CL

NLP/LLMs • Score 85

FG-ConvNO: A Geometry-Aware Neural Operator for Propeller CFD Prediction

arXiv:2610.33456v1 Announce Type: new Abstract: Computational Fluid Dynamics (CFD) is essential in contemporary engineering design, yet it remains expensive to compute and can take thousands of CPU/GPU hours or more for a single high-fidelity simulation. Recent developments in machine learning for scientific modeling have led to powerful surrogate frameworks that can approximate flow fields and physical quantities by using a fraction of the computational cost. However, most of these methods require largescale homogeneous datasets or simple geometries, exhibiting severe generalization gaps when applied to complex and data-scarce configurations. To address this, we propose the Factorized Geometry Convolutional Neural Operator (FG-ConvNO) for robust geometry-aware propeller pressure prediction under limited training data. We introduce geometryaware encoding, efficient interpolation-based decoding, and auxiliary global quantity supervision. In addition, we incorporate DISCO blocks that use discrete continuous convolutions to make the model discretization agnostic. In our experiments, FG-ConvNO achieves the highest accuracy for both surface pressure and global thrust prediction on a procedurally generated propeller CFD dataset. Geometry-aware encoding and architectural simplification improve stability, while random vertex subsampling enhances robustness. Overall, adding geometric priors to grid-based convolutional operators reduces overfitting on complex propeller geometries and improves generalization in low-data regimes.

Fonte: arXiv cs.LG

NLP/LLMs • Score 85

Learning Where to Trust: Reliability-Guided Expert Routing and Velocity Gating for 3D Deformable Registration

arXiv:2610.36672v1 Announce Type: new Abstract: Deformable image registration relies on accurate anatomical correspondences. However, explicitly coupling local matching reliability with spatial context selection and deformation update strength remains insufficiently explored in learning-based registration. This challenge is particularly pronounced in homogeneous, weakly textured, and severely deformed regions, where ambiguous matches may induce erroneous deformation updates. We propose ReliMorph, a reliability-routed symmetric framework for 3D deformable registration that couples correspondence assessment with spatial context selection and update strength.Local correlation distributions characterize correspondence ambiguity using shared anatomical features with modality-specific adaptation. These reliability cues guide spatial expert fusion and gate residual velocities during coarse-to-fine refinement. Updated inverse-inconsistency feedback guides routing and gating at finer pyramid levels. To our knowledge, ReliMorph is the first 3D deformable registration framework to jointly condition spatial expert routing and residual velocity gating on correspondence reliability. Extensive experiments demonstrate that ReliMorph consistently outperforms competing methods in anatomical overlap, highlighting its effectiveness across unimodal and multimodal registration tasks.

Fonte: arXiv cs.AI

NLP/LLMs • Score 85

Adapting Video Models for Robot Control via Motion-guided Asymmetric Prediction

arXiv:2610.36624v1 Announce Type: new Abstract: World Action Models (WAMs) leverage pretrained video generative models for robotic control by jointly predicting future visual observations and actions. The visual prediction objective plays a key role in adapting pretrained video representations to the target robot domain. Yet standard visual prediction inherited from video pretraining treats all visual regions uniformly, despite their differing relevance to robotic control. We therefore investigate the spatial allocation of visual supervision in WAMs and show that focusing supervision on dynamic regions can substantially improve policy performance. Building on this finding, we introduce Motion-Guided Asymmetric Prediction (MoGAP), which augments WAM training with motion-focused visual prediction. MoGAP allocates noise asymmetrically across regions, training the model to reconstruct more heavily corrupted dynamic regions using less corrupted static regions as context. MoGAP is trained alongside standard video-action prediction through a training-only auxiliary prediction path within the shared video diffusion backbone. It uses motion cues derived directly from training videos, requiring neither an external teacher nor additional modalities. Across robot manipulation benchmarks and WAM architectures, MoGAP consistently improves policy performance, increasing success rates on the GR-1 tabletop benchmark from 38.8% to 47.5% for Fast-WAM (Wan2.2-5B) and from 52.3% to 62.3% for Cosmos3-Nano.

