CVPR 2026 Accepted Papers

The full list of 4,068 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.

1. $L^{2}DGS$: Low-Light Dynamic Gaussian Splattingaccepted
2. $\alpha$Matte4K & $\mu$Matting: Dataset and Model for Ultra-Micro Precision Alpha Video Mattingaccepted
3. $\oslash$ Source Models Leak What They Shouldn't $\nrightarrow$: Unlearning Zero-Shot Transfer in Domain Adaptation Through Adversarial Optimizationaccepted
4. $\phi$-DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Modelsaccepted
5. 2-Shots in the Dark: Low-Light Denoising with Minimal Data Acquisitionaccepted
6. 240FPS Stereo Vision from Monocular Mixed Spikesaccepted
7. 2D-LFM: Lifting Foundation Model without 3D Supervisionaccepted
8. 2ndMatch: Finetuning Pruned Diffusion Models via Second-Order Jacobian Matchingaccepted
9. 3D Gaussian Splatting at Arbitrary Resolutions with Compact Proxy Anchorsaccepted
10. 3D Gaussian Splatting from Unposed Spike Streamaccepted
11. 3D Gaussian Splatting with Self-Constrained Priors for High Fidelity Surface Reconstructionaccepted
12. 3D Space as a Scratchpad for Editable Text-to-Image Generationaccepted
13. 3D sans 3D Scans: Scalable Pre-training from Video-Generated Point Cloudsaccepted
14. 3D-Aware Implicit Motion Control for View-Adaptive Human Video Generationaccepted
15. 3D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understandingaccepted
16. 3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Imageaccepted
17. 3D-IDE: 3D Implicit Depth Emergentaccepted
18. 3D-LATTE: Latent Space 3D Editing from Textual Instructionsaccepted
19. 3D-Object Perception Transformer (3PT)accepted
20. 3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decodingaccepted
21. 3DReflecNet: A Large-Scale Dataset for 3D Reconstruction of Reflective, Transparent, and Low-Texture Objectsaccepted
22. 3DrawAgent: Teaching LLM to Draw in 3D with Early Contrastive Experienceaccepted
23. 3M-TI: High-Quality Mobile Thermal Imaging via Calibration-free Multi-Camera Cross-Modal Diffusionaccepted
24. 4C4D: 4 Camera 4D Gaussian Splattingaccepted
25. 4D Local Modeling Toward Dynamic Global Perception for Ambiguity-free Rotation-Invariant Point Cloud Analysisaccepted
26. 4D Primitive-Mache: Glueing Primitives for Persistent 4D Scene Reconstructionaccepted
27. 4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillationaccepted
28. 4DEquine: Disentangling Motion and Appearance for 4D Equine Reconstruction from Monocular Videoaccepted
29. 4DP-QA: Scalable QA for 4D Perception in Vision Language Modelsaccepted
30. 4DSurf: High-Fidelity Dynamic Scene Surface Reconstructionaccepted
31. 4DWorldBench: A Comprehensive Evaluation Framework for 3D/4D World Generation Modelsaccepted
32. A Bit is All You Need! Efficient Video Capture via Single Bit Imagingaccepted
33. A Causal Marriage between VLM and IRM from Understanding to Reasoningaccepted
34. A Closed-Form Solution for Debiasing Vision-Language Models with Utility Guarantees Across Modalities and Tasksaccepted
35. A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helpsaccepted
36. A Combination of Noise and Bilateral Filters Achieve Supralinear and Scalable Adversarial Robustness in CNNsaccepted
37. A Cross-view Fusion Framework for Robust 6-DoF Grasp Pose Estimationaccepted
38. A Debiased Reconstruction-based Framework for Training-Free Detection of AI-Generated Imagesaccepted
39. A Difference-in-Difference Approach to Detecting AI-Generated Imagesaccepted
40. A Faster Path to Continual Learningaccepted
41. A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokensaccepted
42. A Geometric Algebra-Informed 3DGS Framework for Wireless Channel Predictionaccepted
43. A Mixed Diet Makes DINO An Omnivorous Vision Encoderaccepted
44. A More Word-like Image Tokenization for MLLMsaccepted
45. A Multi-Agent Perception-Action Alliance for Efficient Long Video Reasoningaccepted
46. A Polynomial Chaos Framework for Causal Discovery in Nonlinear Uncertain Systemsaccepted
47. A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large Vision-Language Modelsaccepted
48. A Sanity Check for Multi-In-Domain Face Forgery Detection in the Real Worldaccepted
49. A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generationaccepted
50. A Semantically Disentangled Unified Model for Multi-category 3D Anomaly Detectionaccepted
51. A Stitch in Time: Learning Procedural Workflow via Self-Supervised Plackett-Luce Rankingaccepted
52. A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Spaceaccepted
53. A Supervised Multi-task Framework for Joint cryo-ET Restoration Enabled by Generative Physical Simulationaccepted
54. A Temporal and Content Co-Awareness Latent Diffusion for Controllable Hand Image Generationaccepted
55. A Training-Free Style-Personalization via SVD-Based Feature Decompositionaccepted
56. A Unified Framework for Knowledge Transfer in Bidirectional Model Scalingaccepted
57. A Unified Perspective on Adversarial Membership Manipulation in Vision Modelsaccepted
58. A2GC: Asymmetric Aggregation with Geometric Constraints for Locally Aggregated Descriptorsaccepted
59. A3: Towards Advertising Aesthetic Assessmentaccepted
60. ACE-Merging: Data-Free Model Merging with Adaptive Covariance Estimationaccepted
61. ACPV-Net: All-Class Polygonal Vectorization for Seamless Vector Map Generation from Aerial Imageryaccepted
62. ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Modelsaccepted
63. AD-GBC: Anisotropic Granular-Ball Skip-Connection Refiner for UNet-Based Medical Image Segmentationaccepted
64. ADSeeker: A Knowledge-Grounded Reasoning Framework for Industry Anomaly Detection and Reasoningaccepted
65. AE2VID: Event-based Video Reconstruction via Aperture Modulationaccepted
66. AERGS-SLAM: Auto-Exposure-Robust Stereo 3D Gaussian Splatting SLAMaccepted
67. AG-VAS: Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Modelsaccepted
68. AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructionsaccepted
69. AGFT: Alignment-Guided Fine-Tuning for Zero-Shot Adversarial Robustness of Vision-Language Modelsaccepted
70. AGiLe: Learning Robust Long-Horizon Manipulation via Affordance-Grounded Bidirectional Latent Planningaccepted
71. AHS: Adaptive Head Synthesis via Synthetic Data Augmentationsaccepted
72. AIMDepth: Asymmetric Image-Event Mamba for Monocular Depth Estimationaccepted
73. AKCMamba-YOLO: Selective State Space Models For Real-Time Object Detectionaccepted
74. ALLNet: Multi-task Dense Prediction for Degraded Imagesaccepted
75. AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backendaccepted
76. AMap: Distilling Future Priors for Ahead-Aware Online HD Map Constructionaccepted
77. AMusE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understandingaccepted
78. ANTS: Adaptive Negative Textual Space Shaping for OOD Detection via Test-Time MLLM Understanding and Reasoningaccepted
79. APEX: A Decoupled Memory-based Explorer for Asynchronous Aerial Object Goal Navigationaccepted
80. APPO: Attention-guided Perception Policy Optimization for Video Reasoningaccepted
81. AR2-4FV: Anchored Referring and Re-identification for Long-Term Grounding in Fixed-View Videosaccepted
82. ARC Is a Vision Problem!accepted
83. AREA3D: Active Reconstruction Agent with Unified Feed-Forward 3D Perception and Vision-Language Guidanceaccepted
84. ARES: Unifying Asymmetric RGB-Event Stereo for Probabilistic Scene Flow Estimationaccepted
85. ARGUS: Defending Against Multimodal Indirect Prompt Injection via Steering Instruction-Following Behavioraccepted
86. ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoningaccepted
87. ARMFlow: AutoRegressive MeanFlow for Online 3D Human Reaction Generationaccepted
88. ART: Articulated Reconstruction Transformeraccepted
89. AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Modelsaccepted
90. AToken: A Unified Tokenizer for Visionaccepted
91. AURA: Multi-modal Shared Autonomy for Urban Navigationaccepted
92. AV-Reasoner: Improving and Benchmarking Clue-Grounded Audio-Visual Counting for MLLMsaccepted
93. AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Modelsaccepted
94. AVA-VLA: Improving Vision-Language-Action models with Active Visual Attentionaccepted
95. AVATAR: Reinforcement Learning to See, Hear, and Reason Over Videoaccepted
96. AVFakeBench: A Comprehensive Audio-Video Forgery Detection Benchmark for AV-LMMsaccepted
97. AVGGT: Rethinking Global Attention for Accelerating VGGTaccepted
98. AVION: Aerial Vision-Language Instruction from Offline Teacher to Prompt-Tuned Networkaccepted
99. AXG-Reasoner: Error Detection and Explanation in Long Task Videos with Vision-Language Modelsaccepted
100. Abstract 3D Perception for Spatial Intelligence in Vision-Language Modelsaccepted
101. AcTTA: Rethinking Test-Time Adaptation via Dynamic Activationaccepted
102. Accelerating Autoregressive Video Diffusion via History-Guided Cache and Residual Correctionaccepted
103. Accelerating Diffusion Model Training under Minimal Budgets: A Condensation-Based Perspectiveaccepted
104. Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance Schedulingaccepted
105. Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestepaccepted
106. Accelerating Streaming Video Large Language Models via Hierarchical Token Compressionaccepted
107. AceTone: Bridging Words and Colors for Conditional Image Gradingaccepted
108. Act Like a Pathologist: Tissue-Aware Whole Slide Image Reasoningaccepted
109. Act2See: Emergent Active Visual Perception for Video Reasoningaccepted
110. ActAvatar: Temporally-Aware Precise Action Control for Talking Avatarsaccepted
111. Action Motifs: Self-Supervised Hierarchical Representation of Human Body Movementsaccepted
112. Action-Geometry Prediction with 3D Geometric Prior for Bimanual Manipulationaccepted
113. Action-Sketcher: From Reasoning to Action via Visual Sketches for Robotic Manipulationaccepted
114. ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusionaccepted
115. Activation Matters: Test-time Activated Negative Labels for OOD Detection with Vision-Language Modelsaccepted
116. Active Inference for Micro-Gesture Recognition: EFE-Guided Temporal Sampling and Adaptive Learningaccepted
117. Active Intelligence in Video Avatars via Closed-loop World Modelingaccepted
