AIConfPaper
← All conferences

CVPR 2026 Accepted Papers

The full list of 4,067 papers accepted at CVPR 2026 (IEEE/CVF Conference on Computer Vision and Pattern Recognition). Click any title for details, similar papers, and links to the original source. You can also search these papers by meaning, not just keywords.

accepted: 4,067
  1. SAME: Sparse and Anchored Model Editing for Heterogeneous Incremental Learning under Limited Dataaccepted
  2. SAMIX: Reinforcing SAM2 with Semantic Adapter and Reference Selecting Policy for Mix-Supervised Segmentationaccepted
  3. SAMTok: Representing Any Mask with Two Wordsaccepted
  4. SAMosaic3D: Modular Scene Assembly for Real-Time 3D Segment Anythingaccepted
  5. SANER: Switchable Adapter with Non-parametric Enhanced Routing for Person De-Reidentificationaccepted
  6. SAQN: Semantic-based Adaptive Query Network for 3D Referring Expression Segmentationaccepted
  7. SAR2Net: Learning Spatially Anchored Representations for Retrieval-Guided Cross-Stain Alignmentaccepted
  8. SARL-STG: A Spatially Aware Reinforcement Learning Framework for Refining MLLMs in Spatio-Temporal Video Groundingaccepted
  9. SARMAE: Masked Autoencoder for SAR Representation Learningaccepted
  10. SASNet: Spatially-Adaptive Sinusoidal Networks for INRsaccepted
  11. SAT-RRG: LLM-Guided Self-Adaptive Training for Radiology Report Generation with Token-Level Push-Pull Optimizationaccepted
  12. SATTC: Structure-Aware Label-Free Test-Time Calibration for Cross-Subject EEG-to-Image Retrievalaccepted
  13. SAVA-X: Ego-to-Exo Imitation Error Detection via Scene-Adaptive View Alignment and Bidirectional Cross View Fusionaccepted
  14. SAVE: Speech-Aware Video Representation Learning for Video-Text Retrievalaccepted
  15. SCAPO: Self-Supervised Category-Level Articulated Pose Estimation from a Single 3D Observationaccepted
  16. SCE-Depth: A Spherical Compound Eye Framework for Wide FOV Depth Estimationaccepted
  17. SCE-SLAM: Scale-Consistent Monocular SLAM via Scene Coordinate Embeddingsaccepted
  18. SCIEval: Evaluating and Benchmarking the Faithfulness of Scientific Image Generation and Interpretation with Large Multimodal Modelsaccepted
  19. SCoRe: Salience-Coverage Reduction for Vision Token Pruning in Vision-Language Modelsaccepted
  20. SD-FSMIS: Adapting Stable Diffusion for Few-Shot Medical Image Segmentationaccepted
  21. SDDF: Specificity-Driven Dynamic Focusing for Open-Vocabulary Camouflaged Object Detectionaccepted
  22. SDGS: Spatial Difference Guided Gaussian Splatting for Simultaneous Localization and 3D Reconstructionaccepted
  23. SDTrack: A Baseline for Event-based Tracking via Spiking Neural Networksaccepted
  24. SDUIE: Semi-Supervised Diffusion for Underwater Image Enhancement with Quant-Text Dual Controlaccepted
  25. SE(3)-Equivariance with Geometric and Topological Guidance for Category-Level Object Pose Estimationaccepted
  26. SEA-Flow3D: Simplified, Efficient, and Accurate Scene Flow via Spatial Vector Sampling and Multi-scale Refinementaccepted
  27. SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asiaaccepted
  28. SEA: Evaluating Sketch Abstraction Efficiency via Element-level Commonsense Visual Question Answeringaccepted
  29. SEASON: Mitigating Temporal Hallucination in Video Large Language Models via Self-Diagnostic Contrastive Decodingaccepted
  30. SEATrack: Simple, Efficient, and Adaptive Multimodal Trackeraccepted
  31. SEBA: Sample-Efficient Black-Box Attacks on Visual Reinforcement Learningaccepted
  32. SECOS: Semantic Capture for Rigorous Classification in Open-World Semi-Supervised Learningaccepted
  33. SFR-Net: Steering-Fusion-Refining Network in Multi-label Zero-Shot Sewer Defect Detectionaccepted
  34. SG-LoRA: Semantic-guided LoRA Parameters Generationaccepted
  35. SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAMaccepted
  36. SGDE: Self-supervised Geometry Degradation Estimation Framework for Coded Aperture Compressive Spectral Imagingaccepted
  37. SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Drivingaccepted
  38. SGI: Structured 2D Gaussians for Efficient and Compact Large Image Representationaccepted
  39. SGS-Intrinsic: Semantic-Invariant Gaussian Splatting for Sparse-View Indoor Inverse Renderingaccepted
  40. SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signalsaccepted
  41. SHAPE: Structure-aware Hierarchical Unsupervised Domain Adaptation with Plausibility Evaluation for Medical Image Segmentationaccepted
  42. SHARP: Short-Window Streaming for Accurate and Robust Prediction in Motion Forecastingaccepted
  43. SHOW3D: Capturing Scenes of 3D Hands and Objects in the Wildaccepted
  44. SHands: A Multi-View Dataset and Benchmark for Surgical Hand-Gesture and Error Recognition Toward Medical Trainingaccepted
  45. SIF: Semantically In-Distribution Fingerprints for Large Vision-Language Modelsaccepted
  46. SIGMA: A Physics-Based Benchmark for Gas Chimney Understanding in Seismic Imagesaccepted
  47. SIGMA: Selective-Interleaved Generation with Multi-Attribute Tokensaccepted
  48. SIMPACT: Simulation-Enabled Action Planning using Vision-Language Modelsaccepted
  49. SIMPLEPOSTER: A SIMPLE BASELINE FOR PRODUCT POSTER GENERATIONaccepted
  50. SIMSPINE: A Biomechanics-Aware Simulation Framework for 3D Spine Motion Annotation and Benchmarkingaccepted
  51. SIR: Structured Image Representations for Explainable Robot Learningaccepted
  52. SJD-PAC: Accelerating Speculative Jacobi Decoding via Proactive Drafting and Adaptive Continuationaccepted
  53. SLARM: Streaming and Language-Aligned Reconstruction Model for Dynamic Scenesaccepted
  54. SLVMEval: Synthetic Meta Evaluation Benchmark for Text-to-Long Video Generationaccepted
  55. SMAP: Semantic Route Planning with Map-Grounded Multimodal Alignmentaccepted
  56. SMRABooth: Subject and Motion Representation Alignment for Customized Video Generationaccepted
  57. SMV-EAR: Bring Spatiotemporal Multi-View Representation Learning into Efficient Event-Based Action Recognitionaccepted
  58. SMVRT: Implicit Human 3D Modeling Using Sparse Multi-View Volumetric Reconstruction with Transformer Fusionaccepted
  59. SO(3)-Equivariant ViT-Adapter for Data-Efficient Zero-Shot Sim-to-Real Indoor Panoramic Depth Estimationaccepted
  60. SO-Bench: A Structural Output Evaluation of Multimodal LLMaccepted
  61. SODA: Sensitivity-Oriented Dynamic Acceleration for Diffusion Transformeraccepted
  62. SOTA: Self-adaptive Optimal Transport for Zero-Shot Classification with Multiple Foundation Modelsaccepted
  63. SOUPLE: Enhancing Audio-Visual Localization and Segmentation with Learnable Prompt Contextsaccepted
  64. SPAN: Spatial-Projection Alignment for Monocular 3D Object Detectionaccepted
  65. SPAR: Single-Pass Any-Resolution ViT for Open-vocabulary Segmentationaccepted
  66. SPARK: Sim-ready Part-level Articulated Reconstruction with VLM Knowledgeaccepted
  67. SPARROW: Learning Spatial Precision and Temporal Referential Consistency in Pixel-Grounded Video MLLMsaccepted
  68. SPDMark: Selective Parameter Displacement for Robust Video Watermarkingaccepted
  69. SPE-MVS: Spatial Position Encoding Enhanced Multi-View Stereo with Monocular Depth Priorsaccepted
  70. SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understandingaccepted
  71. SPEGC: Continual Test-Time Adaptation via Semantic-Prompt-Enhanced Graph Clustering for Medical Image Segmentationaccepted
  72. SPOT: Spatiotemporal Prompt Optimization for Motion-Stabilized MLLM-Guided Video Segmentationaccepted
  73. SPREAD: Spatial-Physical REasoning via geometry Aware Diffusionaccepted
  74. SR3R: Rethinking Super-Resolution 3D Reconstruction With Feed-Forward Gaussian Splattingaccepted
  75. SRA 2: Variational Autoencoder Self-Representation Alignment for Efficient Diffusion Trainingaccepted
  76. SRA-Det: Learning Omni-Grained Open-Vocabulary Detection Beyond Category Namesaccepted
  77. SRGCD: Stability-Driven Region Growth Framework for 3D Change Detectionaccepted
  78. SRPO: Self-Referential Policy Optimization for Vision-Language-Action Modelsaccepted
  79. SSM-Aware Token-Efficient VMamba via Adaptive Patch Pruning and Merging for Person Re-Identificationaccepted
  80. ST4R-Splat: Spatio-Temporal Referring Segmentation in 4D Gaussian Splattingaccepted
  81. STAC: Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstructionaccepted
  82. STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot Narrativeaccepted
  83. STAR-R1: Multi-View Spatial TrAnsformation Reasoning by Reinforcing Multimodal LLMsaccepted
  84. STAR: Test-Time Adaptation Can Enhance Universal Prompt Learning for Vision-Language Modelsaccepted
  85. STARFlow-V: End-to-End Video Generative Modeling with Autoregressive Normalizing Flowsaccepted
  86. STAvatar: Soft Binding and Temporal Density Control for Monocular 3D Head Avatars Reconstructionaccepted
  87. STCDiT: Spatio-Temporally Consistent Diffusion Transformer for High-Quality Video Super-Resolutionaccepted
  88. STCast: Adaptive Boundary Alignment for Global and Regional Weather Forecastingaccepted
  89. STRNet: Visual Navigation with Spatio-Temporal Representation through Dynamic Graph Aggregationaccepted
  90. STUR3D: Spatio-Temporal Unified Representation Learning for 3D Object Detectionaccepted
  91. STiTch: Semantic Transition and Transportation in Collaboration for Training-Free Zero-Shot Composed Image Retrievalaccepted
  92. SToRe3D: Sparse Token Relevance in ViTs for Efficient Multi-View 3D Object Detectionaccepted
  93. SURF: Signature-Retained Fast Video Generationaccepted
  94. SV-GS: Sparse View 4D Reconstruction with Skeleton-Driven Gaussian Splattingaccepted
  95. SVAgent: Storyline-guided Long Video Understanding via Cross-Modal Multi-Agent Collaborationaccepted
  96. SVBench: Evaluation of Video Generation Models on Social Reasoningaccepted
  97. SVHalluc: Benchmarking Speech-Vision Hallucination in Audio-Visual Large Language Modelsaccepted
  98. SWIFT: Sliding Window Reconstruction for Few-Shot Training-Free Generated Video Attributionaccepted
  99. SaPaVe: Towards Active Perception and Manipulation in Vision-Language Action Models for Roboticsaccepted
  100. SafeDrive: Fine-Grained Safety Reasoning for End-to-End Driving in a Sparse Worldaccepted
  101. SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimizationaccepted
  102. SafeLogo: Turning Your Logos into Jailbreak Shields via Micro-Regional Adversarial Trainingaccepted
  103. SafeRoPE: Risk-specific Head-wise Embedding Rotation for Safe Generation in Rectified Flow Transformersaccepted
  104. Saliency-Driven Token Merging for Vision Transformersaccepted
  105. Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learningaccepted
  106. Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Rewardaccepted
  107. Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucinationaccepted
  108. Same Content, Different Answers: Cross-Modal Inconsistency in MLLMsaccepted
  109. Same or Not? Enhancing Visual Perception in Vision-Language Modelsaccepted
  110. Sampling-Aware Quantization for Diffusion Modelsaccepted
  111. Say Cheese! Detail-Preserving Portrait Collection Generation via Natural Language Editsaccepted
  112. Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstructionaccepted
  113. Scalable Feature Matching via State Space Modeling and Sparse Correlationaccepted
  114. Scalable Multi-View Subspace Clustering with Tensorized Anchor Guidanceaccepted
  115. Scalable Object Relation Encoding for Better 3D Spatial Reasoning in Large Language Modelsaccepted
  116. Scalable Trajectory Generation for Whole-Body Mobile Manipulationaccepted
  117. Scale Space Diffusionaccepted
  118. Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMsaccepted
  119. Scaling Dense Event-Stream Pretraining from Visual Foundation Modelsaccepted
  120. Scaling Instruction-Based Video Editing with a High-Quality Synthetic Datasetaccepted