Fonte: arXiv cs.CV

Vision • Score 85

4D Reconstruction with Events & RGB

arXiv:2610.36610v1 Announce Type: new Abstract: Reconstructing dynamic 3D scenes over time (4D reconstruction) from a single moving camera is central to robotics and AR/VR applications, yet state-of the-art feed-forward methods rely solely on RGB frames and therefore inherit the failure modes of conventional cameras, including motion blur and temporal aliasing under fast or non-uniform camera and object motion. Event cameras report per-pixel brightness changes asynchronously at microsecond resolution, offering a complementary signal that is largely immune to these artifacts, but whether this modality can be incorporated into existing RGB based 4D reconstruction pipelines without a full architectural redesign remains an open question. In this preliminary study, we investigate a minimal extension: we augment Monst3R, an existing RGB-only 4D reconstruction model, with an additional event-camera input branch, leaving the rest of the architecture unchanged. Across 3 benchmark datasets, this simple RGB-event fusion reduces Abs Rel by 3.4% on average relative to the RGB-only Monst3R baseline, and a sensitivity analysis shows that the improvement grows with the magnitude of camera and object motion, with the largest gains observed under high object motion conditions where RGB-only reconstruction degrades most. These early results suggest that even a lightweight, non-invasive fusion of event data can meaningfully improve 4D reconstruction robustness, motivating a more thorough architectural investigation in future work.

Fonte: arXiv cs.CV

Vision • Score 85

GeoGSplat: Geometry-Grounded Non-Pixel-Aligned Gaussian Splatting

arXiv:2610.36760v1 Announce Type: new Abstract: Feed-forward Gaussian Splatting enables efficient novel view synthesis, but pixel-aligned prediction makes the primitive count grow with image resolution and view count, leading to substantial redundancy and increased computational cost. Non-pixel-aligned methods address this limitation by predicting a fixed number of Gaussians. Without explicit ray and depth constraints, these methods yield misplaced Gaussian centers, causing rendering artifacts under large viewpoint changes. To address this issue, we introduce GeoGSplat, a geometry-grounded feed-forward model that explicitly incorporates geometric priors into the non-pixel-aligned framework. A dual-branch encoder constructs Anchors and Triplane to capture coarse 3D structure and fine-grained scene features, respectively. Subsequently, a hierarchical decoder progressively decodes dense 3D points and Gaussian primitives, enabling 3D reconstruction and novel view synthesis. GeoGSplat surpasses both state-of-the-art pixel-aligned and non-pixel-aligned Gaussian Splatting methods on DTU and NRGBD in terms of novel view synthesis and reconstruction. The advantage of our geometry-grounded paradigm further increases as target viewpoints move farther from the input cameras, demonstrating stronger generalization to large viewpoint changes. Project Page: https://comedy0913.github.io/projects/geogsplat

Fonte: arXiv cs.CV

NLP/LLMs • Score 85

Polarity--Time Interaction and Multi-Level Reliability for Event-Based Spacecraft Pose Estimation

arXiv:2610.36625v1 Announce Type: new Abstract: Sparse event responses produce uneven keypoint errors whose effects on spacecraft pose depend on correspondence geometry and the reliability of successive observations. We present a reliability-aware framework connecting polarity--time localization, geometric recovery, event--CAD refinement, and trajectory optimization. A three-branch representation combines positive events, negative events, and recent-event timing through cross-branch attention and gating, followed by spatiotemporal aggregation. An ordered semantic-point head estimates relative correspondence precision for geometrically constrained pose recovery. Event-edge and CAD-projection agreement then guide local pose refinement under keypoint-geometry safeguards. At the sequence level, a ten-dimensional descriptor combines heatmap shape, reprojection consistency, and geometric conditioning to set time-aligned observation scales. On the official SPADES challenge test set, the complete system achieves a combined pose score of 0.0474, approximately 5.4\% below PASAN+IRIS. Validation ablations reduce the score from 0.0772 for base localization with uniform PnP to 0.0514 for the complete cascade; on identical single-frame observations, quality weighting reduces the score from 0.0549 with constant-weight optimization to 0.0514.

Fonte: arXiv cs.AI

Vision • Score 85

A Heart Means Recursion: Exploring Visual Meaning and Communication in VLMs

arXiv:2610.36449v1 Announce Type: new Abstract: Do vision-language models (VLMs) share our ability to communicate visually? We share preliminary findings, starting from a surprising observation: simple visual symbols like a red heart can strongly influence model behavior on seemingly unrelated tasks, such as steering models towards recursive solutions on simple coding problems. Notably, this steering effect is largely implicit, as models' direct interpretations and thinking traces about visual symbols diverge substantially from their observed behavior. In visual communication between models, this leads to a generation--interpretation gap: while models tend to send shape primitives that they (and humans) find intuitive, these visual cues often fail to steer other models. In further communication games involving abstract concepts and stories, models can creatively use visuals to transmit meaning to one another, although some communications remain non-intuitive to humans. These findings reveal that VLMs might be capable of rich, creative, and visually-grounded communication, but their interpretation and production of visual meaning diverges from human conventions in surprising ways. Together this work highlights both the promise and challenges of visual communication between humans and VLMs.