118. Active Perceptual Inference: A Corticothalamic-Inspired Dynamic Nested Recurrent Network for Multimodal Sentiment Analysis with Incomplete Dataaccepted
119. ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Drivingaccepted
120. ActiveGrasp: Information-Guided Active Grasping with Calibrated Energy-based Modelaccepted
121. ActivePolicy: Active Gaussian Reconstruction and Optimization Strategy Based on Global-Local Information Gainaccepted
122. ActiveVLA: Injecting Active Perception into Vision-Language-Action Models for Precise 3D Robotic Manipulationaccepted
123. ActivityForensics: A Comprehensive Benchmark for Localizing Manipulated Activity in Videosaccepted
124. AdaBet: Gradient-free Layer Selection for Efficient Training of Deep Neural Networksaccepted
125. AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generationaccepted
126. AdaDexTrack: Dynamic Modulation for Adaptive and Generalizable Dexterous Manipulation Trackingaccepted
127. AdaIAT: Adaptively Increasing Attention to Generated Text to Alleviate Hallucinations in LVLMaccepted
128. AdaPrior: Bayesian-Inspired Adaptive Prior Correction for Long-Tailed Continual Learningaccepted
129. AdaRadar: Rate Adaptive Spectral Compression for Radar-based Perceptionaccepted
130. AdaSFormer: Adaptive Serialized Transformers for Monocular Semantic Scene Completion from Indoor Environmentsaccepted
131. AdaSVD: Singular Value Decomposition with Adaptive Mechanisms for Large Multimodal Modelsaccepted
132. AdaSpark: Adaptive Sparsity for Efficient Long-Video Understandingaccepted
133. AdaSpot: Spend Resolution Where It Matters for Precise Event Spottingaccepted
134. AdapAction: Adaptive Target Action Backdoor Attack against GUI Agentsaccepted
135. AdapTok: Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Spaceaccepted
136. AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisitionaccepted
137. Adapter Shield: A Unified Framework with Built-in Authentication for Preventing Unauthorized Zero-Shot Image-to-Image Generationaccepted
138. Adapting In-context Generation for Enhanced Composed Image Retrievalaccepted
139. Adapting Lightweight Image-based Counting Models for Video Crowd Countingaccepted
140. Adapting Point Cloud Analysis via Multimodal Bayesian Distribution Learningaccepted
141. Adapting a Pre-trained Single-Cell Foundation Model to Spatial Gene Expression Generation from Histology Imagesaccepted
142. Adaptive 3D Perception for Small Aerial Targets Under Sparse Sampling via Reinforcement Learningaccepted
143. Adaptive Action Chunking at Inference-time for Vision-Language-Action Modelsaccepted
144. Adaptive Anisotropic Gaussian Splatting for Multi-contrast MRI Arbitrary-Scale Super-Resolution with Anatomy Guidanceaccepted
145. Adaptive Auxiliary Prompt Blending for Target-Faithful Diffusion Generationaccepted
146. Adaptive Bayesian Early-Exit Networks for Efficient Non-Transferable Learningaccepted
147. Adaptive Capacity Autoregressive Visual Trackingaccepted
148. Adaptive Confidence Regularization for Multimodal Failure Detectionaccepted
149. Adaptive Data Augmentation with Multi-armed Bandit: Sample-Efficient Embedding Calibration for Implicit Pattern Recognitionaccepted
150. Adaptive Depth Lightweight RGB-T Tracking with Holistic Token Routingaccepted
151. Adaptive Learned Image Compression with Graph Neural Networksaccepted
152. Adaptive Spatial-Temporal Window: Unlocking the Potential of Event Cameras in Heterogeneous Velocity Scenariosaccepted
153. Adaptive Spectral Feature Forecasting for Diffusion Sampling Accelerationaccepted
154. Adaptive Video Distillation: Mitigating Oversaturation and Temporal Collapse in Few-Step Generationaccepted
155. Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learningaccepted
156. AdvFM: Lookahead Flow-Matching Velocity-Field Attacks for Imperceptible and Transferable Adversarial Examplesaccepted
157. Advancing Cancer Prognosis with Hierarchical Fusion of Genomic, Proteomic and Pathology Imaging Data from a Systems Biology Perspectiveaccepted
158. Advancing Image Classification with Discrete Diffusion Classification Modelingaccepted
159. Adversarial Style Optimization: Enhancing VLM Jailbreaks by GRPO-based Stylistic Triggers Optimizationaccepted
160. AeroAgent: A Vision-Physics-Decision Framework for Aerodynamic Vehicle Designaccepted
161. AeroDGS: Physically Consistent Dynamic Gaussian Splatting for Single-Sequence Aerial 4D Reconstructionaccepted
162. AeroGS: Scale-Aware Gaussian Splatting for Pose-Free Dynamic UAV Scene Reconstructionaccepted
163. Aesthetic Camera Viewpoint Suggestion with 3D Aesthetic Fieldaccepted
164. Affine Perspective-Three-Point Problemaccepted
165. AffordGen: Generating Diverse Demonstrations for Generalizable Object Manipulation with Affordance Correspondenceaccepted
166. AffordGrasp: Cross-Modal Diffusion for Affordance-Aware Grasp Synthesisaccepted
167. AffordMatcher: Affordance Learning in 3D Scenes from Visual Signifiersaccepted
168. Affordance Field Intervention: Enabling VLAs to Escape Memory Traps in Robotic Manipulationaccepted
169. Affordance-First Decomposition for Continual Learning in Video-Language Understandingaccepted
170. Affostruction: 3D Affordance Grounding with Generative Reconstructionaccepted
171. Agent4FaceForgery: Multi-Agent LLM Framework for Realistic Face Forgery Detectionaccepted
172. AgentDet: A Shared-Blackboard Multi-Agent Framework for Zero-/Few-Shot Object Detectionaccepted
173. Agentic Retoucher for Text-To-Image Generationaccepted
174. Agentic Video Summarization via Self-Reflecting Multimodal Understandingaccepted
175. Agile Deliberation: Concept Deliberation for Subjective Visual Classificationaccepted
176. Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrievalaccepted
177. AirSim360: A Panoramic Simulation Platform within Drone Viewaccepted
178. AlcheMinT: Fine-grained Temporal Control for Multi-Reference Consistent Video Generationaccepted
179. Alert-CLIP: Abnormality-aware Latent-Enhanced Representation Tuning of CLIP for Video Anomaly Detectionaccepted
180. Align Images Before You Generateaccepted
181. Align Once to Explain: Feature Alignment for Scalable B-cosification of Foundational Vision Transformersaccepted
182. Align While Search: Belief-Guided Exploratory Inference for World-Grounded Embodied Agentsaccepted
183. AlignPose: Generalizable 6D Pose Estimation via Multi-view Feature-metric Alignmentaccepted
184. Aligning Multi-Character Narrative Image Generation with Multi-Aspect Human Preferencesaccepted
185. Aligning Text, Images and 3D Structure Token-by-Tokenaccepted
186. Aligning What Vision-Language Models See and Perceive with Adaptive Information Flowaccepted
187. All Roads Lead to Rome: Incentivizing Divergent Thinking in Vision-Language Modelsaccepted
188. All Vehicles Can Lie: Efficient Adversarial Defense in Fully Untrusted-Vehicle Collaborative Perception via Pseudo-Random Bayesian Inferenceaccepted
189. All in One: Unifying Deepfake Detection, Tampering Localization, and Source Tracing with a Robust Landmark-Identity Watermarkaccepted
190. All-in-One Slider for Attribute Manipulation in Diffusion Modelsaccepted
191. An Efficient Token Compression Framework for Visual Object Trackingaccepted
192. An Empirical Study on How Video-LLMs Answer Video Questionsaccepted
193. An Instance-Centric Panoptic Occupancy Prediction Benchmark for Autonomous Drivingaccepted
194. An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learningaccepted
195. Anatomica: Localized Control over Geometric and Topological Properties for Anatomical Diffusion Modelsaccepted
196. Anatomical Domain Shifts: Test-time Heterogeneous Adaptation for 3D Human Pose Predictionaccepted
197. Anchor-Guided Gradient Alignment for Incomplete Multimodal Learningaccepted
198. AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned Flowsaccepted
199. AnchorSplat: Feed-Forward 3D Gaussian Splatting With 3D Geometric Priorsaccepted
200. Anchoring and Rescaling Attention for Semantically Coherent Inbetweeningaccepted
201. Anchoring the Mind of Multimodal Reasoners: Cognitive Bias as a Vector for Jailbreak Attacksaccepted
202. Ani3DHuman: Photorealistic 3D Human Animation with Self-guided Stochastic Samplingaccepted
203. AniMimic: Imitating 3D Animation from Video Priorsaccepted
204. Animator-Centric Skeleton Generation on Objects with Fine-Grained Detailsaccepted
205. Annotation-Efficient Coreset Selection for Context-dependent Segmentationaccepted
206. Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimizationaccepted
207. Anomaly-Related Residual Fields for Cross-domain Anomaly Detectionaccepted
208. AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectorsaccepted
209. AnthroTAP: Learning Point Tracking with Real-World Motionaccepted
210. Anti-Degradation Lifelong Multi-View Clusteringaccepted
211. Anti-I2V: Safeguarding your Photos from Malicious Image-to-video Generationaccepted
212. AntiStyler: Defending Object Detection Models Against Adversarial Patch Attacks Using Style Removalaccepted
213. Any Resolution Any Geometry: From Multi-View To Multi-Patchaccepted
214. Any2Any 3D Diffusion Models with Knowledge Transfer: A Radiotherapy Planning Studyaccepted
215. Any4D: Unified Feed-Forward Metric 4D Reconstructionaccepted
216. AnyDoc: Enhancing Document Generation via Large-Scale HTML/CSS Data Synthesis and Height-Aware Reinforcement Optimizationaccepted
217. AnyID: Ultra-Fidelity Universal Identity-Preserving Video Generation from Any Visual Referencesaccepted
218. AnyLift: Scaling Motion Reconstruction from Internet Videos via 2D Diffusionaccepted
219. AnyPcc: Compressing Any Point Cloud with a Single Universal Modelaccepted
220. ApET: Approximation-Error Guided Token Compression for Efficient VLMsaccepted
221. Ar2Can: An Architect and an Artist Leveraging a Canvas for Multi-Human Generationaccepted
222. Arcadia: Toward a Full-Lifecycle Framework for Embodied Lifelong Learningaccepted
223. ArchSym: Detecting 3D-Grounded Architectural Symmetries in the Wildaccepted
224. Archon: A Unified Multimodal Model for Holistic Digital Human Generationaccepted
225. Are Image-to-Video Models Good Zero-Shot Image Editors?accepted
226. Are We Ready for RL in Text-to-3D Generation? A Progressive Investigationaccepted
227. ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactionsaccepted
228. ArtLLM: Generating Articulated Assets via 3D LLMaccepted
229. ArtPro: Self-Supervised Articulated Object Reconstruction with Adaptive Integration of Mobility Proposalsaccepted
230. ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understandingaccepted
231. Artiverse: A Diverse and Physically Grounded Dataset for Articulated Objectsaccepted
232. Asking like Socrates: Socrates helps VLMs understand remote sensing imagesaccepted
233. AssemblyBench: Physics-Aware Assembly of Complex Industrial Objectsaccepted
234. Assignment-Driven Hash Learning in a Hyper-Semantic Space for On-the-Fly Category Discoveryaccepted
235. AstraNav-Memory: Contexts Compression for Long Memoryaccepted
236. AsymLoc: Towards Asymmetric Feature Matching for Efficient Visual Localizationaccepted
237. Asynchronous Temporal Modeling with Two-Agent Framework for Streaming Dense Video Captioningaccepted
238. AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robotsaccepted
239. Attack for Defense: Adversarial Agents for Point Prompt Optimization Empowering Segment Anything Modelaccepted
240. Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazingaccepted
241. Attention Surgery: An Efficient Recipe to Linearize Your Video Diffusion Transformeraccepted
242. Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Modelsaccepted
243. Attention-aware Inference Optimizations for Large Vision-Language Models with Memory-efficient Decodingaccepted
244. Attribute-Preserving Pseudo-Labeling for Diffusion-Based Face Swappingaccepted
245. Attribution as Retrieval: Model-Agnostic AI-Generated Image Attributionaccepted
246. Attribution-Guided Model Rectification of Unreliable Neural Network Behaviorsaccepted
247. Audio-sync Video Instance Editing with Granularity-Aware Mask Refineraccepted
248. AudioAvatar: Personalized Audio-driven Whole-body Talking Avatarsaccepted
249. AudioStory: Generating Long-Form Narrative Audio with Large Language Modelsaccepted
250. Authorize-on-Demand: Dynamic Authorization with Legality-Aware Intellectual Property Protection for VLMsaccepted
251. AutoCut: End-to-end advertisement video editing based on multimodal discretization and controllable generationaccepted
252. AutoDebias: An Automated Framework for Detecting and Mitigating Backdoor Biases in Text-to-Image Modelsaccepted
253. AutoRegressive Generation with B-rep Holistic Token Sequence Representationaccepted
254. AutoTraces: Autoregressive Trajectory Forecasting via Multimodal Large Language Modelsaccepted
255. Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversationaccepted
256. AvatarPointillist: AutoRegressive 4D Gaussian Avatarizationaccepted
257. AviaSafe: A Physics-Informed Data-Driven Model for Aviation Safety-Critical Cloud Forecastsaccepted
258. AwareVLN: Reasoning with Self-awareness for Vision-Language Navigationaccepted
259. B$^3$-Seg: Camera-Free, Training-Free 3DGS Segmentation via Analytic EIG and Beta-Bernoulli Bayesian Updatesaccepted
260. BA-GS: Bayesian Adaptive Gaussian Splatting for SFM-Free 3D Reconstructionaccepted
261. BALM: A Model-Agnostic Framework for Balanced Multimodal Learning under Imbalanced Missing Ratesaccepted
262. BAMI: Training-Free Bias Mitigation in GUI Groundingaccepted
263. BAgger: Backwards Aggregation for Mitigating Drift in Autoregressive Video Diffusion Modelsaccepted
264. BD-Merging: Bias-Aware Dynamic Model Merging with Evidence-Guided Contrastive Learningaccepted
265. BDNet:Bio-Inspired Dual-Backbone Small Object Detection Networkaccepted
266. BEA-GS: BEyond RAdiance Supervision in 3DGS for Precise Object Extractionaccepted
267. BEV-CAR: Enhancing Monocular Bird's Eye View Segmentation with Context-Aware Rasterizationaccepted
268. BEV-SLD: Self-Supervised Scene Landmark Detection for Global Localization with LiDAR Bird's-Eye View Imagesaccepted
269. BHCast: Unlocking Black Hole Plasma Dynamics from a Single Blurry Image with Long-Term Forecastingaccepted
270. BIT: Matching-based Bi-directional Interaction Transformation Network for Visible-Infrared Person Re-Identificationaccepted
271. BOP-ASK: Object-Interaction Reasoning for Vision-Language Modelsaccepted
272. BUSSARD: Normalizing Flows for Bijective Universal Scene-Specific Anomalous Relationship Detectionaccepted
273. BabyVLM-V2: Toward Developmentally Grounded Pretraining and Benchmarking of Vision Foundation Modelsaccepted
274. Back to Basics: Let Denoising Generative Models Denoiseaccepted
275. Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detectionaccepted
276. Back to Source: Open-Set Continual Test-Time Adaptation via Domain Compensationaccepted
277. Back to the Feature: Explaining Video Classifiers with Video Counterfactual Explanationsaccepted
278. BackSplit: The Importance of Sub-dividing the Background in Biomedical Lesion Segmentationaccepted
279. Balanced Dataset Distillation via Modeling Multiple Visual Pattern Distributionaccepted
280. Balanced Hierarchical Contrastive Learning with Decoupled Queries for Fine-grained Object Detection in Remote Sensing Imagesaccepted
281. BarbieGait: An Identity-Consistent Synthetic Human Dataset with Versatile Cloth-Changing for Gait Recognitionaccepted
282. Basis-Oriented Low-rank Transfer for Few-Shot and Test-Time Adaptationaccepted
283. Batch Loss Score for Dynamic Data Pruningaccepted
284. Batman: Benign Knowledge Alignment Through Malicious Null Space in Federated Backdoor Attackaccepted
285. Bayesian Decomposition and Semantic Completion for Few-shot Semantic Segmentationaccepted
286. BeautyGRPO: Aesthetic Alignment for Face Retouching via Dynamic Path Guidance and Fine-Grained Preference Modelingaccepted
287. Benchmarking Endoscopic Surgical Image Restoration and Beyondaccepted
288. Benchmarking PhD-Level Coding in 3D Geometric Computer Visionaccepted
289. Benchmarking Single-Factor Physical Video-to-Audio Generationaccepted
290. Best Segmentation Buddies for Image-Shape Correspondenceaccepted
291. Better than Average: Spatially-Aware Aggregation of Segmentation Uncertainty Improves Downstream Performanceaccepted
292. Better, Stronger, Faster: Tackling the Trilemma in MLLM-based Segmentation with Simultaneous Textual Mask Predictionaccepted
293. Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoningaccepted
294. Beyond Appearance: Camouflaged Object Detection via Geometric Structureaccepted
295. Beyond Binary Contrast: Modeling Continuous Skeleton Action Spaces with Transitional Anchorsaccepted
296. Beyond Caption-Based Queries in Video Moment Retrievalaccepted
297. Beyond Duality: A Hybrid Framework of Leveraging Shared and Private Features for RGB-Event Object Detectionaccepted
298. Beyond Endpoints: Path-Centric Reasoning for Vectorized Off-Road Network Extractionaccepted
299. Beyond Euclidean Gossip: KL-Barycentric Consensus on Heterogeneous and Imbalanced Imagesaccepted
300. Beyond Explicit Language: Plug-and-Play Visual-to-Linguistic Modeling Toward General Object Trackingaccepted
301. Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Modelsaccepted
302. Beyond Geometry: Artistic Disparity Synthesis for Immersive 2D-to-3Daccepted
303. Beyond Global Similarity: Multi-Conditional Retrieval for Fine-Grained Cross-Modal Understandingaccepted
304. Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapteraccepted
305. Beyond Ground-Truth: Leveraging Image Quality Priors for Real-World Image Restorationaccepted
306. Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognitionaccepted
307. Beyond Layer-Wise Merging: Chain-of-Merging for Vision-Language Modelsaccepted
308. Beyond Matching to Tiles: Bridging Unaligned Aerial and Satellite Views for Vision-Only UAV Navigationaccepted
309. Beyond Mimicry: Learning Whole-Body Human-Humanoid Interaction from Human-Human Demonstrationsaccepted
310. Beyond Missing Modalities: Hypergraph Conditioned Diffusion for Uncertainty-Aware Multimodal Emotion Recognitionaccepted
311. Beyond Multiple Choice: Verifiable OpenQA for Robust Vision-Language RFTaccepted
312. Beyond Myopic Alignment: Lookahead Optimization for Online Class-Incremental Learningaccepted
313. Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classificationaccepted
314. Beyond Patches: Global-aware Autoregressive Model for Multimodal Few-Shot Font Generationaccepted
315. Beyond Perceptual Shortcuts: Causal-Inspired Debiasing Optimization for Generalizable Video Reasoning in Lightweight MLLMsaccepted
316. Beyond Pixel Simulation: Pathology Image Generation via Diagnostic Semantic Tokens and Prototype Controlaccepted
317. Beyond Prompt Degradation: Prototype-guided Dual-pool Prompting for Incremental Object Detectionaccepted
318. Beyond Reassembly: Fractured Object Recovery with Missing Partsaccepted
319. Beyond Rule-Based Agents: Active Markov Games for Realistic Multi-Agent Interaction in Autonomous Drivingaccepted
320. Beyond Scanpaths: Graph-Based Gaze Simulation in Dynamic Scenesaccepted
321. Beyond Semantic Search: Towards Referential Anchoring in Composed Image Retrievalaccepted
322. Beyond Sequential Tools: A Unified VLM Agent System for Photographic Post-Processing via Dynamic Multi-Expert Fusionaccepted
323. Beyond Single Images: A Comprehensive Benchmark for Album-Level Vision-Language Understandingaccepted
324. Beyond Single Solution: Multi-Hypothesis Deep Unfolding Network for Image Compressive Sensingaccepted
325. Beyond Single-View Sufficiency: CVBench for Cross-View Human Understandingaccepted
326. Beyond Soft Label: Dataset Distillation via Orthogonal Gradient Matchingaccepted
327. Beyond Static Frames: Temporal Aggregate-and-Restore Vision Transformer for Human Pose Estimationaccepted
328. Beyond Strict Pairing: Arbitrarily Paired Training for High-Performance Infrared and Visible Image Fusionaccepted
329. Beyond Success: Refining Elegant Robot Manipulation from Mixed-Quality Data via Just-in-Time Interventionaccepted
330. Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaborationaccepted
331. Beyond Text: Visual Description Assembly by Probabilistic Model for CLIP-based Weakly Supervised Semantic Segmentationaccepted
332. Beyond Tie Points: Satellite Image Block Adjustment based on Dense Feature Consistencyaccepted