  121. Scaling Multi-Identity Consistency for Image Customization via Multi-to-Multi Matching Paradigmaccepted
  122. Scaling Parallel Sequence Models to Vision Foundation Modelsaccepted
  123. Scaling Self-Supervised and Cross-Modal Pretraining for Volumetric CT Transformersaccepted
  124. Scaling Spatial Intelligence with Multimodal Foundation Modelsaccepted
  125. Scaling Test-Time Robustness of Vision-Language Models via Self-Critical Inference Frameworkaccepted
  126. Scaling Up AI-Generated Image Detection with Generator-Aware Prototypesaccepted
  127. Scaling View Synthesis Transformersaccepted
  128. Scaling Zero-Shot Reference-to-Video Generationaccepted
  129. Scaling the Long Video Understanding of Multimodal Large Language Models via Visual Memory Mechanismaccepted
  130. Scaling-Aware Data Selection for End-to-End Autonomous Driving Systemsaccepted
  131. Scaling4D: Pushing the Frontier of Video Novel View Synthesis through Large-Scale Monocular Videosaccepted
  132. Scan Clusters, Not Pixels: A Cluster-Centric Paradigm for Efficient Ultra-high-definition Image Restorationaccepted
  133. SceMoS: Scene-Aware 3D Human Motion Synthesis by Planning with Geometry-Grounded Tokensaccepted
  134. ScenDi: 3D-to-2D Scene Diffusion Cascades for Urban Generationaccepted
  135. Scene Grounding in the Wildaccepted
  136. Scene Reconstruction as Mapping Priors for 3D Detectionaccepted
  137. Scene-Centric Unsupervised Video Panoptic Segmentationaccepted
  138. Scene-VLM: Multimodal Video Scene Segmentation via Vision-Language Modelsaccepted
  139. SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Modelaccepted
  140. SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotationsaccepted
  141. SceneTok: A Compressed, Diffusable Token Space for 3D Scenesaccepted
  142. Scenes as Tokens: Multi-Scale Normal Distributions Transform Tokenizer for General 3D Vision-Language Understandingaccepted
  143. SciEducator: Scientific Video Understanding and Educating via Deming-Cycle Multi-Agent Systemaccepted
  144. Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modelingaccepted
  145. Score2Instruct: Scaling Up Video Quality-Centric Instructions via Automated Dimension Scoringaccepted
  146. Sculpt4D: Generating 4D Shapes via Sparse-Attention Diffusion Transformersaccepted
  147. SeD-UD: An Influence-Driven and Hierarchically-Decoupled Information Bottleneck for Multimodal Intent Recognitionaccepted
  148. SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Modelsaccepted
  149. SearchAD: Large-Scale Rare Image Retrieval Dataset for Autonomous Drivingaccepted
  150. See Further, Think Deeper: Advancing VLM's Reasoning Ability with Low-level Visual Cues and Reflectionaccepted
  151. See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMsaccepted
  152. See Less, See Right: Bi-directional Perceptual Shaping For Multimodal Reasoningaccepted
  153. See Through the Noise: Improving Domain Generalization in Gaze Estimationaccepted
  154. See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understandingaccepted
  155. See What We Cannot See: A Geo-guided Reasoning Benchmark for Object Counting under Adverse Earth Observation Conditionsaccepted
  156. See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesisaccepted
  157. See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Togglesaccepted
  158. SeeGroup: Multi-Layer Depth Estimation of Transparent Surfaces via Self-Determined Groupingaccepted
  159. SeeThrough3D: Occlusion Aware 3D Control in Text-to-Image Generationaccepted
  160. SeeU: Seeing the Unseen World via 4D Dynamics-aware Generationaccepted
  161. Seeing Beyond 8bits: Subjective and Objective Quality Assessment of HDR-UGC Videosaccepted
  162. Seeing Beyond: Extrapolative Domain Adaptive Panoramic Segmentationaccepted
  163. Seeing Both Sides: Towards Bidirectional Semantic Alignment for Open-Vocabulary Camouflaged Object Segmentationaccepted
  164. Seeing Clearly, Reasoning Confidently: Plug-and-Play Remedies for Vision Language Model Blindnessaccepted
  165. Seeing Conversations: Communication Context Identification in Egocentric Videoaccepted
  166. Seeing Depth Through Frequency and Motion: A Progressive Training Paradigm for Monocular Depth Estimationaccepted
  167. Seeing Motion Through Polarity for Event-based Action Recognitionaccepted
  168. Seeing Through Blur: Tackling Defocus in Spike-Based Imagingaccepted
  169. Seeing Through Touch: Tactile-Driven Visual Localization of Material Regionsaccepted
  170. Seeing Through the Noise: Improving Infrared Small Target Detection and Segmentation from Noise Suppression Perspectiveaccepted
  171. Seeing Through the Shift: Causality-Inspired Robust Generalized Category Discoveryaccepted
  172. Seeing What Matters: A Training-Free Self-Guided Framework for Multimodal Detail Perception and Reasoningaccepted
  173. Seeing What Matters: Visual Preference Policy Optimization for Visual Generationaccepted
  174. Seeing as Experts Do: A Knowledge-Augmented Agent for Open-Set Fine-Grained Visual Understandingaccepted
  175. Seeing is Improving: Visual Feedback for Iterative Text Layout Refinementaccepted
  176. Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmarkaccepted
  177. Seeing through Light and Darkness: Sensor-Physics Grounded Deblurring HDR NeRF from Single-Exposure Images and Eventsaccepted
  178. Seeing through boxes: Non-Line-of-Sight 3D Reconstruction from Radar Signalsaccepted
  179. Seeing without Pixels: Perception from Camera Trajectoriesaccepted
  180. Seele: A Unified Acceleration Framework for Real-Time Gaussian Splatting on Mobile Devicesaccepted
  181. SegCompass: Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning Segmentationaccepted
  182. SegEarth-R2: Towards Comprehensive Language-guided Segmentation for Remote Sensing Imagesaccepted
  183. SegGBC: Justifiable Coarse-to-Fine Granular-Ball Computing for Enhancing Clustering Image Segmentationaccepted
  184. SegMo: Co-Designing Content-Aware Sparsity and Locally-Cohesive Segment Parallelism for Efficient VLM Inferenceaccepted
  185. SegMoTE: Token-Level Mixture of Experts for Medical Image Segmentationaccepted
  186. SegQuant: A Semantics-Aware and Generalizable Quantization Framework for Diffusion Modelsaccepted
  187. SelecTKD: Selective Token-Weighted Knowledge Distillation for LLMsaccepted
  188. Select Less, Reason More: Prioritizing Evidence Purity for Video Reasoningaccepted
  189. Select, Hypothesize and Verify: Towards Verified Neuron Concept Interpretationaccepted
  190. Selection-as-Nonlinearity: Bridging Attention and Activation via a Joint Game-Decision Lens for Interpretable, Discriminative Visual Representationsaccepted
  191. Selective Amnesia using Contrastive Subnet Erasure for Class Level Unlearning in Vision Modelsaccepted
  192. Selective, Regularized, and Calibrated: Harnessing Vision Foundation Models for Cross-Domain Few-Shot Semantic Segmentationaccepted
  193. Selectively Extracting and Injecting Visual Attributes into Text-to-Image Modelsaccepted
  194. Self-Attention Driven Tensor Representation for High-Order Data Recoveryaccepted
  195. Self-Consistency for LLM-Based Motion Trajectory Generation and Verificationaccepted
  196. Self-Corrected Image Generation with Explainable Latent Rewardsaccepted
  197. Self-Critical Distillation Network for Video-based Commonsense Captioningaccepted
  198. Self-Diffusion Driven Blind Imagingaccepted
  199. Self-Evaluation Unlocks Any-Step Text-to-Image Generationaccepted
  200. Self-Paced and Self-Corrective Masked Prediction for Movie Trailer Generationaccepted
  201. Self-guided Semantic Inspection for Zero-Shot Composed Image Retrievalaccepted
  202. Self-supervised Dynamic Heterogeneous Degradation Modeling for Unified Zero-Shot Image Restorationaccepted
  203. SelfHVD: Self-Supervised Handheld Video Deblurringaccepted
  204. Selfi: Self-improving Reconstruction Engine via 3D Geometric Feature Alignmentaccepted
  205. SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object Detectionaccepted
  206. SemLayer: Semantic-aware Generative Segmentation and Layer Construction for Abstract Iconsaccepted
  207. SemVideo: Reconstructs What You Watch from Brain Activity via Hierarchical Semantic Guidanceaccepted
  208. Semantic Alignment for Pose-Invariant Identity Preserving Diffusionaccepted
  209. Semantic Audio-Visual Navigation in Continuous Environmentsaccepted
  210. Semantic Context Matters: Improving Conditioning for Autoregressive Modelsaccepted
  211. Semantic Derivative Flow: Graph-Guided Diffusion for Controllable Instance Interactionsaccepted
  212. Semantic Foam: Unifying Spatial and Semantic Scene Decompositionaccepted
  213. Semantic Noise Reduction via Teacher-Guided Dual-Path Audio-Visual Representation Learningaccepted
  214. Semantic Scale Space: A Framework for Controllable Image Abstractionaccepted
  215. Semantic-Adaptive Diffusion for Dynamic Spatiotemporal Fusionaccepted
  216. Semantic-Guided Global-Local Collaborative Prompt Learning for Few-Shot Class Incremental Learningaccepted
  217. SemanticVLA: Towards Semantic Reasoning over Action Memorization via Synergistic Explicit Trace and Latent Action Planningaccepted
  218. Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusionaccepted
  219. Semi-Supervised Conformal Prediction With Unlabeled Nonconformity Scoreaccepted
  220. Semi-supervised Echocardiography Video Segmentation via Anchor Semantic Awareness and Continuous Pseudo-label Reforgingaccepted
  221. SemiGDA: Generative Dual-distribution Alignment for Semi-Supervised Medical Image Segmentationaccepted
  222. SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Cachingaccepted
  223. SenseSearch: Empowering Vision-Language Models with High-Resolution Agentic Search-Reasoning via Reinforcement Learningaccepted
  224. Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Drivingaccepted
  225. ShadowDraw: From Any Object to Shadow-Drawing Compositional Artaccepted
  226. Shape-of-You: Fused Gromov-Wasserstein Optimal Transport for Semantic Correspondence in-the-Wildaccepted
  227. ShapeAR: Generating Editable Shape Layers via Autoregressive Diffusionaccepted
  228. ShapeR: Robust Conditional 3D Shape Generation from Casual Capturesaccepted
  229. SharpTimeGS: Sharp and Stable Dynamic Gaussian Splatting via Lifespan Modulationaccepted
  230. Shedding Light on VLN Robustness: A Black-box Framework for Indoor Lighting-based Adversarial Attackaccepted
  231. ShelfOcc: Native 3D Supervision beyond LiDAR for Vision-Based Occupancy Estimationaccepted
  232. ShiftLUT: Spatial Shift Enhanced Look-Up Tables for Efficient Image Restorationaccepted
  233. Shoe Style-Invariant and Ground-Aware Learning for Dense Foot Contact Estimationaccepted
  234. ShotDirector: Directorially Controllable Multi-Shot Video Generation with Cinematographic Transitionsaccepted
  235. ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinementaccepted
  236. ShowUI-p: Flow-based Generative Models as GUI Dexterous Handsaccepted
  237. ShreddingNet: Coarse-to-Fine Restoration for Multi-Source Shredded Manuscriptsaccepted
  238. SigLino: Efficient Multi-Teacher Distillation for Agglomerative Vision Foundation Modelsaccepted
  239. SignPR: A Progressive Vector-Quantized Diffusion Framework for Sign Language Productionaccepted
  240. SimLBR: Learning to Detect Fake Images by Learning to Detect Real Imagesaccepted
  241. SimRecon: SimReady Compositional Scene Reconstruction from Real Videosaccepted
  242. SimScale: Learning to Drive via Real-World Simulation at Scaleaccepted
  243. Similarity-Consistent Likelihood Diffusion enables Hidden Person Detection from Wall Reflectionsaccepted
  244. Similarity-as-Evidence: Calibrating Overconfident VLMs for Interpretable and Label-Efficient Medical Active Learningaccepted
  245. Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimizationaccepted
  246. Simple but Effective Triplet-Based Compression Strategies for Compact Visual Localizationaccepted
  247. Simple-ViLMedSAM: Simple Text Prompts Meet Vision-Language Models for Medical Image Segmentationaccepted
  248. SinGeo: Unlock Single Model's Potential for Robust Cross-View Geo-Localizationaccepted
  249. SineProject: Machine Unlearning for Stable Vision-Language Alignmentaccepted
  250. Single-Round Scalable Analytic Federated Learningaccepted
  251. Single-step Diffusion-based Video Coding with Semantic-Temporal Guidanceaccepted
  252. SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognitionaccepted
  253. Sketch2CT: Multimodal Diffusion for Structure-Aware 3D Medical Volume Generationaccepted
  254. Sketch2Colab: Sketch-Conditioned Multi-Human Animation via Controllable Flow Distillationaccepted
  255. SketchAssist: A Practical Assistant for Semantic Edits and Precise Local Redrawingaccepted
  256. SketchDeco: Training-Free Latent Composition for Precise Sketch Colourisationaccepted
  257. SketchFaceGS: Real-Time Sketch-Driven Face Editing and Generation with Gaussian Splattingaccepted
  258. SketchRevive: Fine-Grained Pixel-to-Vector Sketch Completion with Diffusion-Prior-Guided Multimodal LLMsaccepted
  259. SketchVL: Policy Optimization via Fine-Grained Credit Assignment for Chart Understanding and Moreaccepted
  260. SkillSight: Efficient First-Person Skill Assessment with Gazeaccepted
  261. Skullptor: High Fidelity 3D Head Reconstruction in Seconds with Multi-View Normal Predictionaccepted
  262. Sky2Ground: A Benchmark for Site Modeling under Varying Altitudeaccepted
  263. SkyReels-Text: Fine-Grained Font-Controllable Text Editing for Poster Designaccepted
  264. SkySense-VITA: Towards Universal In-context Segmentation of Multi-modal Remote Sensing Imageryaccepted
  265. Skyra: AI-Generated Video Detection via Grounded Artifact Reasoningaccepted
  266. SliderEdit: Continuous Image Editing with Fine-Grained Instruction Controlaccepted
  267. Small Object, Great Challenge: A Benchmark for Small Object Visual Groundingaccepted
  268. Smart Replay: Adaptive Scheduling of Memory Rehearsal for Computational Resource-Aware Incremental Learningaccepted
  269. SmokeSVD: Smoke Reconstruction from A Single View via Progressive Novel View Synthesis and Refinement with Diffusion Modelsaccepted
  270. Smoothing the Score Function to Enhance Generalization in Diffusion Modelsaccepted
  271. SoC: Semantic Orthogonal Calibration for Test-Time Prompt Tuningaccepted
  272. SoPE: Spherical Coordinate-Based Positional Embedding for Enhancing Spatial Perception of 3D LVLMsaccepted
  273. SoccerMaster: A Vision Foundation Model for Soccer Understandingaccepted
  274. SocialNav: Training Human-Inspired Foundation Model for Socially-Aware Embodied Navigationaccepted
  275. Socratic-Geo: Synthetic Data Generation and Cross-Modal Geometric Reasoning via Multi-Agent Interactionaccepted
  276. Soft Modality-Guided Expert Specialization in MoE-VLMsaccepted
  277. SoliReward: Mitigating Susceptibility to Reward Hacking and Annotation Noise in Video Generation Reward Modelsaccepted
  278. Solvability of the Viewing Graph Under the Affine Camera Modelaccepted
  279. Solving Minimal Problems Without Matrix Inversion Using FFT-Based Interpolationaccepted
  280. Solving a Nonlinear Blind Inverse Problem for Tagged MRI with Physics and Deep Generative Priorsaccepted
  281. SonoWorld: From One Image to a 3D Audio-Visual Sceneaccepted
  282. Soul: Breathe Life into Digital Human for High-fidelity Long-term Multimodal Animationaccepted
  283. SounDiT: Geo-Contextual Soundscape-to-Landscape Generationaccepted
  284. Space-Time Forecasting of Dynamic Scenes with Motion-aware Gaussian Groupingaccepted
  285. SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Drivingaccepted
  286. SpaceMind: Camera-Guided Modality Fusion for Spatial Reasoning in Vision-Language Modelsaccepted
  287. SpaceTimePilot: Generative Rendering of Dynamic Scenes Across Space and Timeaccepted
  288. SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RLaccepted
  289. SparVAR: Exploring Sparsity in Visual AutoRegressive Modeling for Training-Free Accelerationaccepted
  290. Sparse Spectral LoRA: Routed Experts for Medical VLMsaccepted
  291. Sparse Task Vector Mixup with Hypernetworks for Efficient Knowledge Transfer in Whole-Slide Image Prognosisaccepted
  292. Sparse-LaViDa: Sparse Multimodal Discrete Diffusion Language Modelsaccepted
  293. Sparse-View Localization via Online Neural 3D Regressionaccepted
  294. SparseCam4D: Spatio-Temporally Consistent 4D Reconstruction from Sparse Camerasaccepted
  295. SparseOIT: Improving Order-Independent Transparency 3DGS via Active Set Methodaccepted
  296. SparseSplat: Towards Applicable Feed-Forward 3D Gaussian Splatting with Pixel-Unaligned Predictionaccepted
  297. SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Modelaccepted
  298. Sparsely Timing the Change: A Spiking Temporal Framework for Remote Sensing Interpretationaccepted
  299. Sparsity as a Key: Unlocking New Insights from Latent Structures for Out-of-Distribution Detectionaccepted
  300. Sparsity-Aware Voxel Attention and Foreground Modulation for 3D Semantic Scene Completionaccepted
  301. Spatia: Video Generation with Updatable Spatial Memoryaccepted
  302. SpatiaLQA: A Benchmark for Evaluating Spatial Logical Reasoning in Vision-Language Modelsaccepted
  303. Spatial Matters: Position-Guided 3D Referring Expression Segmentationaccepted
  304. Spatial Retrieval Augmented Autonomous Drivingaccepted
  305. Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videosaccepted
  306. Spatial-Frequency Collaborative Learning for Occluded Visible-Infrared Person Re-Identificationaccepted
  307. Spatial-SAM: Spatially Consistent 3D Electron Microscopy Segmentation with SDF Memory and Semi-Supervised Learningaccepted
  308. Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learningaccepted
  309. Spatial-Spectral Residuals Informed Diffusion Neural Operator for Pan-sharpeningaccepted
  310. SpatialDiff: 3D-Aware Object Movement via Implicit Spatial Modelingaccepted
  311. SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generationaccepted
  312. SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligenceaccepted
  313. SpatialStack: Layered Geometry-Language Fusion for 3D VLM Spatial Reasoningaccepted
  314. SpatialTree: How Spatial Intelligence Branches Out in MLLMsaccepted
  315. SpatialVID: A Large-Scale Video Dataset with Spatial Annotationsaccepted
  316. Spatio-Temporal Conditional Denoising Transformer for Modality-Missing RGBT Trackingaccepted
  317. Spatio-Temporal Difference Guided Motion Deblurring with the Complementary Vision Sensoraccepted
  318. Spatiotemporal Pyramid Flow Matching for Climate Emulationaccepted
  319. Spe-BEVHead: Rethinking the Detection Head Design for Bird's-Eye-View Object Detectionaccepted
  320. Specificity-aware reinforcement learning for fine-grained open-world classificationaccepted
  321. Spectral Conformal Risk Control: Distribution-Free Tail Guarantees via Bayesian Quadratureaccepted
  322. Spectral Mixture-of-Experts for Continual Learningaccepted
  323. Spectral Scalpel: Amplifying Adjacent Action Discrepancy via Frequency-Selective Filtering for Skeleton-Based Action Segmentationaccepted
  324. Spectral Super-Resolution via Adversarial Unfolding and Data-Driven Spectrum Regularization: From Multispectral Satellite Data to NASA Hyperspectral Imageaccepted
  325. Spectral-Geometric Neural Fields for Pose-Free LiDAR View Synthesisaccepted
  326. Spectrally Distilled Representations Aligned with Instruction-Augmented LLMs for Satellite Imageryaccepted
  327. Spectrum from Defocus: Fast Spectral Imaging with Chromatic Focal Stackaccepted
  328. SpeeDe3DGS: Speedy Deformable 3D Gaussian Splatting with Temporal Pruning and Motion Groupingaccepted
  329. SpeeDiff: Scalable Pixel-Anchored End-to-End Latent Diffusion Modelaccepted
  330. Speeding Up the Learning of 3D Gaussians with Much Shorter Gaussian Listsaccepted
  331. Spherical Leech Quantization for Visual Tokenization and Generationaccepted
  332. Spherical Voronoi: Directional Appearance as a Differentiable Partition of the Sphereaccepted
  333. SpiderCam: Low-Power Snapshot Depth from Differential Defocusaccepted
  334. Spike-driven Discrete Aggregation for Event-based Object Detectionaccepted
  335. SpikeTrack: A Spike-driven Framework for Efficient Visual Trackingaccepted
  336. SpikeTrack: High-performance and Energy-efficient Event-Based Object Tracking with Spiking Neural Networkaccepted
  337. SpiralDiff: Spiral Diffusion with LoRA for RGB-to-RAW Conversion Across Camerasaccepted
  338. Spk2VidNet: A Hierarchical Recurrent Architecture for High-Fidelity Video Reconstruction from Long Spike-Camera Streamsaccepted
  339. Splat-Based Metal Artifact Reduction in Cone-Beam CT via Compact Attenuation Modelingaccepted
  340. SplatSuRe: Selective Super-Resolution for Multi-view Consistent 3D Gaussian Splattingaccepted
  341. Splatent: Splatting Diffusion Latents for Novel View Synthesisaccepted
  342. SplitFlux: Learning to Decouple Content and Style from a Single Imageaccepted
  343. Spot The Ball: A Benchmark for Visual Social Inferenceaccepted
  344. SpotEdit: Selective Region Editing in Diffusion Transformersaccepted
  345. StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representationaccepted
  346. StaR-KVQA: Structured Reasoning Traces for Implicit-Knowledge Visual Question Answeringaccepted
  347. Stability-Driven Motion Generation for Object-Guided Human-Human Co-Manipulationaccepted
  348. Stabilizing Feature Geometry in Noisy Pretrained Models for Robust Downstream Tasksaccepted
  349. Stabilizing Streaming Video Geometry via Dynamic Feature Normalizationaccepted
  350. Stable Mean Flow: Lyapunov-Inspired One-Step Flow Matchingaccepted
  351. Stable Spike: Dual Consistency Optimization via Bitwise AND Operations for Spiking Neural Networksaccepted
  352. Stable and Efficient Single-Rollout RL for Multimodal Reasoningaccepted
  353. StableMTL: Repurposing Latent Diffusion Models for Multi-Task Learning from Partially Annotated Synthetic Datasetsaccepted
  354. StableMaterials: Enhancing Diversity in Material Generation via Semi-Supervised Learningaccepted
  355. Stake the Points: Structure-Faithful Instance Unlearningaccepted
  356. Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generationaccepted
  357. Statistical Characteristic-Guided Denoising for Rapid High-Resolution Transmission Electron Microscopy Imagingaccepted
  358. Stay in your Lane: Role Specific Queries with Overlap Suppression Loss for Dense Video Captioningaccepted
  359. Stealing Split Learning Bottom Models by Recovering Embedding Geometryaccepted
  360. Steering Where to Diffuse: Generative Modeling of Phenotypic Response Simulation with Steered Diffusion Bridgeaccepted
  361. Stepwise Credit Assignment for GRPO on Flow-Matching Modelsaccepted
  362. Stereo World Model: Camera-Guided Stereo Video Generationaccepted
  363. StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generationaccepted
  364. Stitch-a-Demo: Creating Video Demonstrations from Multistep Descriptionsaccepted
  365. Stochastic Ray Tracing for the Reconstruction of 3D Gaussian Splattingaccepted
  366. StoryTailor:A Zero-Shot Pipeline for Action-Rich Multi-Subject Visual Narrativesaccepted
  367. StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatarsaccepted
  368. StreamDiT: Real-Time Streaming Text-to-Video Generationaccepted
  369. StreamRAG: Enhancing Real-Time Video Understanding with Retrieval Augmentationaccepted
  370. StreamReady: Learning What to Answer and When in Long Streaming Videosaccepted
  371. StreamVLO: Streaming Visual-LiDAR Odometry with Cumulative Drift Compensationaccepted