Fonte: arXiv cs.AI

NLP/LLMs • Score 85

Enhancing Deep Learning Model Performance through Data Generation Strategies: Classification of Olive Tree Diseases

arXiv:2610.35984v1 Announce Type: new Abstract: Deep learning models are highly effective in a wide range of domains, particu larly in plant disease diagnosis. However, their performance is often limited by challenges such as insufficient data and class imbalance. In our work, we propose a comprehensive data generation strategy to overcome these limitations. First, we apply various data generation techniques, including traditional augmentation methods, CutMix, MixUp, and synthetic image generation using Deep Convolu tional Generative Adversarial Networks (DCGANs), to create new data samples. Second, we exploit this generated data in three scenarios: (S1) balancing class distribution in the original dataset, (S2) increasing the number of samples per class, and (S3) expanding the dataset while maintaining balanced classes. Third, we evaluate the impact of these data distributions (S1, S2, S3) on model perfor mance using the EfficientNetV2B0 architecture with pre-trained and fine-tuned weights. The experimental results show a substantial improvement in classifica tion accuracy, emphasizing the critical role of data diversity and class balance. These findings highlight the effectiveness and adaptability of the proposed strat egy of data generation and distribution for enhancing dataset quality, offering promising applications in plant disease detection and precision agriculture.

Fonte: arXiv cs.AI

NLP/LLMs • Score 85

Generative Refinement Learning for Temporal Interpolation in Scientific Machine Learning

arXiv:2610.36751v1 Announce Type: cross Abstract: Computationally expensive simulations and real-world observations often provide data at a lower temporal resolution than downstream tasks require. Averaging observations at fixed grid points can introduce errors, and motion estimates alone do not determine how the physical field values change. In this work, we study whether learning to correct a simple numerical interpolation improves the reconstruction of intermediate scientific fields. Our model, interpolative FLow EXpert (iFLEX), first estimates the missing field by taking a weighted average of the two observations at each grid point, giving more weight to the observation closer to the requested time. During training, subtracting this estimate from an observed intermediate field gives the residual that a conditional diffusion model learns to generate. Both observations condition the model, together with the target time, the interval between observations, and available physical parameters. To reconstruct an unobserved intermediate field, the generated residual is added to the weighted average. We evaluate iFLEX on Navier-Stokes Kraichnan turbulence, Shanghai radar precipitation, and sea surface temperature. Across these datasets, iFLEX achieves lower reconstruction error than the evaluated baselines, including optical-flow and diffusion models developed for video frame interpolation in computer vision. In a controlled turbulence comparison at a Reynolds number of 36,000, learning the residual reduces relative Frobenius norm error from about 13.7 for direct field generation to 10.5, with the diffusion backbone and training setup held fixed. Code is available at https://github.com/paulpuren/iflex.

Fonte: arXiv stat.ML

NLP/LLMs • Score 85

Haste Makes Waste? Towards Safe Few-Step Text-to-Image Models

arXiv:2610.36665v1 Announce Type: new Abstract: While few-step distilled text-to-image models have gained traction due to their fast generation times, the speed-up implications on their unsafe generation rates remain unknown. We uncover an inherent tension between speed and safety: few-step models are often more unsafe than their teachers, and reducing the number of inference steps consistently raises unsafe generation rates. We further find that acceleration makes unsafe concepts harder to erase in few-step models, with existing concept-erasure methods markedly less effective than in teachers. We offer a mechanistic diagnosis for why erasure methods fail on few-step models, finding that the fragility of few-step models' generation process and the way generation guidance is usually distilled into those models may hinder established concept-erasure methods. To address the speed-safety trade-off, we propose DICE (Distillation-Integrated Concept Erasure), a post-distillation erasure method tailored for few-step models. DICE aligns both its latent construction and its generation-preservation loss with the distillation method that produced the model, keeping erasure faithful to few-step models. DICE demonstrates strong results in our evaluation. For example, on FLUX Schnell, DICE reduces unsafe-generation rate to 0.046 (vs. at least 0.161 for prior erasure methods we test), while mostly preserving benign generation quality.