333. Beyond Top Activations: Efficient and Reliable Crowdsourced Evaluation of Automated Interpretabilityaccepted
334. Beyond Weak Supervision: MLLMs-Guided Graded Knowledge Distillation for Unsupervised Camouflaged Object Detectionaccepted
335. Beyond What's Shared: Recovering Lost Unique Information from Intermediate Layers to Boost Multimodal Geo-Foundation Modelsaccepted
336. Beyond [CLS] Token: Query-Driven Token-Level Forgery Purification for Generalizable Deepfake Detectionaccepted
337. Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinationsaccepted
338. Beyond the Golden Data: Resolving the Motion-Vision Quality Dilemma via Timestep Selective Trainingaccepted
339. Beyond the Ground Truth: Enhanced Supervision for Image Restorationaccepted
340. Beyond the Static World: Continual Category Discovery under Visual Driftaccepted
341. Beyond the Static-World: Lifelong Learning for All-in-One Medical Image Restorationaccepted
342. Bezier Degradation Modeling for LiDAR-based Human Motion Captureaccepted
343. Bi-Bridge: Bidirectional Diffusion Bridges for Low-Light Image Enhancementaccepted
344. Bi-directional Autoregressive Diffusion for Large Complex Motion Interpolationaccepted
345. BiEvLight: Bi-level Learning of Task-Aware Event Refinement for Low-Light Image Enhancementaccepted
346. BiFM: Bidirectional Flow Matching for Few-Step Image Editing and Generationaccepted
347. BiGMINT: Biologically-guided Hierarchical Multimodal Integration for Modeling Multiple Compound Activities in Drug Discoveryaccepted
348. BiGain: Unified Token Compression for Joint Generation and Classificationaccepted
349. BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generationaccepted
350. BiOTPrompt: Bidirectional Optimal Transport Guided Prompting for Disease Evolution-aware Radiology Report Generationaccepted
351. BiPA: Bilevel Prompt Adaptation for Underwater Instance Segmentationaccepted
352. BiPreManip: Learning Affordance-Based Bimanual Preparatory Manipulation through Anticipatory Collaborationaccepted
353. BiProLoRA: Bilevel Prompt LoRA for Real Scene Recoveryaccepted
354. Bias In, Bias Out? Finding Unbiased Subnetworks in Vanilla Modelsaccepted
355. Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Modelsaccepted
356. Bias at the End of the Scoreaccepted
357. Bidirectional Cross-Modal Prompting for Event-Frame Asymmetric Stereoaccepted
358. Bidirectional Multimodal Prompt Learning with Scale-Aware Training for Few-Shot Multi-Class Anomaly Detectionaccepted
359. Bidirectional Normalizing Flow: From Data to Noise and Backaccepted
360. Bidirectional Query-Driven Generation of Parametric CAD Sketchaccepted
361. Bilevel Layer-Positioning LoRA for Real Image Dehazingaccepted
362. BinaryAttention: One-Bit QK-Attention for Vision and Diffusion Transformersaccepted
363. BioVITA: Biological Dataset, Model, and Benchmark for Visual-Textual-Acoustic Alignmentaccepted
364. BiomedCCPL: Causal Conditional Prompt Learning for Biomedical Vision-Language Modelsaccepted
365. Black-Box Domain Adaptation for Object Detection with Retention-Driven Knowledge Compressionaccepted
366. Black-box Membership Inference Attacks on the Pre-training Data of Image-generation Modelsaccepted
367. BlackMirror: Black-Box Backdoor Detection for Text-to-Image Models via Instruction-Response Deviationaccepted
368. Blink: Dynamic Visual Token Resolution for Enhanced Multimodal Understandingaccepted
369. Block-Sparse Global Attention for Efficient Multi-View Geometry Transformersaccepted
370. Block-based Learned Image Compression without Blocking Artifactsaccepted
371. BluRef: Unsupervised Image Deblurring with Dense-Matching Referencesaccepted
372. BoostSLT: Boosting Sign Language Translation via a Plug-and-Play Diffusion-Based Semantic Enhanceraccepted
373. Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processingaccepted
374. Boosting Quantitive and Spatial Awareness for Zero-Shot Object Countingaccepted
375. Boosting Reasoning in Large Multimodal Models via Activation Replayaccepted
376. Boosting Self-Supervised Tracking with Contextual Prompts and Noise Learningaccepted
377. Boosting Vision-Language Models Towards Cross-Domain Incremental Object Detectionaccepted
378. Boosting Vision-Language-Action Finetuning with Feasible Action Neighborhood Prioraccepted
379. Boosting Visual Reprogramming for CLIP with Dual Granularity Alignmentaccepted
380. Bootstrap Dynamic-Aware 3D Visual Representation for Scalable Robot Learningaccepted
381. Bootstrap Your Own AV-Proxies: Adaptive Contrastive and Prototype Learning for Audio-Visual Segmentationaccepted
382. Bootstrapping Multi-view Learning for Test-time Noisy Correspondenceaccepted
383. Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptationaccepted
384. Boundary-Responsive Differentiable Gating for Superpixel-Based Segmentationaccepted
385. Breaking Multimodal LLM Safety via Video-Driven Promptingaccepted
386. Breaking Semantic Boundaries: Distribution-Guided Semantic Exploration for Creative Generationaccepted
387. Breaking Smooth-Motion Assumptions: A UAV Benchmark for Multi-Object Tracking in Complex and Adverse Conditionsaccepted
388. Breaking Spurious Correlations: Uncertainty-Driven Causal Transformers for AU Detectionaccepted
389. Breaking the 3D Dataset Bottleneck: Fast Scalable Generation of Aligned 3D Assets from Scratch for Category 6D Pose Estimation and Robotic Graspingaccepted
390. Breaking the Continuum: Discrete Distribution Learning for Structural MRI Reconstructionaccepted
391. Breaking the Illusion: When Positive Meets Negative in Multimodal Decodingaccepted
392. Breaking the Regional Perception Bottleneck of Multimodal Large Language Models via External Reasoning Frameworkaccepted
393. Breaking the Scalability Limit of Multi-Projector Calibration with Embedded Camerasaccepted
394. BrepGaussian: CAD reconstruction from Multi-View Images with Gaussian Splattingaccepted
395. BrepVGAE: Variational Graph Autoencoder with Unified Latent Representation for B-repaccepted
396. Brewing Stronger Features: Dual-Teacher Distillation for Multispectral Earth Observationaccepted
397. BriMA: Bridged Modality Adaptation for Multi-Modal Continual Action Quality Assessmentaccepted
398. BrickNet: Graph-Backed Generative Brick Assemblyaccepted
399. Bridge: Basis-Driven Causal Inference Marries VFMs for Domain Generalizationaccepted
400. BridgeEQA: Virtual Embodied Agents for Real Bridge Inspectionsaccepted
401. Bridging Brain and Semantics: A Hierarchical Framework for Semantically Enhanced fMRI-to-Video Reconstructionaccepted
402. Bridging Domain Expertise and Generalization for Performance Estimationaccepted
403. Bridging Domains through Subspace-Aware Model Mergingaccepted
404. Bridging Facial Understanding and Animation via Language Modelsaccepted
405. Bridging Fidelity-Reality with Controllable One-Step Diffusion for Image Super-Resolutionaccepted
406. Bridging Human Evaluation to Infrared and Visible Image Fusionaccepted
407. Bridging Pixels and Words: Mask-Aware Local Semantic Fusion for Multimodal Media Verificationaccepted
408. Bridging Privacy and Provenance: Traceable Virtual Identity Generationaccepted
409. Bridging RGB and Hematoxylin Components: An Interleaved Guidance and Fusion Framework for Point Supervised Nuclei Segmentationaccepted
410. Bridging the 2D-3D Gap: A Hierarchical Semantic-Geometric Map for Vision Language Navigationaccepted
411. Bridging the Modality Gap in Compositional Zero-Shot Learning via Sparse Alignment and Unimodal Memory Bankaccepted
412. Bridging the Perception Gap in Image Super-Resolution Evaluationaccepted
413. Bringing Your Portrait to 3D Presenceaccepted
414. BuildAnyPoint: 3D Building Structured Abstraction from Diverse Point Cloudsaccepted
415. Building Robust Vision Encoders for Cross-Dataset Evaluation in Immunofluorescent Microscopyaccepted
416. Building a Precise Video Language with Human-AI Oversightaccepted
417. BuildingGPT: Auto-Regressive Building Wireframe Reconstruction Model with Reinforcement Learningaccepted
418. Bulk RNA-seq Guided Multi-modal Detection of Anomalous Regions in Human Cancer via Spatial Transcriptomicsaccepted
419. BulletTime: Decoupled Control of Time and Camera Pose for Video Generationaccepted
420. Bypassing the Transport Plan: Dynamic Reweighting for Out-of-Distribution Detection with Optimal Transportaccepted
421. C-GenReg: Training-Free 3D Point Cloud Registration by Multi-View-Consistent Geometry-to-Image Generation with Probabilistic Modalities Fusionaccepted
422. C-LaV: Conditional Latent Velocity Field Denoising for Weather-Robust LiDAR Place Recognitionaccepted
423. CAD-Refiner: A Unified Framework for CAD Generation and Iterative Editingaccepted
424. CADC: Content Adaptive Diffusion-Based Generative Image Compressionaccepted
425. CADFS: A Big CAD Program Dataset and Framework for Computer-Aided Design with Large Language Modelsaccepted
426. CAPT: Confusion-Aware Prompt Tuning for Reducing Vision-Language Misalignmentaccepted
427. CAR-SAM: Cross-Attention Reconstruction for Post-Training Quantization of the Segment Anything Modelaccepted
428. CARD: A Multi-Modal Automotive Dataset for Dense 3D Reconstruction in Challenging Road Topographyaccepted
429. CARD: Correlation Aware Restoration with Diffusionaccepted
430. CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoningaccepted
431. CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editingaccepted
432. CARE: A Molecular-Guided Foundation Model with Adaptive Region Modeling for Whole Slide Image Analysisaccepted
433. CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interactionaccepted
434. CARLoS: Retrieval via Concise Assessment Representation of LoRAs at Scaleaccepted
435. CASPA: Graph-Structured Concept Anchors for Modality-Agnostic Adaptation in Vision-Language Modelsaccepted
436. CASR: A Robust Cyclic Framework for Arbitrary Large-Scale Super-Resolution with Distribution Alignment and Self-Similarity Awarenessaccepted
437. CAST: Context-Aware Dynamic Latent Space Transformation for Interactive Text-to-Image Retrievalaccepted
438. CATNet: Collaborative Alignment and Transformation Network for Cooperative Perceptionaccepted