  372. Streaming Diffusion Model for Fast Infrared and Visible Video Fusionaccepted
  373. Streaming Video Crime Anticipation with Spatio-Temporal Causal Reasoningaccepted
  374. Streaming Video Instruction Tuningaccepted
  375. StreamingTOM: Streaming Token Compression for Efficient Video Understandingaccepted
  376. Streamlined Knowledge Distillationaccepted
  377. Streamlined Open-Vocabulary Human-Object Interaction Detectionaccepted
  378. Stronger Normalization-Free Transformersaccepted
  379. StructXLIP: Enhancing Vision-language Models with Multimodal Structural Cuesaccepted
  380. Structural Action Transformer for 3D Dexterous Manipulationaccepted
  381. Structural Graph Probing of Vision-Language Modelsaccepted
  382. Structure-Aware Representation Distillation for Tiny-Dense Object Segmentationaccepted
  383. Structure-to-Intensity Diffusion for Adverse-Weather LiDAR Generationaccepted
  384. Style-GRPO: Semantic-Aware Preference Optimization for Image Style Transfer Guided by Reward Modelingaccepted
  385. StyleDoctor: Towards Specialist Reward Model for Style-centric Generation Tasksaccepted
  386. StyleGallery: Training-free and Semantic-aware Personalized Style Transfer from Arbitrary Image Referencesaccepted
  387. StyleTextGen: Style-Conditioned Multilingual Scene Text Generationaccepted
  388. SuP: Sub-cloud Driven Point Cloud Registrationaccepted
  389. Submodel Extraction for Efficient and Personalized Federated Learning via Optimal Transportaccepted
  390. Subspace Alignment for CLIP-based Continual Learning via Canonical Correlation Analysisaccepted
  391. SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modelingaccepted
  392. SunFaded: Illumination-Aware Gaussian Splatting for Dark Scenes with Camera-Mounted Active Lightingaccepted
  393. Superman: Unifying Skeleton and Vision for Human Motion Perception and Generationaccepted
  394. Suppressing Non-Semantic Noise in Masked Image Modeling Representationsaccepted
  395. SurgCoT: Advancing Spatiotemporal Reasoning in Surgical Videos through a Chain-of-Thought Benchmarkaccepted
  396. SwiftTailor: Efficient 3D Garment Generation with Geometry Image Representationaccepted
  397. SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overheadaccepted
  398. SwitchCraft: Training-Free Multi-Event Video Generation with Attention Controlsaccepted
  399. SymphoMotion: Joint Control of Camera Motion and Object Dynamics for Coherent Video Generationaccepted
  400. Symphony: A Cognitively-Inspired Multi-Agent System for Long-Video Understandingaccepted
  401. SynCLIP: Synonym-Coherent Language-Image Pretraining for Robust Open-Vocabulary Dense Perceptionaccepted
  402. SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generationaccepted
  403. SyncDreamer: Controllable and Expressive Avatar Generation Beyond the Talking Headaccepted
  404. SyncMos: Scalable Motion Synchronisation for Multi-Agent Scene Interactionaccepted
  405. Synergistic Bleeding Region and Point Detection in Laparoscopic Surgical Videosaccepted
  406. SynthRGB-T: Language-Vision Guided Image Translation for Diversity Synthesisaccepted
  407. Synthesizing Visual Concepts as Vision-Language Programsaccepted
  408. Synthetic Curriculum Reinforces Compositional Text-to-Image Generationaccepted
  409. Synthetic Object Compositions for Scalable and Accurate Learning in Detection, Segmentation, and Groundingaccepted
  410. T2SGrid: Temporal-to-Spatial Gridification for Video Temporal Groundingaccepted
  411. TACO: Task-Aware Contrastive Learning for Joint LiDAR Localization and 3D Object Detectionaccepted
  412. TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Expertsaccepted
  413. TALO: Pushing 3D Vision Foundation Models Towards Globally Consistent Online Reconstructionaccepted
  414. TALON: Test-time Adaptive Learning for On-the-Fly Category Discoveryaccepted
  415. TAMER: A Tri-Modal Contrastive Alignment and Multi-Scale Embedding Refinement Framework for Zero-Shot ECG Diagnosisaccepted
  416. TANGO: Learning Distribution-wise Foundation Prior Consistency and Instance-wise Style Calibration for Medical Image Generalizationaccepted
  417. TANGO: Text-Anchored Guided Optimization for Robust Fine-tuning Vision-Language Models under Label Noiseaccepted
  418. TAP: A Token-Adaptive Predictor Framework for Training-Free Diffusion Accelerationaccepted
  419. TAPE: Task-Adaptive Prototype Evolution in Audio-Language Models for Fully Few-shot Class-incremental Audio Classificationaccepted
  420. TAR: Token-Aware Refinement for Fine-grained Generalized Category Discoveryaccepted
  421. TAS-LoRA: Transformer Architecture Search with Mixture-of-LoRA Expertsaccepted
  422. TAlignDiff: Automatic Tooth Alignment assisted by Diffusion-based Transformation Learningaccepted
  423. TC-Pade: Trajectory-Consistent Pade Approximation for Diffusion Accelerationaccepted
  424. TDATR: Improving End-to-End Table Recognition via Table Detail-Aware Learning and Cell-Level Visual Alignmentaccepted
  425. TEAR: Temporal-aware Automated Red-teaming for Text-to-Video Modelsaccepted
  426. TESO: Online Tracking of Essential Matrix by Stochastic Optimizationaccepted
  427. TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysisaccepted
  428. TEXTRIX: Latent Attribute Grid for Native Texture Generation and Beyondaccepted
  429. TF-CADE: Foreground-Concentrated Text-Video Alignment for Zero-Shot Temporal Action Detectionaccepted
  430. TF-SSD: A Strong Pipeline via Synergic Mask Filter for Training-free Co-salient Object Detectionaccepted
  431. TGSFormer: Scalable Temporal Gaussian Splatting for Embodied Semantic Scene Completionaccepted
  432. TGT: Text-Grounded Trajectories for Locally Controlled Video Generationaccepted
  433. TGTrack: Temporal Generative Learning for Unified Single Object Trackingaccepted
  434. THE MORE, THE MERRIER: CONTRASTIVE FUSION FOR HIGHER-ORDER MULTIMODAL ALIGNMENTaccepted
  435. TIACam: Text-Anchored Invariant Feature Learning with Auto-Augmentation for Camera-Robust Zero-Watermarkingaccepted
  436. TIGER: A Unified Framework for Time, Images and Geo-location Retrievalaccepted
  437. TIM: Temporal Decoupling with Iterative Mutual-Refinement Model for Longitudinal Radiology Report Generationaccepted
  438. TINA: Text-Free Inversion Attack for Unlearned Text-to-Image Diffusion Modelsaccepted
  439. TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignmentaccepted
  440. TLMA: Mitigating the Impact of Weakly Labeled Information for Video Anomaly Detectionaccepted
  441. TM-BSN: Triangular-Masked Blind-Spot Network for Real-World Self-Supervised Image Denoisingaccepted
  442. TR2M: Transferring Monocular Relative Depth to Metric Depth with Language Descriptions and Dual-Level Scale-Oriented Contrastaccepted
  443. TRANSPORTER: Transferring Visual Semantics from VLM Manifoldsaccepted
  444. TRCoRSurg: Temporal-Relational Co-Reasoning for Surgical Video Triplet Recognitionaccepted
  445. TRIDENT: A Trimodal Cascade Generative Framework for Drug and RNA-Conditioned Cellular Morphology Synthesisaccepted
  446. TRM-VLA: Temporal-Aware Chain-of-Thought Reasoning and Memorization for Vision-Language-Action Modelsaccepted
  447. TROPHIES: Temporal Reconstruction of Places, Humans, and Cameras from Multi-view Videosaccepted
  448. TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognitionaccepted
  449. TSTM: Temporal Segmentation for Task-relevant Mask in Visual Reinforcement Learning Generalizationaccepted
  450. TTAPFormer: Robust Arbitrary Point Tracking via Transient Asynchronous Fusion of Frames and Eventsaccepted
  451. TTL: Test-time Textual Learning for OOD Detection with Pretrained Vision-Language Modelsaccepted
  452. TTP: Test-Time Padding for Adversarial Detection and Robust Adaptation on Vision-Language Modelsaccepted
  453. TTRV: Test-Time Reinforcement Learning for Vision Language Modelsaccepted
  454. TUDSR: Twice Upsampling-Diffusion for Higher Super-Resolutionaccepted
  455. TUNA: Taming Unified Visual Representations for Native Unified Multimodal Modelsaccepted
  456. TV2TV: A Unified Framework for Interleaved Language and Video Generationaccepted
  457. TVHighlights: LLM-Guided Human-Free Collaborative Training for Video Highlight Detection in Movies and TV Dramasaccepted
  458. TWEO: Transformers Without Extreme Outliers Enables FP8 Training And Quantization For Dummiesaccepted
  459. TWINGS: Thin Plate Splines Warp-aligned Initialization for Sparse-View Gaussian Splattingaccepted
  460. TableMix: Enhancing Multimodal Table Reasoning in MLLMs from a Data-Centric Perspectiveaccepted
  461. TacSIm: A Dataset and Benchmark for Football Tactical Style Imitationaccepted
  462. Tackling Alignment Ambiguity in Person Retrieval through Conversational Attribute Miningaccepted
  463. Tackling Model Bias via Game-theoretic Multi-agent Collaboration Framework for Hateful Meme Classificationaccepted
  464. TagSplat: Topology-Aware Gaussian Splatting for Dynamic Mesh Modeling and Trackingaccepted
  465. Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenesaccepted
  466. Talking Together: Synthesizing Co-Located 3D Conversations from Audioaccepted
  467. Taming Generative Diffusion Model for Task-Oriented Infrared Imagingaccepted
  468. Taming Noise-Induced Prototype Degradation for Privacy-Preserving Personalized Federated Fine-Tuningaccepted
  469. Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion Reinforcement Learningaccepted
  470. Taming Sampling Perturbations with Variance Expansion Loss for Latent Diffusion Modelsaccepted
  471. Taming Video Models for 3D and 4D Generation via Zero-Shot Camera Controlaccepted
  472. Taming the Long Tail: Rebalancing Adversarial Training via Adaptive Perturbationaccepted
  473. Target-Aware Invertible Encoder with Reconstruction Guidance for Infrared Small Target Detectionaccepted
  474. Task-Aware Image Signal Processor for Advanced Visual Perceptionaccepted
  475. Task-Driven Implicit Representations for Automated Design of LiDAR Systemsaccepted
  476. Task-Oriented Data Synthesis and Control-Rectify Sampling for Remote Sensing Semantic Segmentationaccepted
  477. TaskForce: Cooperative Multi-agent Reinforcement Learning for Multi-task Optimizationaccepted
  478. TaskIT: Memory-Efficient Fine-Tuning of Multi-LoRA LLMs via Cross-Task Importance Transferaccepted
  479. Tavatar: Topology-Aware Gaussian Attribute Derivation for Animatable Human Avatarsaccepted
  480. Taxonomy-Aware Representation Alignment for Hierarchical Visual Recognition with Large Multimodal Modelsaccepted
  481. TeFlow: Enabling Multi-frame Supervision for Self-Supervised Feed-forward Scene Flow Estimationaccepted
  482. TeHOR: Text-Guided 3D Human and Object Reconstruction with Texturesaccepted
  483. Tea-Adapter: Teacher Adapter for Efficient Conditional Generationaccepted
  484. Teacher-Guided Routing for Sparse Vision Mixture-of-Expertsaccepted
  485. Teaching DINOv3 About Partial 3D Geometry: A Self-Supervised Geometry-Aware Approachaccepted
  486. TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Sizeaccepted
  487. Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attentionaccepted
  488. Tell2Adapt: A Unified Framework for Source Free Unsupervised Domain Adaptation via Vision Foundation Modelaccepted
  489. TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learningaccepted
  490. TempoControl: Temporal Attention Guidance for Text-to-Video Modelsaccepted
  491. TempoMaster: Efficient Long Video Generation via Next-Frame-Rate Predictionaccepted
  492. Temporal Equilibrium MeanFlow: Bridging the Scale Gap for One-Step Generationaccepted
  493. Temporal Imbalance of Positive and Negative Supervision in Class-Incremental Learningaccepted
  494. Temporal Interaction in Spiking Transformers with Multi-Delay Mixeraccepted
  495. Temporal Inversion for Learning Interval Change in Chest X-Raysaccepted