Fonte: arXiv cs.CV

Vision • Score 85

Multi-task Disentangling Fusion Mamba-CNN for MODIS Spectral-Temporal Unmixing with Endmember Variability Modeling

arXiv:2610.36750v1 Announce Type: new Abstract: Spectral-temporal unmixing of MODIS time series is essential for applications such as abundance mapping and spectral library construction, yet it remains challenging due to (i) spectral-temporal information coupling in MODIS data, (ii) intra-class endmember spectral variability and inter-class signature ambiguity, and (iii) the instability of naively fusing multiple expert representations. This paper presents the Multi- task Disentangling Fusion Mamba (MDF-Mamba) to address these limitations. To resolve spectral-temporal coupling, we design a disentangling architecture that pairs per-channel spectral experts with a dedicated bidirectional state-space (Mamba) temporal branch. Convolutional modules each process a single spectral channel, while the Mamba branch encodes the cross-channel seasonal trajectory, forming a multi-branch expert ensemble with soft inter-expert reweighting based on squeeze-and-excitation. For the integration of these spectral and temporal expert outputs, we introduce mHCFusion, adapting the manifold-constrained hyper-connection framework to merge the outputs in a stable and interpretable manner. Endmember variability is addressed by extending the linear mixing model with pixel-wise learnable spectral variability weights that capture intra-class endmember variation. Finally, we design a multi-task training objective that combines supervised abundance estimation with self-supervised spectral reconstruction and endmember regularization terms on the same training data, yielding a highly efficient framework for spectral-temporal unmixing. Experiments on MODIS time series covering the Alberta and Saskatchewan provinces show that MDF-Mamba achieves the best performance on 12 of 14 evaluation metrics across both datasets (7 of 7 on Alberta; 5 of 7 on Saskatchewan), ranking second on the remaining two.

Fonte: arXiv cs.CV

NLP/LLMs • Score 85

FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation

arXiv:2610.36545v1 Announce Type: new Abstract: Unified conditional image generation requires a single model to preserve different aspects of a visual input while producing a target image that follows textual guidance. Pretrained video models provide a promising foundation by encoding visual transformations across time, yet existing approaches typically assign the condition and target to fixed temporal positions. We observe that condition-target relationships vary substantially across generation tasks, while video models naturally encode visual transformations at different temporal scales. This motivates us to model conditional generation through input-adaptive virtual temporal relations. We propose FrameForge, which captures two complementary aspects of such relations. Mixture of Temporal Experts (MoTE) models how far the target lies from the condition by dynamically selecting temporal RoPE experts with different virtual intervals. Chain of Temporal Reasoning (CoTR) models how the condition is transformed into the target through a latent intermediate state, with a reasoning-bottleneck attention mask encouraging information propagation through this pathway. Experiments on DreamBench, COCO2017, and GEdit-Bench show that FrameForge achieves superior performance in subject-driven generation, canny-to-image generation, and image editing among the compared methods.

Fonte: arXiv cs.CV

Vision • Score 85

Vision Token Pruning via Query-Vision Interaction Decomposition

arXiv:2610.33215v1 Announce Type: new Abstract: Large vision-language models (VLMs), which process both visual inputs and text queries, incur high inference costs due to the large number of visual tokens, making visual token pruning a natural approach for improving efficiency. Recent work has leveraged query information to guide token selection, often through heuristics derived from attention patterns or token dynamics. However, these approaches do not explicitly exploit the underlying structure of query-vision interactions. We address this gap by observing that the query-vision interaction matrix, naturally induced by the query and key projections already present in transformer attention, is effectively low-rank, with a small number of dominant latent interaction modes capturing query-relevant semantics. Motivated by this observation, we propose Query-Vision Decomposition (QViD), a novel training-free query-aware visual token pruning method that exploits this structure. Extensive experiments on both image and video understanding benchmarks show that QViD consistently improves performance under matched token budgets, with the largest gains appearing under aggressive compression regimes.

Fonte: arXiv cs.LG

Vision • Score 85

Evaluation-Guided Demonstration Refinement for Vision-Language-Action Policies: The Winning Entry in the MetaFine Open Competition

arXiv:2610.36765v1 Announce Type: new Abstract: We fine-tuned a separate $\pi_{0.5}$ policy for each of the five tasks in the MetaFine Open Competition, with a task-specific training mixture and number of actions executed per prediction. Training started from the official demonstrations and expert procedures. Local evaluation exposed recurring grasping, pushing, and insertion failures. We addressed them by revising the demonstrated motions and by adding expert continuations from states the policy reached, while keeping nominal demonstrations in training. Checkpoints were compared on every instruction, so that a gain on one instruction could not hide a loss on another. Our submission, MAI, ranked first overall with a score of 96.66.