439. CC-VQA: Conflict- and Correlation-Aware Method for Mitigating Knowledge Conflict in Knowledge-Based Visual Question Answeringaccepted
440. CCCaption: Dual-Reward Reinforcement Learning for Complete and Correct Image Captioningaccepted
441. CCF: Complementary Collaborative Fusion for Domain Generalized Multi-Modal 3D Object Detectionaccepted
442. CD-Buffer: Complementary Dual-Buffer Framework for Test-Time Adaptation in Adverse Weather Object Detectionaccepted
443. CDICS: Delving Into Fine-Grained Attribute for In-Context Segmentation via Compositional Prompts and Phased Decouplingaccepted
444. CF-IPT: Cross-Modal Fusion Interactive Prompt Tuning of Vision-Language Pre-Trained Model for Multisource Remote Sensing Data Classificationaccepted
445. CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidanceaccepted
446. CG-Floor: Centroid-Guided Diffusion for Large-Scale Floorplan Generationaccepted
447. CG-Reasoner: Centroid-Guided Positional Reasoning Segmentation for Medical Imaging with a Robust Visual-Text Consistency Metricaccepted
448. CGHair: Compact Gaussian Hair Reconstruction with Card Clusteringaccepted
449. CGL: Advancing Continual GUI Learning via Reinforcement Fine-Tuningaccepted
450. CGU-Bayes: Causal Graph Uncertainty-Guided Bayesian Inference for Domain Generalizationaccepted
451. CHAL: Causal-guided Hierarchical Anomaly-aware Learning for Moving Infrared Small Target Detectionaccepted
452. CHEEM: Continual Learning by Reuse, New, Adapt and Skip - A Hierarchical Exploration-Exploitation Approachaccepted
453. CHIPS: Efficient CLIP Adaptation via Curvature-aware Hybrid Influence-based Data Selectionaccepted
454. CHIRP dataset: towards long-term, individual-level, behavioral monitoring of bird populations in the wildaccepted
455. CI-VID: A Coherent Interleaved Text-Video Datasetaccepted
456. CICA: Coupling Confidence-Aware Pretraining with Confidence-Informed Attention for Robust Multimodal Sentiment Analysisaccepted
457. CIGMA: Causal Information-Gain Mechanistic Attribution of Attention Heads in Vision Transformersaccepted
458. CIGPose: Causal Intervention Graph Neural Network for Whole-Body Pose Estimationaccepted
459. CLAY: Conditional Visual Similarity Modulation in Vision-Language Embedding Spaceaccepted
460. CLCR: Cross-Level Semantic Collaborative Representation for Multimodal Learningaccepted
461. CLEP: Contrastive Language-Pose Pretrainingaccepted
462. CLEX: Complementary Label Exchange Learning for Noisy Facial Expression Recognitionaccepted
463. CLIP Is Shortsighted: Paying Attention Beyond the First Sentenceaccepted
464. CLIP-like Model as a Foundational Density Ratio Estimatoraccepted
465. CLIPoint3D: Language-Grounded Few-Shot Unsupervised 3D Point Cloud Domain Adaptationaccepted
466. CLP: A Real-World Dataset of Contaminated Lens Protectors for Robust Semantic Segmentationaccepted
467. CLaD: Planning with Grounded Foresight via Cross-Modal Latent Dynamicsaccepted
468. CLiViS: Unleashing Cognitive Map through Linguistic-Visual Synergy for Embodied Visual Reasoningaccepted
469. CME-CAD: Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generationaccepted
470. CMR-RD: Long-Tailed Adaptive VLM for Explainable CMR Diagnosisaccepted
471. COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimationaccepted
472. COPE: Consistent Occlusion and Prompt Enhancement Network for Occluded Person Re-identificationaccepted
473. COPO: Causal-Oriented Policy Optimization for Hallucinations of MLLMsaccepted
474. COPYLENS: Towards Copyrighted Characters Infringement Detection via Copyright-Aware Prompt Learningaccepted
475. CORE: Compact Object-centric REpresentations as a New Paradigm for Token Merging in LVLMsaccepted
476. COT-FM: Cluster-wise Optimal Transport Flow Matchingaccepted
477. CRAFT-LoRA: Content-Style Personalization via Rank-Constrained Adaptation and Training-Free Fusionaccepted
478. CRAFT: Aligning Diffusion Models with Fine-Tuning Is Easier Than You Thinkaccepted
479. CREval: An Automated Interpretable Evaluation for Creative Image Manipulation under Complex Instructionsaccepted
480. CREward: A Type-Specific Creativity Reward Modelaccepted
481. CRFT: Consistent-Recurrent Feature Flow Transformer for Cross-Modal Image Registrationaccepted
482. CRIT: Graph-Based Automatic Data Synthesis to Enhance Cross-Modal Multi-Hop Reasoningaccepted
483. CROWn: A Unified Framework for Anti-Aliased Downsampling and Phase-Calibrated Fusion in 3D Medical Segmentationaccepted
484. CSF: Black-box Fingerprinting via Compositional Semantics for Text-to-Image Modelsaccepted
485. CTCal: Rethinking Text-to-Image Diffusion Models via Cross-Timestep Self-Calibrationaccepted
486. CUBic: Coordinated Unified Bimanual Perception and Control Frameworkaccepted
487. CUE: Concept-Aware Multi-Label Expansion to Mitigate Concept Confusion in Long-Tailed Learningaccepted
488. CUPID: Generative 3D Reconstruction via Joint Object and Pose Modelingaccepted
489. CURE: Curriculum-guided Multi-task Training for Reliable Anatomy Grounded Report Generationaccepted
490. CURVE: A Benchmark for Cultural and Multilingual Long Video Reasoningaccepted
491. CVA: Context-aware Video-text Alignment for Video Temporal Groundingaccepted
492. C^2FG: Control Classifier-Free Guidance via Score Discrepancy Analysisaccepted
493. CaReFlow: Cyclic Adaptive Rectified Flow for Multimodal Fusionaccepted
494. CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answeringaccepted
495. CaT-GS: Efficient 3DGS Rendering for Large-Scale Scenes with Inter-frame Caching and Tile Schedulingaccepted
496. CaTok: Taming Mean Flows for One-Dimensional Causal Image Tokenizationaccepted
497. CaliTex: Geometry-Calibrated Attention for View-Coherent 3D Texture Generationaccepted
498. CamDirector: Towards Long-Term Coherent Video Trajectory Editingaccepted
499. CamPI: Physical Adversarial Examples through Camera Power Signal Injectionaccepted
500. Camera Control for Text-to-Image Generation via Learning Viewpoint Tokensaccepted
501. Camouflage-aware Image-Text Retrieval via Expert Collaborationaccepted
502. Can Natural Image Autoencoders Compactly Tokenize fMRI Volumes for Long-Range Dynamics Modeling?accepted
503. Can We Build Scene Graphs, Not Classify Them? FlowSG: Progressive Image-Conditioned Scene Graph Generation with Flow Matchingaccepted
504. Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformersaccepted
505. Can a Second-View Image Be a Language? Geometric and Semantic Cross-Modal Reasoning for X-ray Prohibited Item Detectionaccepted
506. CanonCGT: Reference-Based Color Grading via Canonical Pivot Representationaccepted
507. CapNav: Benchmarking Vision Language Models on Capability-conditioned Indoor Navigationaccepted
508. Captain Safari: A World Engine with Pose-Aligned 3D Memoryaccepted
509. CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objectsaccepted
510. CaptionQA: Is Your Caption as Useful as the Image Itself?accepted
511. CaricHarmony: Contrastive Diffusion Paths for Identity-Preserving Caricature Synthesisaccepted
512. Catalyst4D: High-Fidelity 3D-to-4D Scene Editing via Dynamic Propagationaccepted
513. Causal Motion Diffusion Models for Autoregressive Motion Generationaccepted
514. CausalLens: Sensitivity-Guided Multi-Head Causal Intervention for Hallucination Mitigation in Large Vision-Language Modelsaccepted
515. CausalVAD: De-confounding End-to-End Autonomous Driving via Causal Interventionaccepted
516. Causality in Video Diffusers is Separable from Denoisingaccepted
517. Cell-Type Prototype-Informed Neural Network for Gene Expression Estimation from Pathology Imagesaccepted
518. ChArtist: Generating Pictorial Charts with Unified Spatial and Subject Controlaccepted
519. Chain of Event-Centric Causal Thought for Physically Plausible Video Generationaccepted
520. Chain of World: World Model Thinking in Latent Motionaccepted
521. Chain-of-Frames: Advancing Video Understanding in Multimodal LLMs via Frame-Aware Reasoningaccepted
522. Chain-of-Models Pre-Training: Rethinking Training Acceleration of Vision Foundation Modelsaccepted
523. Chain-of-Thought Guided Multi-Modal Object Re-Identificationaccepted
524. ChangeBridge: Spatiotemporal Image Generation with Multimodal Controls for Remote Senisngaccepted
525. Changes in Real Time: Online Scene Change Detection with Multi-View Fusionaccepted
526. Charge: A Comprehensive Novel View Synthesis Benchmark and Dataset to Bind Them Allaccepted
527. Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Chartsaccepted
528. ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understandingaccepted
529. ChartR: Evaluating Reasoning Accuracy and Robustness in Chart Question Answeringaccepted
530. ChimeraLoRA: Multi-Head LoRA-Guided Synthetic Datasetsaccepted
531. ChordEdit: One-Step Low-Energy Transport for Image Editingaccepted
532. Choreographing a World of Dynamic Objectsaccepted
533. Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encodingaccepted
534. ChronoGS: Disentangling Invariants and Changes in Multi-Period Scenesaccepted
535. CineBrain: A Large-Scale Multi-Modal Audiovisual Brain Dataset for Brain-Conditioned Video Generationaccepted
536. CineSRD: Leveraging Visual, Acoustic, and Linguistic Cues for Open-World Visual Media Speaker Diarizationaccepted
537. CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generationaccepted
538. Cinematic Audio Source Separation Using Visual Cuesaccepted
539. Circuit Mechanisms for Spatial Relation Generation in Diffusion Transformersaccepted
540. Circular-DPO: Aligning Multi-Stage 3D Generative Models via Preference Feedback Loopaccepted
541. Clair Obscur: an Illumination-Aware Method for Real-World Image Vectorizationaccepted
542. Clay-to-Stone: Phase-wise 3D Gaussian Splatting for Monocular Articulated Hand-Object Manipulation Modelingaccepted
543. Cleaning the Pool: Progressive Filtering of Unlabeled Pools in Deep Active Learningaccepted
544. ClimaOoD: Improving Anomaly Segmentation via Physically Realistic Synthetic Dataaccepted
545. Clinically-Grounded Counterfactual Reasoning for Medical Video Diagnosisaccepted
546. ClipGStream: Clip-Stream Gaussian Splatting for Any Length and Any Motion Multi-View Dynamic Scene Reconstructionaccepted
547. Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Modelsaccepted