  496. Temporal Representation Enhancement (TRE): Learning to Forget Dominant Patterns for Enhanced Temporal Spiking Featuresaccepted
  497. TerraScope: Pixel-Grounded Visual Reasoning for Earth Observationaccepted
  498. TerraSeg: Self-Supervised Ground Segmentation for Any LiDARaccepted
  499. Test-Time 3D Occupancy Predictionaccepted
  500. Test-Time Alignment of Text-to-Image Diffusion Models via Null-Text Embedding Optimisationaccepted
  501. Test-Time Attention Purification for Backdoored Large Vision Language Modelsaccepted
  502. Test-Time Instance-Specific Parameter Composition: A New Paradigm for Adaptive Generative Modelingaccepted
  503. Test-Time Multi-Prompt Adaptation for Open-Vocabulary Remote Sensing Image Segmentationaccepted
  504. Test-Time Perturbation Tuning with Delayed Feedback for Vision-Language-Action Modelsaccepted
  505. Test-Time Training for LiDAR Semantic Segmentation under Corruption via Geometric Inlier Discriminationaccepted
  506. Test-time Ego-Exo-centric Adaptation for Action Anticipation via Multi-Label Prototype Growing and Dual-Clue Consistencyaccepted
  507. Test-time Sparsity for Extreme Fast Action Diffusionaccepted
  508. Text-Driven 3D Hand Motion Generation from Sign Language Dataaccepted
  509. Text-Image Conditioned 3D Generationaccepted
  510. Text-Phase Synergy Network with Dual Priors for Unsupervised Cross-Domain Image Retrievalaccepted
  511. Text-Printed Image: Bridging the Image-Text Modality Gap for Text-centric Training of Large Vision-Language Modelsaccepted
  512. Text-guided Feature Disentanglement for Cross-modal Gait Recognitionaccepted
  513. TextFM: Robust Semi-dense Feature Matching with Language Guidanceaccepted
  514. TextOVSR: Text-Guided Real-World Opera Video Super-Resolutionaccepted
  515. TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Renderingaccepted
  516. Texvent: Asynchronous Event Data Simulation via Text Promptaccepted
  517. The Blind Spot of Adaptation: Quantifying and Mitigating Forgetting in Fine-tuned Driving Modelsaccepted
  518. The Coherence Trap: When MLLM-Crafted Narratives Exploit Manipulated Visual Contextsaccepted
  519. The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignmentaccepted
  520. The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discoveryaccepted
  521. The Devil is in Attention Sharing: Improving Complex Non-rigid Image Editing Faithfulness via Attention Synergyaccepted
  522. The Drift Kernel: Why Diffusion Models Change Even When Told Not Toaccepted
  523. The Geometry of Robustness: Optimizing Loss Landscape Curvature and Feature Manifold Alignment for Robust Finetuning of Vision-Language Modelsaccepted
  524. The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptationaccepted
  525. The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generationaccepted
  526. The Invisible Gorilla Effect in Out-of-distribution Detectionaccepted
  527. The LLM Bottleneck: Why Open-Source Vision LLMs Struggle with Hierarchical Visual Recognitionaccepted
  528. The Midas Touch for Metric Depthaccepted
  529. The Missing GAP: From Solving Square Jigsaw Puzzles to Handling Real World Archaeological Fragmentsaccepted
  530. The Missing Point in Vision Transformers for Universal Image Segmentationaccepted
  531. The Power of Decaying Steps: Enhancing Attack Stability and Transferability for Sign-based Optimizersaccepted
  532. The Power of Prior: Training-Free Open-Vocabulary Semantic Segmentation with LLaVAaccepted
  533. The Road Less Seen: Segment Exploration for Weakly Supervised Video Anomaly Detectionaccepted
  534. The SA-FARI Dataset: Segment Anything in Footage of Animals for Recognition and Identificationaccepted
  535. The Surprising Effectiveness of Noise Pretraining for Implicit Neural Representationsaccepted
  536. The Universal Normal Embeddingaccepted
  537. The devil is in the details: Enhancing Video Virtual Try-On via Keyframe-Driven Details Injectionaccepted
  538. TherA: Thermal-Aware Visual-Language Prompting for Controllable RGB-to-Thermal Infrared Translationaccepted
  539. Thermal Diffusion Matters: Infrared Spatial-Temporal Video Super-Resolution through Heat Conduction Priorsaccepted
  540. Thermal is Always Wild: Characterizing and Addressing Challenges in Thermal-Only Novel View Synthesisaccepted
  541. Thermal-Det: Language-Guided Cross-Modal Distillation for Open-Vocabulary Thermal Object Detectionaccepted
  542. Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systemsaccepted
  543. Think 360deg: Beyond Depth: Evaluating the Width-centric Reasoning Capability of MLLMsaccepted
  544. Think Before You Drive: World Model-Inspired Multimodal Groundingaccepted
  545. Think Visually, Reason Textually: Vision-Language Synergy in Abstract Reasoningaccepted
  546. Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Viewsaccepted
  547. Think, Then Verify: A Hypothesis-Verification Multi-Agent Framework for Long Video Understandingaccepted
  548. Think-Then-Generate: Structural Chain-of-Thought Reasoning for Consistent 3D Generationaccepted
  549. Think-as-You-See: Streaming Chain-of-Thought Reasoning for Large Vision-Language Modelsaccepted
  550. ThinkGen: Generalized Thinking for Visual Generationaccepted
  551. Thinking Beyond Labels: Vocabulary-Free Fine-Grained Recognition using Reasoning-Augmented LMMsaccepted
  552. Thinking Diffusion: Penalize and Guide Visual-Grounded Reasoning in Diffusion Multimodal Language Modelsaccepted
  553. Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoningaccepted
  554. Thinking in 360deg: Humanoid Visual Search in the Wildaccepted
  555. Thinking in Dynamics: How Multimodal Large Language Models Perceive, Track, and Reason Dynamics in Physical 4D Worldaccepted
  556. Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decodingaccepted
  557. Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understandingaccepted
  558. Thinking with Frames: Generative Video Distortion Evaluation via Frame Reward Modelaccepted
  559. Thinking with Programming Vision: Towards a Unified View for Thinking with Imagesaccepted
  560. Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigmaccepted
  561. Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generationaccepted
  562. ThinkingViT: Matryoshka Thinking Vision Transformer for Elastic Inferenceaccepted
  563. Through the Frequency Lens: Cross-Domain Generalisable Gaze Estimation with Adaptive Modulationaccepted
  564. TiViBench: Benchmarking Think-in-Video Reasoning for Video Generationaccepted
  565. Time Blindness: Why Video-Language Models Can't See What Humans Can?accepted
  566. Time Without Time: Pseudo-Temporal Representation for Space-Time Super-Resolutionaccepted
  567. Time-Aware One Step Diffusion Network for Real-World Image Super-Resolutionaccepted
  568. Time-Specialized Event-Image Alignment for Blur-to-Video Decompositionaccepted
  569. TimeBridge: Self-Supervised Video Representation Learning via Start-End Joint Embedding and In-Between Frame Predictionaccepted
  570. TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMsaccepted
  571. TimeRipples: Accelerating vDiTs by Understanding the Spatio-Temporal Correlations in Latent Spaceaccepted
  572. TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understandingaccepted
  573. Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Modelsaccepted
  574. Token Warping Helps MLLMs Look from Nearby Viewpointsaccepted
  575. TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokensaccepted
  576. TokenHand: Discrete Token Representation for Efficient Hand Mesh Reconstructionaccepted
  577. TokenLight: Precise Lighting Control in Images using Attribute Tokensaccepted
  578. TokenSplat: Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstructionaccepted
  579. TokenTrace: Multi-Concept Attribution through Watermarked Token Recoveryaccepted
  580. Tokenization Allows Multimodal Large Language Models to Understand, Generate and Edit Architectural Floor Plansaccepted
  581. Too Vivid to Be Real? Benchmarking and Calibrating Generative Color Fidelityaccepted
  582. TopoCL: Topological Contrastive Learning for Medical Imagingaccepted
  583. TopoHR: Hierarchical Centerline Representation for Cyclic Topology Reasoning in Driving Scenes with Point-to-Instance Relationsaccepted
  584. TopoMA: Topology-Guided Multi-Agent Dense RGB 3D Reconstruction via Distributed Inferenceaccepted
  585. TopoMesh: High-Fidelity Mesh Autoencoding via Topological Unificationaccepted
  586. TopoSlide: Topologically-Informed Histopathology Whole Slide Image Representation Learningaccepted
  587. Topology-aware Feature Propagation for Unsupervised Non-rigid Point Cloud Correspondenceaccepted
  588. TouchDream: 3D Object Completion through Imagined Touchaccepted
  589. Toward Diffusible High-Dimensional Latent Spaces: A Frequency Perspectiveaccepted
  590. Toward Early Quality Assessment of Text-to-Image Diffusion Modelsaccepted
  591. Toward Generalizable Whole Brain Representations with High-Resolution Light-Sheet Dataaccepted
  592. Toward Low-Cost yet Effective Temporal Learning for UAV Trackingaccepted
  593. Toward Real-world Infrared Image Super-Resolution: A Unified Autoregressive Framework and Benchmark Datasetaccepted
  594. Towards Balanced Multi-Modal Learning in 3D Human Pose Estimationaccepted
  595. Towards Calibrating Prompt Tuning of Vision- Language Modelsaccepted
  596. Towards Cross-Modal Preservation, Consistency and Alignment for Privacy-Preserving Visible-Infrared Person Re-Identificationaccepted
  597. Towards Decompositional Human Motion Generation with Energy-Based Diffusion Modelsaccepted
  598. Towards Dynamic Modality Alignment in Multimodal Continual Learningaccepted
  599. Towards Efficient Medical Reasoning with Minimal Fine-Tuning Dataaccepted
  600. Towards Fine-Grained Attribution: Instance-Aware Preference Optimization for Aligning Diffusion Modelsaccepted
  601. Towards Foundation Models for 3D Scene Understanding: Instance-Aware Self-Supervised Learning for Point Cloudsaccepted
  602. Towards GUI Agents: Vision-Language Diffusion Models for GUI Groundingaccepted
  603. Towards Generalizable AI-Generated Image Detection via Image-Adaptive Prompt Learningaccepted
  604. Towards Generalized Multimodal Homography Estimationaccepted
  605. Towards Generalized Representations for Low-Light Understanding: When Signal Constancy Meets Semantic Enrichmentaccepted
  606. Towards High-Quality Image Segmentation: Improving Topology Accuracy by Penalizing Neighbor Pixelsaccepted
  607. Towards High-resolution and Disentangled Reference-based Sketch Colorizationaccepted
  608. Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interactionaccepted
  609. Towards Highly-Constrained Human Motion Generation with Retrieval-Guided Diffusion Noise Optimizationaccepted
  610. Towards Holistic Modeling for Video Frame Interpolation with Auto-regressive Diffusion Transformersaccepted
  611. Towards Human-Imperceptible Backdoor Attacks on Text-to-Image Diffusion Modelsaccepted
  612. Towards Human-Like Robot Handwriting via Contour-Aware Generationaccepted
  613. Towards Intrinsic-Aware Monocular 3D Object Detectionaccepted
  614. Towards Knowledge-augmented Bayesian Deep Learning For Computer Visionaccepted
  615. Towards Motion Turing Test: Evaluating Human-Likeness in Humanoid Robotsaccepted
  616. Towards Multimodal Domain Generalization with Few Labelsaccepted
  617. Towards Open Environments and Instructions: General Vision-Language Navigation via Fast-Slow Interactive Reasoningaccepted
  618. Towards Open-Vocabulary Industrial Defect Understanding with a Large-Scale Multimodal Datasetaccepted
  619. Towards Persistence: Learning Topological Constraints for Event-based Small Object Detectionaccepted
  620. Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Frameworkaccepted
  621. Towards Policy-Adaptive Image Guardrail: Benchmark and Methodaccepted