Fonte: arXiv cs.CV

Vision • Score 85

Hy-Nomas: Towards Free-form Interactive World Generation

arXiv:2610.36729v1 Announce Type: new Abstract: Interactive world generation requires models to follow successive commands while preserving relevant history and action consequences. We present Hy-Nomas, a video world model with an 8B diffusion backbone that supports free-form text instructions and continuous camera control across multiple interaction turns. It generates variable-length segments conditioned on current inputs and cached history. Our central design aligns structured video captions with action-aware causal attention: descriptive context remains accessible across segments, while action instructions are restricted to their intended temporal windows. A vision-language Prompt Enhancer (PE) translates user requests and multimodal interaction histories into structured conditions for the next segment. A multi-stage curriculum progressively introduces causal generation, text interaction, camera control, and training on model-generated histories, followed by diffusion distillation. In human evaluation, Hy-Nomas shows superior performance over existing world models. We release model weights, code and benchmarks, together with a lightweight adaptation workflow, to support reproducible research on interactive world generation.

Fonte: arXiv cs.CV

Vision • Score 85

SAGE: Saliency-Annealed Gated Encoder for Universal Vision Recognition

arXiv:2610.36719v1 Announce Type: new Abstract: When adapting self-supervised Vision Transformers (ViTs) to dense prediction, existing methods often treat the ViT as a passive feature extractor and may underuse the rich priors encoded in its representations, including saliency, global context, and high-frequency details. We propose SAGE (Saliency-Annealed Gated Encoder), an enhanced ViT-Adapter backbone that explicitly exploits these priors through three complementary innovations: (1) a saliency-guided architecture that extracts DINO-style class-token (CLS) saliency to guide feature gating and high-frequency enhancement, together with dynamic multi-layer aggregation and a local-detail branch; (2) an annealing-based training paradigm designed to improve convergence and feature quality during early training while reducing feature drift later in training; and (3) a two-stage, quality-aware training mechanism that smoothly transitions from focal loss to Varifocal Loss (VFL) within a single training run. Across the evaluated tasks (Fig.~\ref{fig:fig_com}), SAGE achieves state-of-the-art (SOTA) or competitive results on COCO (62.8 box AP and 55.3 mask AP), COCO keypoint estimation (78.5 AP), ADE20K (60.3 mIoU for semantic segmentation and 44.9 mask AP for instance segmentation), TinyImageNet classification (94.76\% Top-1 accuracy), and DIOR-R oriented object detection (78.8 AP$_{50}$). The same backbone is used across tasks, with task-specific decoders. To the best of our knowledge, SAGE is the first framework to achieve multi-task state-of-the-art results on Huawei Ascend NPUs. Code and pretrained models will be released after internal review.

Fonte: arXiv cs.CV

Vision • Score 92

LociArt: A Unified Paradigm for Free-Style Local Video Stylization

arXiv:2610.36456v1 Announce Type: new Abstract: Video stylization typically transforms entire scenes, while local artistic editing requires precise region--style association, spatial control, and temporal consistency. We introduce LociArt, a unified paradigm for free-style local video stylization that explicitly specifies where to stylize and what style to apply while preserving non-target content. At its core, GRNStyle builds on Generative Refinement Networks (GRN) and introduces a polar style-aware mask that embeds style identities as equal-norm directions within selected regions. Complementary representation--geometry conditioning combines encoded mask features with raw-mask spatial support, integrating spatiotemporal context with geometric control. To provide paired supervision, we develop an automated pipeline combining global stylization, video object removal, matting, and compositing, and construct the LociArt-100K Dataset with 100K local stylization pairs. We further establish the LociArt Benchmark, comprising 80 source videos and 84 target masks covering 168 foreground/background stylization cases, with a Style Prototype Similarity (SPS) evaluation scheme for regional style quality and complementary measures of non-target preservation and temporal consistency. Experiments show that GRNStyle outperforms existing methods in regional style quality and spatial control while maintaining strong temporal consistency. Qualitative examples further illustrate joint stylization of multiple regions with the same or different learned styles, despite training only on single-region, single-style pairs. Together, these components provide a unified foundation for learning and evaluating controllable local video stylization. Project page: https://higherhu.github.io/lociart/.

Fonte: arXiv cs.CV