548. Closed-Form Concept Erasure via Double Projectionsaccepted
549. Clothe and Poseaccepted
550. Cluster-Aware Neural Collapse Prompt Tuning for Long-Tailed Generalization of Vision-Language Modelsaccepted
551. Cluster-Wise Spatio-Temporal Masking for Efficient Video-Language Pretrainingaccepted
552. Cluster-aware Anchor Learning for Multi-View Clusteringaccepted
553. ClusterMark: Towards Robust Watermarking for Autoregressive Image Generators with Visual Token Clusteringaccepted
554. Co-Me: Confidence Guided Token Merging for Visual Geometric Transformersaccepted
555. CoCoVideo: The High-Quality Commercial-Model-Based Contrastive Benchmark for AI-Generated Video Detectionaccepted
556. CoD: A Diffusion Foundation Model for Image Compressionaccepted
557. CoFiDA-M: Concept-Aware Feature Modulation for Cross-Domain Adaptation with Image-Only Inferenceaccepted
558. CoIn3D: Revisiting Configuration-Invariant Multi-Camera 3D Object Detectionaccepted
559. CoIn: Coverage and Informativeness-Guided Token Reduction for Efficient Large Multimodal Modelsaccepted
560. CoLC: Communication-Efficient Collaborative Perception with LiDAR Completionaccepted
561. CoLoGen: Progressive Learning of Concept-Localization Duality for Unified Image Generationaccepted
562. CoLoR: The Devil is in Scene Coordinate Regression for Large-Scale Visual Localizationaccepted
563. CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learningaccepted
564. CoRiM: Conflict-driven Risk Minimization for Dynamic Multimodal Fusionaccepted
565. CoRoGS: Contextual Gaussian Splatting for Robust Large-Deviation View Synthesisaccepted
566. CoSMo3D: Open-World Promptable 3D Semantic Segmentation through LLM-Guided Canonical Spatial Modelingaccepted
567. CoT-Edit: Let CoT Guide Instruction Video Editingaccepted
568. CoV-Align: Efficient Fine-grained Cross-Modal Alignment with Cohesive Visual Semantics Priorityaccepted
569. CoVFT: Context-aware Visual Fine-tuning for Multimodal Large Language Modelsaccepted
570. CoWTracker: Tracking by Warping instead of Correlationaccepted
571. CodeDance: A Dynamic Tool-integrated MLLM for Executable Visual Reasoningaccepted
572. CodeMMR: Bridging Natural Language, Code, and Image for Unified Retrievalaccepted
573. CodePercept: Code-Grounded Visual STEM Perception for MLLMsaccepted
574. CodeV: Code with Images for Faithful Visual Reasoning via Tool-Aware Policy Optimizationaccepted
575. Coded-E2LF: Coded Aperture Light Field Imaging from Eventsaccepted
576. CogDriver: Integrating Cognitive Inertia for Temporally Coherent Planning in Autonomous Drivingaccepted
577. CogniEdit: Dense Gradient Flow Optimization for Fine-Grained Image Editingaccepted
578. CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric Reasoningaccepted
579. ColaVLA: Leveraging Cognitive Latent Reasoning for Hierarchical Parallel Trajectory Planning in Autonomous Drivingaccepted
580. Collaborative Multi-Mode Pruning for Vision-Language Modelsaccepted
581. Color When It Counts: Grayscale-Guided Online Triggering for Always-On Streaming Video Sensingaccepted
582. Color-Encoded Illumination for High-Speed Volumetric Scene Reconstructionaccepted
583. ColorFLUX: A Structure-Color Decoupling Framework for Old Photo Colorizationaccepted
584. ComPose: A Unified Completion-Pose Framework for Robust Category-Level Object Pose Estimationaccepted
585. Common Inpainted Objects In-N-Out of Contextaccepted
586. CompBench: Benchmarking Complex Instruction-guided Image Editingaccepted
587. CompetitorFormer: Mitigating Query Conflicts for 3D Instance Segmentation via Competitive Strategyaccepted
588. Complementary Prototype Mapping for Efficient Multimodal Anomaly Detectionaccepted
589. Complet4R: Geometric Complete 4D Reconstructionaccepted
590. Composing Concepts from Images and Videos via Concept-prompt Bindingaccepted
591. Composite-Attribute Person Re-Identification via Pose-Guided Disentanglementaccepted
592. Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimizationaccepted
593. Compositional Transformation Reasoning for Composed Video Retrievalaccepted
594. Compressed-Domain-Aware Online Video Super-Resolutionaccepted
595. Computation and Communication Efficient Federated Unlearning via On-server Gradient Conflict Mitigation and Expressionaccepted
596. Computational Speckle Pattern Interferometryaccepted
597. Computer Vision with a Superpixelation Cameraaccepted
598. Conan: Progressive Learning to Reason Like a Detective over Multi-Scale Visual Evidenceaccepted
599. Concept Regions Matter: Benchmarking CLIP with a New Cluster-Importance Approachaccepted
600. Concept-Aware Batch Sampling Improves Language-Image Pretrainingaccepted
601. Concept-Aware LoRA for Domain-Aligned Segmentation Dataset Generationaccepted
602. Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustnessaccepted
603. ConceptPose: Training-Free Zero-Shot Object Pose Estimation using Concept Vectorsaccepted
604. ConceptPrism: Concept Disentanglement in Personalized Diffusion Models via Residual Token Optimizationaccepted
605. Condensed Test-Time Adaptation of VLMs for Action Recognitionaccepted
606. Conditional Factuality Controlled LLMs with Generalization Certificates via Conformal Samplingaccepted
607. ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrievalaccepted
608. Confidence-Guided Multi-Scale Aggregation for Sparse-View High-Resolution 3D Gaussian Splattingaccepted
609. Conflict-Aware Adaptive Cross-Reconstruction for Multimodal Sentiment Analysisaccepted
610. Confusion-Aware Spectral Regularizer for Long-Tailed Recognitionaccepted
611. ConsID-Gen: View-Consistent and Identity-Preserving Image-to-Video Generationaccepted
612. Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCRaccepted
613. Consensus vs. Controversy: Mapping the Decision Space Where Architectures Divergeaccepted
614. ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulationaccepted
615. ConsistCompose: Unified Multimodal Layout Control for Image Compositionaccepted
616. Consistency Beyond Contrast: Enhancing Open-Vocabulary Object Detection Robustness via Contextual Consistency Learningaccepted
617. Consistent Instance Field for Dynamic Scene Understandingaccepted
618. Contact-Aware Neural Dynamicsaccepted
619. Content-Adaptive Hierarchical Hyperprior for Neural Video Codingaccepted
620. Content-Aware Dynamic Patchification for Efficient Video Diffusionaccepted
621. Content-Aware Frequency Encoding for Implicit Neural Representations with Fourier-Chebyshev Featuresaccepted
622. Context-Nav: Context-Driven Exploration and Viewpoint-Aware 3D Spatial Reasoning for Instance Navigationaccepted
623. Continual Distillation of Teachers from Different Domainsaccepted
624. Continual Learning for fMRI-Based Brain Disorder Diagnosis via Functional Connectivity Matrices Generative Replayaccepted
625. Continuous Exposure-Time Modeling for Realistic Atmospheric Turbulence Synthesisaccepted
626. Contrastive Cross-Bag Augmentation for Multiple Instance Learning-based Whole Slide Image Classificationaccepted
627. Controllable Federated Prompt Learning at Test Timeaccepted
628. Conversational Image Segmentation: Grounding Abstract Concepts with Scalable Supervisionaccepted
629. Convexity-Aware Noise Calibration: A Self-Supervised Framework for Noise-Level-Unknown Image Denoisingaccepted
630. Convolutional Neural Networks Driven by Content Similarityaccepted
631. CoopDiff: A Diffusion-Guided Approach for Cooperation under Corruptionsaccepted
632. CoordSpeaker: Exploiting Gesture Captioning for Coordinated Caption-Empowered Co-Speech Gesture Generationaccepted
633. Coordinate Denoising for Non-Equilibrium Molecular Representation Learningaccepted
634. Copy-Transform-Paste: Zero-Shot Object-Object Alignment Guided by Vision-Language and Geometric Constraintsaccepted
635. Correspondence-Attention Alignment for Multi-View Diffusion Modelsaccepted
636. CountGD++: Generalized Prompting for Open-World Countingaccepted
637. Counterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoningaccepted
638. Coupled Diffusion Sampling for Training-Free Multi-View Image Editingaccepted
639. Coupling Liquid Time-Constant Encoders with Modern Hopfield Memoryaccepted
640. Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimationaccepted
641. Coverage Optimization for Camera View Selectionaccepted
642. CrackSSM: Reviving SSMs for Crack Segmentation via Dynamic Scanningaccepted
643. CraftMesh: High-Fidelity Generative Mesh Manipulation via Poisson Seamless Fusionaccepted
644. Critical Patch-Aware Sparse Prompting with Decoupled Training for Continual Learning on the Edgeaccepted
645. Cross from Left to Right Brain: Adaptive Text Dreamer for Vision-and-Language Navigationaccepted
646. Cross-Architecture Adaptation: Cloud-Edge Continual Test-Time Adaptation with Dynamic Sampling and Heterogeneous Distillationaccepted
647. Cross-Axis Feature Fusion with Joint-Wise Motion Difference Prediction for Text-Based 3D Human Motion Editingaccepted
648. Cross-Domain Demo-to-Code via Neurosymbolic Counterfactual Reasoningaccepted
649. Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptationaccepted
650. Cross-Hand Latent Representation for Vision-Language-Action Modelsaccepted
651. Cross-Instance Gaussian Splatting Registration via Geometry-Aware Feature-Guided Alignmentaccepted
652. Cross-Modal Attention Calibration for LVLM Hallucination Mitigationaccepted
653. Cross-Modal Emotion Transfer for Emotion Editing in Talking Face Videoaccepted
654. Cross-Modal Guided Visual Synthesis for Data-Efficient Multimodal Depression Recognitionaccepted
655. Cross-Scale Pansharpening via ScaleFormer and the PanScale Benchmarkaccepted
656. Cross-Slice Knowledge Transfer via Masked Multi-Modal Heterogeneous Graph Contrastive Learning for Spatial Gene Expression Inferenceaccepted
657. Cross-Subject EEG-to-Video Reconstruction and Beyondaccepted
658. Cross-View Distillation and Adaptive Masking for Incomplete Multi-View Multi-Label Classificationaccepted
659. Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced Imagesaccepted
660. Cross-domain Dual-stream Feature Disentanglement for Brain Disorder Prediction with Sparsely Labeled PETaccepted