  622. Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Trainingaccepted
  623. Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priorsaccepted
  624. Towards Reasoning-Preserving Unlearning in Multimodal Large Language Modelsaccepted
  625. Towards Reliable Evaluation of Adversarial Robustness for Spiking Neural Networksaccepted
  626. Towards Robust Multi-Modal Semantic Segmentation with Teacher-Student Framework and Hybrid Prototype Distillationaccepted
  627. Towards Robust Multimodal Large Language Models Against Jailbreak Attacksaccepted
  628. Towards Robust Sequential Decomposition for Complex Image Editingaccepted
  629. Towards Robust Vision Transformers: Path Dependency Analysis and a Simple Two-Stage Adversarial Trainingaccepted
  630. Towards Sparse Video Understanding and Reasoningaccepted
  631. Towards Stable Federated Continual Test-Time Adaptation in Wild Worldaccepted
  632. Towards Stable Self-Supervised Object Representations in Unconstrained Egocentric Videoaccepted
  633. Towards Stealthy and Effective Backdoor Attacks on Lane Detection: A Naturalistic Data Poisoning Approachaccepted
  634. Towards Storytelling Animations: Joint Synthesis of Human and Camera Motionsaccepted
  635. Towards Streaming Referring Video Segmentation via Large Language Modelaccepted
  636. Towards Training-free Scene Text Editingaccepted
  637. Towards Uncertainty-aware Unsupervised Domain Adaptation for Videos and Time-Series with Causal Optimal Transportaccepted
  638. Towards Unified Human Perception and Machine Understanding: Token Flow Guided Compression Frameworkaccepted
  639. Towards Universal Computational Aberration Correction in Photographic Cameras: A Comprehensive Benchmark Analysisaccepted
  640. Towards Visual Query Localization in the 3D Worldaccepted
  641. Towards an Incremental Unified Multimodal Anomaly Detection: Augmenting Multimodal Denoising From an Information Bottleneck Perspectiveaccepted
  642. TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videosaccepted
  643. TrackMAE: Video Representation Learning via Track Mask and Predictaccepted
  644. Tracking by Predicting 3-D Gaussians Over Timeaccepted
  645. Tracking through Severe Occlusion via Event-Derived Transient Cuesaccepted
  646. Tracking-Guided 4D Generation: Foundation-Tracker Motion Priors for 3D Model Animationaccepted
  647. TrafficAlign: Aligning Large Language Models for Traffic Scenario Generationaccepted
  648. Trainable Log-linear Sparse Attention for Efficient Diffusion Transformersaccepted
  649. Training High-Level Schedulers with Execution-Feedback Reinforcement Learning for Long-Horizon GUI Automationaccepted
  650. Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learningaccepted
  651. Training-Free Open-Vocabulary Camouflaged Object Segmentation via Fine-Grained Object Binding and Adaptive Hybrid Promptaccepted
  652. Training-Only Heterogeneous Image-Patch-Text Graph Supervision for Advancing Few-Shot Learning Adaptersaccepted
  653. Training-free Detection of Generated Videos via Spatial-Temporal Likelihoodsaccepted
  654. Training-free Mixed-Resolution Latent Upsampling for Spatially Accelerated Diffusion Transformersaccepted
  655. Training-free Motion Factorization for Compositional Video Generationaccepted
  656. Training-free, Perceptually Consistent Low-Resolution Previews with High-Resolution Image for Efficient Workflows of Diffusion Modelsaccepted
  657. TrajRAG: Retrieving Geometric-Semantic Experience for Zero-Shot Object Navigationaccepted
  658. TrajTok: Learning Trajectory Tokens Enhances Video Understandingaccepted
  659. TransPrune: Token Transition Pruning for Efficient Large Vision-Language Modelaccepted
  660. Transform to Transfer: Boosting Adversarial Attack Transferability on Vision-Language Pre-training Modelsaccepted
  661. Transition Matching Distillation for Fast Video Generationaccepted
  662. Transition Models: Rethinking the Generative Learning Objectiveaccepted
  663. Translating Signals to Languages for sEMG-Based Activity Recognitionaccepted
  664. TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Explorationaccepted
  665. Tri-Modal Fusion Transformers for UAV-based Object Detectionaccepted
  666. Tri-Subspaces Disentanglement for Multimodal Sentiment Analysisaccepted
  667. TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detectionaccepted
  668. TriLite: Efficient Weakly Supervised Object Localization with Universal Visual Features and Tri-Region Disentanglementaccepted
  669. TriSim: Tri-Dimensional Similarity Modeling with Extreme Value Theory for False-Negative Mitigation in Remote Sensing Image-Text Retrievalaccepted
  670. TruckDrive: Long-Range Autonomous Highway Driving Datasetaccepted
  671. Trust-calibrated Collaborative Learning for Long-Tailed Visual Recognitionaccepted
  672. Tunable Soft Equivariance with Guaranteesaccepted
  673. Turbo-GS: Accelerating 3D Gaussian Fitting for High-Resolution Radiance Fieldsaccepted
  674. Turning Pre-Trained Vision Transformers into End-to-End Histopathology Whole Slide Image Models for Survival Predictionaccepted
  675. Tutor-Student Reinforcement Learning: A Dynamic Curriculum for Robust Deepfake Detectionaccepted
  676. Twin-T & TwintVQA: A Reliable Structure-Detail Separating VLM and a Comprehensive Benchmark for Chart and Table Tasksaccepted
  677. U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generationaccepted
  678. U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequencesaccepted
  679. UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancementaccepted
  680. UAST: Unified Active Search and Tracking for Arbitrary Targets with UAVsaccepted
  681. UAV-CB: A Complex-Background RGB-T Dataset and Local Frequency Bridge Network for UAV Detectionaccepted
  682. UAVLight: A Benchmark for Illumination-Robust 3D Reconstruction in Unmanned Aerial Vehicle (UAV) Scenesaccepted
  683. UCAN: Unified Convolutional Attention Network for Expansive Receptive Fields in Lightweight Super-Resolutionaccepted
  684. UCMNet: Uncertainty-Aware Context Memory Network for Under-Display Camera Image Restorationaccepted
  685. UDAPose: Unsupervised Domain Adaptation for Low-Light Human Pose Estimationaccepted
  686. UETrack: A Unified and Efficient Framework for Single Object Trackingaccepted
  687. UFO: Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene Modelingaccepted
  688. UFVideo: Towards Unified Fine-Grained Video Cooperative Understanding with Large Language Modelsaccepted
  689. UI-Lens: Assessing General MLLMs' Potential to Automate UI Display Quality Assuranceaccepted
  690. UIKA: Fast Universal Head Avatar from Pose-Free Imagesaccepted
  691. ULF-Loc: Unbiased Landmark Feature for Robust Visual Localization with 3D Gaussian Splattingaccepted
  692. UNI-OOD: Unified Object- and Image-level Out-of-Distribution Detection via Cross-Context Attentive Vision-Language Modelingaccepted
  693. UNICBench: UNIfied Counting Benchmark for MLLMaccepted
  694. UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attendersaccepted
  695. URICA: A Uniformity Region Affine Identifier Capture Algorithm for Arbitrary Region Retrieval in Pathology Imagesaccepted
  696. URScenes: A Multi-scenario Dataset for Unstructured Road Environmentsaccepted
  697. UST-Hand: An Uncertainty-aware Spatiotemporal Point Cloud Interaction Network for 3D Self-supervised Hand Pose Estimationaccepted
  698. UTPTrack: Towards Simple and Unified Token Pruning for Visual Trackingaccepted
  699. UVU: Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigmaccepted
  700. UZ3DVG: Unaided Zero-Shot 3D Visual Grounding with Generated Language Conditionsaccepted
  701. U^2Flow: Uncertainty-Aware Unsupervised Optical Flow Estimationaccepted
  702. Ultra Diffusion Poser: Diffusion-Based Human Motion Tracking from Sparse Inertial Sensors and Ranging-based Between-sensor Distancesaccepted
  703. Ultra-Fast Neural Video Compressionaccepted
  704. Ultra-Low Bitrate Perceptual Image Compression with Shallow Encoderaccepted
  705. UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratiosaccepted
  706. Ultrasound-CLIP: Semantic-Aware Contrastive Pre-training for Ultrasound Image-Text Understandingaccepted
  707. UnReflectAnything: RGB-Only Highlight Removal by Rendering Synthetic Specular Supervisionaccepted
  708. Unblur-SLAM: Dense Neural SLAM for Blurry Inputsaccepted
  709. Uncertainty-Aware Exploratory Direct Preference Optimization for Multimodal Large Language Modelsaccepted
  710. Uncertainty-Aware Knowledge Distillation for Multimodal Large Language Modelsaccepted
  711. Uncertainty-Aware Modality Fusion for Unaligned RGB-T Salient Object Detectionaccepted
  712. Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Fieldaccepted
  713. Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Modelsaccepted
  714. Underground Plant Exploration: Non-Destructive 3D Root Assessment with GPR Based on Point Graph Neural Networkaccepted
  715. Understanding Counting Mechanisms in Large Language and Vision-Language Modelsaccepted
  716. Understanding Task Transfer in Vision-Language Modelsaccepted
  717. Understanding Temporal Logic Consistency in Video-Language Models through Cross-Modal Attention Discriminabilityaccepted
  718. Understanding and Enforcing Weight Disentanglement in Task Arithmeticaccepted
  719. Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought Modelsaccepted
  720. Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Modelsaccepted
  721. Understanding, Accelerating, and Improving MeanFlow Trainingaccepted
  722. Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generationaccepted
  723. Uni-Encoder Meets Multi-Encoders: Representation Before Fusion for Brain Tumor Segmentation with Missing Modalitiesaccepted
  724. Uni-Hema: Unified Model for Digital Hematopathologyaccepted
  725. Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Imagesaccepted
  726. UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactionsaccepted
  727. UniChange: Unifying Change Detection with Multimodal Large Language Modelaccepted
  728. UniComp: Rethinking Video Compression Through Informational Uniquenessaccepted
  729. UniCompress: Token Compression for Unified Vision-Language Understanding and Generationaccepted
  730. UniCorrn: Unified Correspondence Transformer Across 2D and 3Daccepted
  731. UniDAC: Universal Metric Depth Estimation for Any Cameraaccepted
  732. UniDef: Universal Defense Against Unauthorized Image Manipulationaccepted
  733. UniDex: A Robot Foundation Suite for Universal Dexterous Hand Control from Egocentric Human Videosaccepted
  734. UniEdit-I: Training-free Image Editing for Unified VLM via Iterative Understanding, Editing and Verifyingaccepted
  735. UniFusion: A Unified Image Fusion Framework with Robust Representation and Source-Aware Preservationaccepted
  736. UniGame: Turning a Unified Multimodal Model Into Its Own Adversaryaccepted
  737. UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in RLaccepted
  738. UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detectionaccepted
  739. UniGeoRS: A Unified Benchmark for Tri-view Geo-Localizationaccepted
  740. UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenesaccepted
  741. UniLDiff: Unlocking the Power of Diffusion Priors for All-in-One Image Restorationaccepted
  742. UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speakingaccepted
  743. UniLight: A Unified Representation for Lightingaccepted
  744. UniM: A Unified Any-to-Any Interleaved Multimodal Benchmarkaccepted
  745. UniMERNet: A Universal Network for Real-World Mathematical Expression Recognitionaccepted
  746. UniMMAD: Unified Multi-Modal and Multi-Class Anomaly Detection via MoE-Driven Feature Decompressionaccepted
  747. UniPR: Unified Object-level Real-to-Sim Perception and Reconstruction from a Single Stereo Pairaccepted
  748. UniPart: Part-Level 3D Generation with Unified 3D Geom-Seg Latentsaccepted
  749. UniPercept: A Unified Diffusion Model for Generalizable Visual Perceptionaccepted
  750. UniPixie: Unified and Probabilistic 3D Physics Learning via Flow Matchingaccepted
  751. UniRain: Unified Image Deraining with RAG-based Dataset Distillation and Multi-objective Reweighted Optimizationaccepted
  752. UniRefiner: Teaching Pre-trained ViTs to Self-Dispose Dross via Contrastive Registeraccepted
  753. UniSER: A Foundation Model for Unified Soft Effects Removalaccepted
  754. UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Passaccepted
  755. UniSpector: Towards Universal Open-set Defect Recognition via Spectral-Contrastive Visual Promptingaccepted
  756. UniT: Unified Multimodal Chain-of-Thought Test-time Scalingaccepted
  757. UniTEX: Universal High Fidelity Generative Texturing for 3D Shapesaccepted
  758. UniVBench: Towards Unified Evaluation for Video Foundation Modelsaccepted
  759. UniVerse: A Unified Modulation Framework for Segmentation-Free, Disentangled Multi-Concept Personalizationaccepted
  760. UniVerse: Empower Unified Generation with Reasoning and Knowledgeaccepted
  761. UnicEdit-10M: A Dataset and Benchmark Breaking the Scale-Quality Barrier via Unified Verification for Reasoning-Enriched Editsaccepted
  762. Unified Camera Positional Encoding for Controlled Video Generationaccepted
  763. Unified Customized Generation by Disentangled Reward Modelingaccepted
  764. Unified Generation and Self-Verification for Vision-Language Models via Advantage Decoupled Preference Optimizationaccepted
  765. Unified Latent Space for Understanding and Generation via Semantic Auto-encoderaccepted
  766. Unified Multimodal Models as Auto-Encodersaccepted
  767. Unified Number-Free Text-to-Motion Generation Via Flow Matchingaccepted
  768. Unified Personalized Understanding, Generating and Editingaccepted
  769. Unified Primitive Proxies for Structured Shape Completionaccepted
  770. Unified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retentionaccepted
  771. Unified Spherical Frontend: Learning Rotation-Equivariant Representations of Spherical Images from Any Cameraaccepted
  772. Unified Vector Floorplan Generation via Markup Representationaccepted
  773. Unifying Language-Action Understanding and Generation for Autonomous Drivingaccepted
  774. Unifying Perception and Action: A Hybrid-Modality Pipeline with Implicit Visual Chain-of-Thought for Robotic Action Generationaccepted
  775. Unifying Precise Keyframes and Semantic Control via Multi-level Diffusionaccepted
  776. Unique Lives, Shared World: Learning from Single-Life Videosaccepted
  777. UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generationaccepted
  778. Universal 3D Shape Matching via Coarse-to-Fine Language Guidanceaccepted
  779. Universal Guideline-Driven Image Clustering via a Hybrid LLM Agentaccepted
  780. Universal-to-Specific: Dynamic Knowledge-Guided Multiple Instance Learning for Few-Shot Whole Slide Image Classificationaccepted
  781. Unlearning without Forgetting: Securely Removing Targeted Concepts from Large-Scale Vision-Language Open-Vocabulary Detectorsaccepted
  782. Unleashing Stealthy Backdoor Pandemic by Infecting a Single Diffusion Modelaccepted
  783. Unleashing VLA Potentials in Autonomous Driving via Explicit Learning from Failuresaccepted
  784. Unleashing Vision-Language Semantics for Deepfake Video Detectionaccepted
  785. Unleashing the Intrinsic Visual Representation Capability of Multimodal Large Language Modelsaccepted
  786. Unleashing the Power of Chain-of-Prediction for Monocular 3D Object Detectionaccepted
  787. Unlocking 3D Affordance Segmentation with 2D Semantic Knowledgeaccepted
  788. Unlocking Motion from Large Vision Models with a Semantic and Kinematic Duality for Gait Recognitionaccepted
  789. Unlocking Positive Transfer in Incrementally Learning Surgical Instruments: A Self-reflection Hierarchical Prompt Frameworkaccepted
  790. Unlocking Pre-trained Weights: Parameter Inheritance for Zero-Shot Initializationaccepted
  791. Unlocking Strong Supervision: A Data-Centric Study of General-Purpose Audio Pre-Training Methodsaccepted
  792. Unlocking Token Rewards via Training-Free Reward Attributionaccepted
  793. Unlocking the Power of Critical Factors for 3D Visual Geometry Estimationaccepted
  794. Unpaired Image Deraining Using Reward-Guided Self-Reinforcement Strategyaccepted
  795. Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Imagesaccepted
  796. Unsafe2Safe: Controllable Image Anonymization for Downstream Utilityaccepted
  797. Unstitching the Chimera: Frame-Level Risk and Train-Free Mitigation for Video Hallucinationaccepted
  798. Unsupervised 3d Motion Estimation Using Event Cameraaccepted
  799. Unsupervised Monocular 3D Keypoint Discovery from Multi-View Diffusion Priorsaccepted
  800. Unsupervised Multi-Scale Segmentation of 3D Subcellular World with Stable Diffusion Foundation Modelaccepted
  801. Unsupervised Multi-agent and Single-agent Perception from Cooperative Viewsaccepted
  802. Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsamplingaccepted
  803. Urban-GS: A Unified 3D Gaussian Splatting Framework for Compact and High-Fidelity Aerial-to-Street Reconstructionaccepted
  804. V-Attack: Targeting Disentangled Value Features for Controllable Adversarial Attacks on LVLMsaccepted
  805. V-DPM: 4D Video Reconstruction with Dynamic Point Mapsaccepted
  806. V-RGBX: Video Editing with Accurate Controls over Intrinsic Propertiesaccepted
  807. V2U4Real: A Real-world Large-scale Dataset for Vehicle-to-UAV Cooperative Perceptionaccepted
  808. VA-p: Variational Policy Alignment for Pixel-Aware Autoregressive Generationaccepted
  809. VABench: A Comprehensive Benchmark for Audio-Video Generationaccepted
  810. VAD-GS: Visibility-Aware Densification for 3D Gaussian Splatting in Dynamic Urban Scenesaccepted
  811. VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generationaccepted
  812. VAST: Video Ability-Stratified Taxonomy for Data-Efficient Video Reasoningaccepted
  813. VCP-Attack: Visual-Contrastive Projection for Transferable Black-Box Targeted Attacks on Large Vision-Language Modelsaccepted
  814. VCU-Bridge: Hierarchical Visual Connotation Understanding via Semantic Bridgingaccepted
  815. VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimationaccepted
  816. VDFE: Difference-Aware 3D Scene Editing with Non-Intrusive Video Diffusion Priors for Multi-View Consistency and Efficiencyaccepted
  817. VDOT: Efficient Unified Video Creation via Optimal Transport Distillationaccepted
  818. VEMamba: Efficient Isotropic Reconstruction of Volume Electron Microscopy with Axial-Lateral Consistent Mambaaccepted
  819. VENI: Variational Encoder for Natural Illuminationaccepted
  820. VES-RFT: Rewarding Visual Evidence Sensitivity to Mitigate Hallucinations in Large Vision-Language Modelsaccepted
  821. VGA-Bench: A Unified Benchmark and Multi-Model Framework for Video Aesthetics and Generation Quality Evaluationaccepted
  822. VGA: Empowering Aerial-Ground Localization by Visual Geometry Alignmentaccepted
  823. VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scaleaccepted
  824. VGGDrive: Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous Drivingaccepted
  825. VGGT-360: Geometry-Consistent Zero-Shot Panoramic Depth Estimationaccepted
  826. VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detectionaccepted
  827. VGGT-Segmentor: Geometry-Enhanced Cross-View Segmentationaccepted
  828. VGGT-Ωaccepted
  829. VGent: Visual Grounding via Modular Design for Disentangling Reasoning and Predictionaccepted
  830. VIAFormer: Voxel-Image Alignment Transformer for High-Fidelity Voxel Refinementaccepted
  831. VIMCAN: Visual-Inertial 3D Human Pose Estimation with Hybrid Mamba-Cross-Attention Networkaccepted
  832. VINS-120K: Ultra High-Resolution Image Editing with A Large-Scale Datasetaccepted
  833. VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulationaccepted
  834. VIRD: View-Invariant Representation through Dual-Axis Transformation for Cross-View Pose Estimationaccepted
  835. VIRO: Robust and Efficient Neuro-Symbolic Reasoning with Verification for Referring Expression Comprehensionaccepted
  836. VIRST: Video-Instructed Reasoning Assistant for SpatioTemporal Segmentationaccepted
  837. VISTA: A Test-Time Self-Improving Video Generation Agentaccepted
  838. VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactionsaccepted
  839. VITAL: Vision-Encoder-centered Pre-training for LMMs in Visual Quality Assessmentaccepted
  840. VIVA: VLM-Guided Instruction-Based Video Editing with Reward Optimizationaccepted
  841. VKG-QA: Visual Knowledge Graph-based Question Answer for Large Multimodal Modelsaccepted
  842. VL-Eraser: Vacuum Distillation for Machine Unlearning in Vision-Language Modelsaccepted
  843. VL-RouterBench: A Benchmark for Vision-Language Model Routingaccepted
  844. VLA Models Are More Generalizable Than You Think: Revisiting Physical and Spatial Modelingaccepted
  845. VLIC: Vision-Language Models As Perceptual Judges for Human-Aligned Image Compressionaccepted
  846. VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstructionaccepted
  847. VLM-Guided Group Preference Alignment for Diffusion-based Human Mesh Recoveryaccepted
  848. VLM-Loc: Localization in Point Cloud Maps via Vision-Language Modelsaccepted
  849. VLM-PTQ: Efficient Post-Training Quantization for Large Vision-Language Modelsaccepted
  850. VLM-Pruner: Buffering for Spatial Sparsity in an Efficient VLM Centrifugal Token Pruning Paradigmaccepted
  851. VLM4RSDet: Collaborative Optimization with Vision-Language Model for Enhancing Remote Sensing Object Detectionaccepted
  852. VMD-FACT: A New Video Dataset and MLLM-based method for Detecting Realistic AI-Generated Video Misinformationaccepted
  853. VMonarch: Efficient Video Diffusion Transformers with Structured Attentionaccepted
  854. VOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy Distillationaccepted
  855. VOSR: A Vision-Only Generative Model for Image Super-Resolutionaccepted
  856. VQ-VA World: Towards High-Quality Visual Question-Visual Answeringaccepted
  857. VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstructionaccepted
  858. VRCLIP: Multimodal Canonical Correlation Alignment for CLIP-Driven Vision-Radio Person Re-Identificationaccepted
  859. VRR-QA: Visual Relational Reasoning in Videos Beyond Explicit Cuesaccepted
  860. VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environmentsaccepted
  861. VSRELL: A Simple Baseline for Video Super-Resolution and Enhancement in Low-Light Environmentaccepted
  862. VT-Intrinsic: Physics-Based Decomposition of Reflectance and Shading using a Single Visible-Thermal Image Pairaccepted
  863. VULCAN: Tool-Augmented Multi Agents for Iterative 3D Object Arrangementaccepted
  864. VVS: Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial Verification Skippingaccepted
  865. V^2-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondenceaccepted
  866. Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervisionaccepted
  867. VarSplat: Uncertainty-aware 3D Gaussian Splatting for Robust RGB-D SLAMaccepted
  868. Variation-aware Vision Token Dropping for Faster Large Vision-Language Modelsaccepted
  869. Variational Graph-based Normal Integrationaccepted
  870. VecAttention: Vector-wise Sparse Attention for Accelerating Long Context Inferenceaccepted
  871. VecGlypher: Unified Vector Glyph Generation with Language Modelsaccepted
  872. Vector Prism: Animating Vector Graphics by Stratifying Semantic Structureaccepted
  873. VectorArk: Learning Practical Image Vectorization with Rounded Polygon Representationaccepted
  874. Velox: Learning Representations of 4D Geometry and Appearanceaccepted
  875. Venus: Benchmarking and Empowering Multimodal Large Language Models for Aesthetic Guidance and Croppingaccepted