661. Cross-modal Fuzzy Alignment Network for Text-Aerial Person Retrieval and A Large-scale Benchmarkaccepted
662. Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learningaccepted
663. Cross-modal Representation Learning for Diffusion-generated Image Detectionaccepted
664. CrossEarth-Gate: Fisher-Guided Adaptive Tuning Engine for Efficient Adaptation of Cross-Domain Remote Sensing Semantic Segmentationaccepted
665. CrossHOI-Bench: A Unified Benchmark for HOI Evaluation across Vision-Language Models and HOI-Specific Methodsaccepted
666. CrossHOI: Learning Cross-View Representations for Monocular 3D Human-Object Interaction Reconstructionaccepted
667. CrossVL: Complexity-Aware Feature Routing and Paired Curriculum for Cross-View Vision-Language Detectionaccepted
668. CrowdGaussian: Reconstructing High-Fidelity 3D Gaussians for Human Crowd from a Single Imageaccepted
669. CryoHype: Reconstructing a thousand cryo-EM structures with transformer-based hypernetworksaccepted
670. CryoKRAQEN: Kernel-Regularized Annealing for Quantized Embedding Networks in Cryo-EM Heterogeneous Reconstructionaccepted
671. CubeComposer: Spatio-Temporal Autoregressive 4K 360deg Video Generation from Perspective Videoaccepted
672. Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokensaccepted
673. Curriculum Group Policy Optimization: Adaptive Sampling for Unleashing the Potential of Text-to-Image Generationaccepted
674. Curvature-Aware Captioning: Leveraging Geodesic Attention for 3D Scene Understandingaccepted
675. Curvature-Aware Zeroth-Order Optimization for Memory-Efficient Test-Time Adaptationaccepted
676. CustomTex: High-fidelity Indoor Scene Texturing via Multi-Reference Customizationaccepted
677. Customized Fusion: A Closed-Loop Dynamic Network for Adaptive Multi-Task-Aware Infrared-Visible Image Fusionaccepted
678. Cut to the Chase: Training-free Multimodal Summarization via Chain-of-Eventsaccepted
679. Cycle-Consistent Tuning for Layered Image Decompositionaccepted
680. CycleBEV: Regularizing View Transformation Networks via View Cycle Consistency for Bird's-Eye-View Semantic Segmentationaccepted
681. CycleManip: Enabling Cycle-based Manipulation via Effective History Perception and Understandingaccepted
682. D$^2$-FOSA: Dual-Diffusion Guided EEG-to-Image Reconstruction with Frequency-Oriented Semantic Alignmentaccepted
683. D-Convexity: A Unified Differentiable Convex Shape Prior via Quasi-Concavity for Data-driven Image Segmentationaccepted
684. D-Prism: Differentiable Primitives for Structured Dynamic Modelingaccepted
685. D2Cache: Second-Order Delta Caching for Higher Video Diffusion Accelerationaccepted
686. D2Dewarp: Dual Dimensions Geometric Representation Learning Based Document Image Dewarpingaccepted
687. D2FANet: Enhancing Video Object Detection with Dual-Domain Feature Aggregation Networkaccepted
688. D2T2 - Multimodal Automated Planning for Brachytherapyaccepted
689. D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigationaccepted
690. DA-Mamba: Learning Domain-Aware State Space Model for Global-Local Alignment in Domain Adaptive Object Detectionaccepted
691. DA-VAE: Plug-in Latent Compression for Diffusion via Detail Alignmentaccepted
692. DABO: Difficulty-Aware Bayesian Optimization with Diffusion-Learned Priorsaccepted
693. DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimationaccepted
694. DARC: Dual Adjustment Reasoning with Counterfactuals for Trustworthy Chest X-ray Classificationaccepted
695. DASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examplesaccepted
696. DBMSolver: A Training-free Diffusion Bridge Sampler for High-Quality Image-to-Image Translationaccepted
697. DC-Merge: Improving Model Merging with Directional Consistencyaccepted
698. DCoAR: Deep Concept Injection into Unified Autoregressive Models for Personalized Text-to-Image Generationaccepted
699. DDSF: Robust Few-Shot Learning via Disentangled Subspaces with Determinantal Point Processaccepted
700. DDT: Decoupled Diffusion Transformeraccepted
701. DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformersaccepted
702. DENALI: A Dataset Enabling Non-Line-of-Sight Spatial Reasoning with Low-Cost LiDARsaccepted
703. DETACH : Decomposed Spatio-Temporal Alignment for Exocentric Video and Ambient Sensors with Staged Learningaccepted
704. DEVA: Fine-tuning Multimodal Large Language Models for Visual Perception Tasksaccepted
705. DFD-HR: Generalizable Deepfake Detection via Hierarchical Routing Learningaccepted
706. DF^2-VB: Dual-level Fuzzy Fusion with View-specific Boosting for Multi-view Multi-label Classificationaccepted
707. DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Imagesaccepted
708. DGS: Dual Gradient and Semantic-Shift Guided Low-Rank Adaptation for Class Incremental Learningaccepted
709. DICArt: Advancing Category-level Articulated Object Pose Estimation in Discrete State-Spacesaccepted
710. DIMOS: Disentangling Instance-level Moving Object Segmentationaccepted
711. DINO Eats CLIP: Adapting Beyond Knowns for Open-set 3D Object Retrievalaccepted
712. DK-DDIL: Adaptive Knowledge Retention for Dynamic Domain-Incremental Learning in Medical Imagingaccepted
713. DLVP-CLIP: Enhancing Fine-Grained Zero-Shot Anomaly Detection via Dynamic Local Visual Promptingaccepted
714. DLWM: Dual Latent World Models enable Holistic Gaussian-centric Pre-training in Autonomous Drivingaccepted
715. DMAligner: Enhancing Image Alignment via Diffusion Model Based View Synthesisaccepted
716. DMGD: Train-Free Dataset Distillation with Semantic-Distribution Matching in Diffusion Modelsaccepted
717. DNF-SR: Dual-Input and Negative-Aware Feature Fine-Tuning for Real-World Image Super-Resolutionaccepted
718. DP-FedAdamW: An Efficient Optimizer for Differentially Private Federated Large Modelsaccepted
719. DPAR: Dynamic Patchification for Efficient Autoregressive Visual Generationaccepted
720. DPGF-Net: Dual-Prior Guided Fusion Network for Joint Assessment of Perceptual Quality and Semantic Consistency in AI-Generated Imagesaccepted
721. DPL: Decoupled Prototype Learning for Enhancing Robustness of Vision-Language Transformers to Missing Modalitiesaccepted
722. DRAMA: Next-Gen Dynamic Orchestration for Resilient Multi-Agent Ecosystems in Fluxaccepted
723. DREAM: Document Recognition with Explicit Adaptive Memoryaccepted
724. DRM: Diffusion-based Reward Model With Step-wise Guidanceaccepted
725. DROID-SLAM in the Wildaccepted
726. DRS-GUI: Dynamic Region Search for Training-Free GUI Groundingaccepted
727. DRiffusion: Draft-and-Refine Process Parallelizes Diffusion Models with Easeaccepted
728. DSCA: Dynamic Subspace Concept Alignment for Lifelong VLM Editingaccepted
729. DSERT-RoLL: Robust Multi-Modal Perception for Diverse Driving Conditions with Stereo Event-RGB-Thermal Cameras, 4D Radar, and Dual-LiDARaccepted
730. DSFlash: Comprehensive Panoptic Scene Graph Generation in Realtimeaccepted
731. DSO: Direct Steering Optimization for Bias Mitigationaccepted
732. DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolutionaccepted
733. DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inferenceaccepted
734. DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolutionaccepted
735. DVAR: Dynamic Visual Autoregressive Modeling for Image Super-Resolutionaccepted
736. DVGT: Driving Visual Geometry Transformeraccepted
737. D^3FER: Dual Channel and Dual Branch Network for Robust Facial Expression Recognition under Dual Challengesaccepted
738. Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridgingaccepted
739. Dark3R: Learning Structure from Motion in the Darkaccepted
740. DarkAct: A RGB-Thermal Dataset and Fusion Framework for Multimodal Low-Light Action Recognitionaccepted
741. DarkShake-DVS: Event-based Human Action Recognition under Low-light and Shaking Camera Conditionsaccepted
742. Data Leakage Detection and De-duplication in Large Scale Geospatial Image Datasetsaccepted
743. Data-Centric Meta-Learning for Robust Few-Shot Generalizationaccepted
744. Dataset Distillation by Influence Matchingaccepted
745. DeAR: Fine-Grained VLM Adaptation by Decomposing Attention Head Rolesaccepted
746. DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generationaccepted
747. DeDelayed: Deleting Remote Inference Delay via On-Device Correctionaccepted
748. DeRVOS: Decoupling Consistent Trajectory Generation and Multimodal Understanding for Referring Video Object Segmentationaccepted
749. DeX-Portrait: Disentangled and Expressive Portrait Animation via Explicit and Latent Motion Representationsaccepted
750. Debiased Sample Selection for Learning with Noisy Labelsaccepted
751. Deciphering Genotype-Phenotype Mechanisms from High-Content Profiling via Knowledge-Guided Multi-modal Graph Learningaccepted
752. Decision Boundary-aware Generation for Long-tailed Learningaccepted
753. DecoVLN: Decoupling Observation, Reasoning, and Correction for Vision-and-Language Navigationaccepted
754. Decoding 3D Perception via BrainSSD: Synergistic Fusion of EEG Representations from Static and Dynamic Visual Streamsaccepted
755. Decompose and Transfer: CoT-Prompting Enhanced Alignment for Open-Vocabulary Temporal Action Detectionaccepted
756. Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compressionaccepted
757. Deconstructing the Failure of Ideal Noise Correction: A Three-Pillar Diagnosisaccepted
758. Decouple Your Discovery and Memory in Continual Generalized Category Discoveryaccepted
759. Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoningaccepted
760. Decoupled Generative Modeling for Human-Object Interaction Synthesisaccepted
761. Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translationaccepted
762. Decoupled and Reusable Adaptation for Efficient Cross-Modal Transferaccepted
763. Decoupling Bias, Aligning Distributions: Synergistic Fairness Optimization for Deepfake Detectionaccepted
764. Decoupling Defense Strategies for Robust Image Watermarkingaccepted
765. Decoupling Stability and Plasticity for Multi-Modal Test-Time Adaptationaccepted
766. Decoupling Vision and Language: Codebook Anchored Visual Adaptationaccepted
767. Deep Feature Deformation Weightsaccepted
768. DeepAlign: Mitigating Modality Conflict through Modality-Specific Alignmentaccepted