  876. Verifying Neural Network Robustness with Dual Perturbationsaccepted
  877. VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Controlaccepted
  878. VesMamba: 3D Pulmonary Vessel Segmentation from CT images via Mamba with Structural Perception and Scale-aware Filteringaccepted
  879. ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Bodyaccepted
  880. ViHOI: Human-Object Interaction Synthesis with Visual Priorsaccepted
  881. ViKey: Enhancing Temporal Understanding in Videos via Visual Promptingaccepted
  882. ViLearn: Accelerating Training Convergence of Image-to-3D Generation via Visibility Learningaccepted
  883. ViLoMem: Agentic Learner with Grow-and-Refine Multimodal Semantic Memoryaccepted
  884. ViRC: Enhancing Visual Interleaved Mathematical CoT with Reason Chunkingaccepted
  885. ViStoryBench: Comprehensive Benchmark Suite for Story Visualizationaccepted
  886. ViT$^3$: Unlocking Test-Time Training in Visionaccepted
  887. ViTPrompt: Training-Free Prompt Refinement with Visual Tokens for Open-Vocabulary Detectionaccepted
  888. Vibe Spaces for Creatively Connecting and Expressing Visual Conceptsaccepted
  889. VibeToken: Scaling 1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generationsaccepted
  890. VidEoMT: Your ViT is Secretly Also a Video Segmentation Modelaccepted
  891. VidPrism: Heterogeneous Mixture of Experts for Image-to-Video Transferaccepted
  892. VidTAG: Temporally Aligned Video to GPS Geolocalization with Denoising Sequence Prediction at a Global Scaleaccepted
  893. Video Generation with Stable Transparency via Shiftable RGB-A Distribution Learneraccepted
  894. Video Panels for Long Video Understandingaccepted
  895. Video-CoE: Reinforcing Video Event Prediction via Chain of Eventsaccepted
  896. Video-Only ToM: Enhancing Theory of Mind in Multimodal Large Language Modelsaccepted
  897. Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPOaccepted
  898. Video2Robo: 3DGS-based Synthetic Data from One Video Enables Scalable Robot Learningaccepted
  899. VideoARM: Agentic Reasoning over Hierarchical Memory for Long-Form Video Understandingaccepted
  900. VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twiceaccepted
  901. VideoChat-M1: Collaborative Policy Planning for Video Understanding via Multi-Agent Reinforcement Learningaccepted
  902. VideoCoF: Unified Video Editing with Temporal Reasoneraccepted
  903. VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusionaccepted
  904. VideoITG: Multimodal Video Understanding with Instructed Temporal Groundingaccepted
  905. VideoMaMa: Mask-Guided Video Matting via Generative Prioraccepted
  906. VideoNet: A Large-Scale Dataset for Domain-Specific Action Recognitionaccepted
  907. VideoRealBench: A Chain-of-Thought Realism Evaluation Benchmark for Generated Human-Centric Videosaccepted
  908. VideoSSR: Video Self-Supervised Reinforcement Learningaccepted
  909. VideoSeek: Long-Horizon Video Agent with Tool-Guided Seekingaccepted
  910. VideoWeaver: Multimodal Multi-View Video-to-Video Transfer for Embodied Agentsaccepted
  911. VideoWorld 2: Learning Transferable Knowledge from Real-world Videosaccepted
  912. View-Aware Semantic Alignment for Aerial-Ground Person Re-Identificationaccepted
  913. VinQA: Visual Elements Interleaved Long-form Answer Generation for Real-World Multimodal Document QAaccepted
  914. Vinedresser3D: Towards Agentic Text-guided 3D Editingaccepted
  915. Virtual Full-stack Scanning of Brain MRI via Imputing Any Quantised Codeaccepted
  916. Virtual Immunohistochemistry Staining with Dual-Aligned Multi-Task Feature Guidanceaccepted
  917. Virtual Nodes Guided Dynamic Graph Neural Network for Brain Tumor Segmentation with Missing Modalitiesaccepted
  918. VirtueBench: Evaluating Trustworthiness under Uncertainty in Long Video Understandingaccepted
  919. VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Modelsaccepted
  920. VisPlay: Self-Evolving Vision-Language Modelsaccepted
  921. VisRef: Visual Refocusing while Thinking Improves Test-Time Scaling in Multi-Modal Large Reasoning Modelsaccepted
  922. VisRes Bench: On Evaluating the Visual Reasoning Capabilities of VLMsaccepted
  923. VisiLock: Authorizing Instruction-based Image editing with Dual Score Distillationaccepted
  924. Vision Foundation Models Can Be Good Tokenizers for Latent Diffusion Modelsaccepted
  925. Vision Transformers Need More Than Registersaccepted
  926. Vision-Language Attribute Disentanglement and Reinforcement for Lifelong Person Re-Identificationaccepted
  927. Vision-Language Model Guided Source-Free Domain Adaptation via Optimal Transportaccepted
  928. Vision-Oriented Lightweight Neural Architecture Search with Budget-Adaptive Evaluationaccepted
  929. Vision-Speech Models: Teaching Speech Models to Converse about Imagesaccepted
  930. VisionDirector: Vision-Language Guided Closed-Loop Refinement for Generative Image Synthesisaccepted
  931. VisionLeaf: Entropy-Guided Leaf-First Reasoning for Efficient and Accurate Think-with-Imageaccepted
  932. Vista4D: Video Reshooting with 4D Point Cloudsaccepted
  933. Visual Diffusion Models are Geometric Solversaccepted
  934. Visual Document Understanding and Reasoning: A Multi-Agent Collaboration Framework with Agent-Wise Adaptive Test-Time Scalingaccepted
  935. Visual Grounding for Object Questionsaccepted
  936. Visual Personalization Turing Testaccepted
  937. Visual Prototype Conditioned Focal Region Generation for UAV-Based Object Detectionaccepted
  938. Visual-Aware CoT: Achieving High-Fidelity Visual Consistency in Unified Modelsaccepted
  939. Visual-RRT: Finding Paths toward Visual-Goals via Differentiable Renderingaccepted
  940. VisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformeraccepted
  941. VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenesaccepted
  942. ViterbiPlanNet: Injecting Procedural Knowledge via Differentiable Viterbi for Planning in Instructional Videosaccepted
  943. VoDaSuRe: A Large-Scale Dataset Revealing Domain Shift in Volumetric Super-Resolutionaccepted
  944. Vocabulary Scaling Law: Tuning Open-vocabulary Predictors for Their Opennessaccepted
  945. Volumetric Functional Mapsaccepted
  946. VoxTell: Free-Text Promptable Universal 3D Medical Image Segmentationaccepted
  947. Voxify3D: Pixel Art Meets Volumetric Renderingaccepted
  948. W2W: Language-Model-Based Trajectory Prediction with Reinforcement Learningaccepted
  949. WAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Drivingaccepted
  950. WEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generationaccepted
  951. WHU-MARS: A Multispectral Aerial-Ground Benchmark Towards Any-Scenario Person Re-Identificationaccepted
  952. WISER: Wider Search, Deeper Thinking, and Adaptive Fusion for Training-Free Zero-Shot Composed Image Retrievalaccepted
  953. WOD-E2E: Waymo Open Dataset for End-to-End Driving in Challenging Long-tail Scenariosaccepted
  954. WPT: World-to-Policy Transfer via Online World Model Distillationaccepted
  955. WRIVINDER: Towards Spatial Intelligence for Geo-locating Ground Images onto Satellite Imageryaccepted
  956. WaDi: Weight Direction-aware Distillation for One-step Image Synthesisaccepted
  957. WaTeRFlow: Watermark Temporal Robustness via Flow Consistencyaccepted
  958. WalkGPT: Grounded Vision-Language Conversation with Depth-Aware Segmentation for Pedestrian Navigationaccepted
  959. Wan-Weaver: Interleaved Multi-modal Generation via Decoupled Trainingaccepted
  960. Wanderland: Geometrically Grounded Simulation for Open-World Embodied AIaccepted
  961. Watch and Learn: Learning to Use Computers from Online Videosaccepted
  962. Wave-Former: Through-Occlusion 3D Reconstruction via Wireless Shape Completionaccepted
  963. Wavelet-Driven 3D Anomaly Detection under Pose-Agnostic and Sparse-Viewaccepted
  964. Wavelet-based Frame Selection by Detecting Semantic Boundary for Long Video Understandingaccepted
  965. WeDetect: Fast Open-Vocabulary Object Detection as Retrievalaccepted
  966. WeMMU: Enhanced Bridging of Vision-Language Models and Diffusion Models via Noisy Query Tokensaccepted
  967. Weakly Supervised Video Anomaly Detection with Anomaly-Connected Components and Intention Reasoningaccepted
  968. WeatherCity: Urban Scene Reconstruction with Controllable Multi-Weather Transformationaccepted
  969. WeaveTime: Streaming from Earlier Frames into Emergent Memory in VideoLLMsaccepted
  970. WebChain: A Large-Scale Human-Annotated Dataset of Real-World Web Interaction Tracesaccepted
  971. WebGym: Scaling Training Environments for Long-Horizon Visual Web Agents with Realistic Tasksaccepted
  972. Weight Space Representation Learning via Neural Field Adaptationaccepted
  973. What Are You Doing? A Closer Look at Controllable Human Video Generationaccepted
  974. What Do Visual Tokens Really Encode? Uncovering Sparsity and Redundancy in Multimodal Large Language Modelsaccepted
  975. What Is It Like to Be a Noise? An Entropy-based Gaussian Noise Regularization for Diffusion Modelsaccepted
  976. What Is the Optimal Ranking Score Between Precision and Recall? We Can Always Find It and It Is Rarely F1accepted
  977. What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching?accepted
  978. What Matters in Practical Learned Image Compressionaccepted
  979. What Your Features Reveal: Data-Efficient Black-Box Feature Inversion Attack for Split DNNsaccepted
  980. What's Wrong with Synthetic Data for Scene Text Recognition? A Strong Synthetic Engine with Diverse Simulations and Self-Evolutionaccepted
  981. When AVSR Meets Video Conferencing: Dataset, Degradation, and the Hidden Mechanism Behind Performance Collapseaccepted
  982. When Anonymity Breaks: Identifying Models Behind Text-to-Image Leaderboardsaccepted
  983. When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustnessaccepted
  984. When Do Models Actually Decide? Mapping the Layer-Wise Decision Timeline in Pretrained Neural Networksaccepted
  985. When Lines Meet Textures: Spatial-Frequency Aligned Diffusion Features for Cross-Sparsity Correspondenceaccepted
  986. When LoRA Betrays: Backdooring Text-to-Image Models by Masquerading as Benign Adaptersaccepted
  987. When Local Rules Create Global Order: Self-Organized Representation Learning for Latent Diffusion Modelsaccepted
  988. When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Modelsaccepted
  989. When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generatorsaccepted
  990. When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Modelsaccepted
  991. When Robots Should Say ''I Don't Know'': Benchmarking Abstention in Embodied Question Answeringaccepted
  992. When Safety Collides: Resolving Multi-Category Harmful Conflicts in Text-to-Image Diffusion via Adaptive Safety Guidanceaccepted
  993. When Token Pruning is Worse than Random: Understanding Visual Token Information in VLLMsaccepted
  994. When Transformers Meet Mamba: A Hybrid Transformer-Mamba Network for Video Object Detectionaccepted
  995. When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigmaccepted
  996. When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thoughtaccepted
  997. When to Think and When to Look: Uncertainty-Guided Lookbackaccepted
  998. Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generationaccepted
  999. Where Does Vision Meet Language? Understanding and Refining Visual Fusion in MLLMs via Contrastive Attentionaccepted
  1000. Where MLLMs Attend and What They Rely On: Explaining Autoregressive Token Generationaccepted

CVPR accepted papers in other years

CVPR 2025 (2,872)CVPR 2024 (2,640)CVPR 2023 (2,307)CVPR 2022 (2,043)CVPR 2021 (1,659)CVPR 2020 (1,466)CVPR 2019 (1,294)CVPR 2018 (979)CVPR 2017 (783)CVPR 2016 (643)CVPR 2015 (602)

Looking for submission deadlines instead? See the conference deadline calendar.