769. DeepProtect: Proactive Face-Swapping Defense using Identity Blending and Attribute Distortionaccepted
770. DeepScan: A Training-Free Framework for Visually Grounded Reasoning in Large Vision-Language Modelsaccepted
771. Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Modelsaccepted
772. DeepfakeImpact: A Two-Stage Benchmark with Real-World Impact in Deepfake Detectionaccepted
773. Defect Cue-Preserved Structural Feature Refinement for Few-Shot Anomaly Detectionaccepted
774. Defending Unauthorized Model Merging via Dual-Stage Weight Protectionaccepted
775. Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillationaccepted
776. Deformation-based In-Context Learning for Point Cloud Understandingaccepted
777. Degradation-Consistent Test-Time Adaptation for All-in-One Image Restorationaccepted
778. Degradation-Robust Fusion: An Efficient Degradation-Aware Diffusion Framework for Multimodal Image Fusion in Arbitrary Degradation Scenariosaccepted
779. Dehallu3D: Hallucination-Mitigated 3D Generation from a Single Image via Cyclic View Consistency Refinementaccepted
780. Dejavu: Towards Experience Feedback Learning for Embodied Intelligenceaccepted
781. Delta Rectified Flow Sampling for Text-to-Image Editingaccepted
782. DeltaQuant: 4-bit Video Diffusion Models with Spatiotemporal Delta Smoothingaccepted
783. Delving Aleatoric Uncertainty in Medical Image Segmentation via Vision Foundation Modelsaccepted
784. Demo2Tutorial: From Human Experience to Multimodal Software Tutorialsaccepted
785. DemoFunGrasp: Universal Dexterous Functional Grasping via Demonstration-Editing Reinforcement Learningaccepted
786. Den-TP: A Density-Balanced Data Curation and Evaluation Framework for Trajectory Predictionaccepted
787. Denoise and Align: Towards Source-Free UDA for Robust Panoramic Semantic Segmentationaccepted
788. Denoising as Path Planning: Training-Free Acceleration of Diffusion Models with DPCacheaccepted
789. Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generationaccepted
790. Dense Metric Depth Completion from Sparse Direct Time-of-Flight Sensorsaccepted
791. Depth Any Endoscopy: Towards Self-Supervised Generalizable Depth Estimation in Monocular Endoscopyaccepted
792. Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimationaccepted
793. Depth Hypothesis Guided Iterative Refinement for Event-Image Monocular Depth Estimationaccepted
794. Depth Peeling for High-Fidelity Gaussian-Enhanced Surfel Renderingaccepted
795. DepthFocus: Controllable Depth Estimation for See-Through Scenesaccepted
796. Describe Anything Anywhere At Any Momentaccepted
797. Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Modelsaccepted
798. Designing Instance-Level Sampling Schedules via REINFORCE with James-Stein Shrinkageaccepted
799. Designing to Forget: Deep Semi-parametric Models for Unlearningaccepted
800. DetAny4D: Detect Anything 4D Temporally in a Streaming RGB Videoaccepted
801. Detect Any AI-Counterfeited Text Imageaccepted
802. Detect Anything via Next Point Predictionaccepted
803. DetectSCI: Toward Object-Guided ROI Reconstruction for High-Resolution Video Snapshot Compressive Imagingaccepted
804. Detecting AI-Generated Forgeries via Iterative Manifold Deviation Amplificationaccepted
805. Detecting Compressed AI-Generated Images via Phase Spectrum Robustnessaccepted
806. Detecting Unknown Objects via Energy-based Separation for Open World Object Detectionaccepted
807. DextER: Language-driven Dexterous Grasp Generation with Embodied Reasoningaccepted
808. Dexterous World Modelsaccepted
809. DiG: Differential Grounding for Enhancing Fine-Grained Perception in Multimodal Large Language Modelsaccepted
810. DiGraphHal-Bench: Evaluating Multimodal Large Language Models on Complex Directed Graphsaccepted
811. DiP: Taming Diffusion Models in Pixel Spaceaccepted
812. DiT-Distill: Open-Set Fine-Grained Retrieval via Generative Curriculum Knowledgeaccepted
813. DiT-IC: Aligned Diffusion Transformer for Efficient Image Compressionaccepted
814. DiT360: High-Fidelity Panoramic Image Generation via Hybrid Trainingaccepted
815. Diagnose, Correct, and Learn from Manipulation Failures via Visual Symbolsaccepted
816. Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projectionaccepted
817. Diagram2Structure: Unlocking LLMs' Diagram Comprehension through DiagramDiff, a Framework for Structuring Offline Diagramsaccepted
818. DialogueVPR: Towards Conversational Visual Place Recognitionaccepted
819. Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMsaccepted
820. Diff-SemiER: Transparency-Aware Adaptive Fusion Diffusion Model with Generative Prior for Semi-Transparent Eyeglasses Removalaccepted
821. Diff4Splat: Repurposing Video Diffusion Models for Dynamic Scene Generationaccepted
822. DiffBMP: Differentiable Rendering with Bitmap Primitivesaccepted
823. DiffDecompose: Layer-Wise Decomposition of Alpha-Composited Images via Diffusion Transformersaccepted
824. DiffGraph: An Automated Agent-driven Model Merging Framework for In-the-Wild Text-to-Image Generationaccepted
825. DiffSoup: Direct Differentiable Rasterization of Triangle Soup for Extreme Radiance Field Simplificationaccepted
826. Differences That Matter: Auditing Models for Capability Gap Discovery and Rectificationaccepted
827. Differentiable Adaptive 4D Structured Illumination for Joint Capture of Shape and Reflectanceaccepted
828. Differentiable Laplacian Matrix Guided Superpixel Segmentationaccepted
829. Differentiable Stroke Planning with Dual Parameterization for Efficient and High-Fidelity Painting Creationaccepted
830. Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compressionaccepted
831. Differentially Private 2D Human Pose Estimationaccepted
832. DiffuView: Multi-View Diffusion Pretraining for 3D Aware Robotic Manipulationaccepted
833. Diffusion Forcing Planner: History-Annealed Planning with Time-Dependent Guidance for Autonomous Drivingaccepted
834. Diffusion Guided Chain-of-Vision for Large Autoregressive Vision Modelsaccepted
835. Diffusion MRI Transformer with a Diffusion Space Rotary Positional Embedding (D-RoPE)accepted
836. Diffusion Mental Averagesaccepted
837. Diffusion Probe: Generated Image Result Prediction Using CNN Probesaccepted
838. Diffusion Sampling Path Tells More: An Efficient Plug-and-Play Strategy for Sample Filteringaccepted
839. Diffusion with a Linguistic Compass: Steering the Generation of Clinically Plausible Future sMRI Representations for Early MCI Conversion Predictionaccepted
840. Diffusion-Based Makeup Transfer with Facial Region-Aware Makeup Featuresaccepted
841. Diffusion-Based Native Adversarial Synthesis for Enhanced Medical Segmentation Generalizationaccepted
842. Diffusion-Based sRGB Real Noise Generation via Prompt-Driven Noise Representation Learningaccepted
843. DiffusionFF: A Diffusion-based Framework for Joint Face Forgery Detection and Fine-Grained Artifact Localizationaccepted
844. DiffusionHarmonizer: Bridging Neural Reconstruction and Photorealistic Simulation with Online Diffusion Enhanceraccepted
845. Direct Segmentation without Logits Optimization for Training-Free Open-Vocabulary Semantic Segmentationaccepted
846. DirectFisheye-GS: Enabling Native Fisheye Input in Gaussian Splatting with Cross-View Joint Optimizationaccepted
847. Direction-aware 3D Large Multimodal Modelsaccepted
848. DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Cachingaccepted
849. Disco-GS: Gaussian Splatting in Dynamic Color Lightingaccepted
850. Discover, Segment, and Select: A Progressive Mechanism for Zero-shot Camouflaged Object Segmentationaccepted
851. Discovering Adaptive Task Dependencies for Efficient Multi-Task Representation Compressionaccepted
852. Discriminative Perception via Anchored Description for Reasoning Segmentationaccepted
853. Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglementaccepted
854. Disentangled Textual Priors for Diffusion-based Image Super-Resolutionaccepted
855. Disentanglement-wise Image Dehazing through Cross-Domain Manifold Consensusaccepted
856. Disentangling to Re-couple: Resolving the Similarity-Controllability Paradox in Subject-Driven Text-to-Image Generationaccepted
857. Distilling Balanced Knowledge from a Biased Teacheraccepted
858. Distilling Quasi-Conformal Mapping: A Generalizable and Efficient Solution for Wide-Angle Correctionaccepted
859. Distilling Unsigned Distance Function for Surface Reconstruction from 3D Gaussian Splattingaccepted
860. Distributed Image Compression with Multimodal Side Information at Extremely Low Bitratesaccepted
861. Distribution-Aligned Multimodal Fusion for Robust Object Detectionaccepted
862. Diverse Video Generation with Determinantal Point Process-Guided Policy Optimizationaccepted
863. DiverseDiT: Towards Diverse Representation Learning in Diffusion Transformersaccepted
864. DiverseGRPO: Mitigating Mode Collapse in Image Generation via Diversity-Aware GRPOaccepted
865. Diversity over Uniformity: Rethinking Representation in Generated Image Detectionaccepted
866. Divide, Conquer, and Aggregate: Asymmetric Experts for Class-Imbalanced Semi-Supervised Medical Image Segmentationaccepted
867. Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understandingaccepted
868. Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?accepted
869. Do VLMs Perceive or Recall? Probing Visual Perception vs. Memory with Classic Visual Illusionsaccepted
870. Do Vision-Language Models Leak What They Learn? Adaptive Token-Weighted Model Inversion Attacksaccepted
871. Do Vision-Language Models Measure Up? Benchmarking Visual Measurement Reading with MeasureBenchaccepted
872. Do You Have Freestyle? Expressive Humanoid Locomotion via Audio Controlaccepted
873. Do You See What I Am Pointing At? Gesture-Based Egocentric Video Question Answeringaccepted
874. DocPrune: Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruningaccepted
875. DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understandingaccepted
876. Does YOLO Really Need to See Every Training Image in Every Epoch?accepted
877. Domain Sensitive Federated Learning with Fisher-Informed Pruningaccepted
878. Domain-Skewed Federated Learning with Feature Decoupling and Calibrationaccepted
879. Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programsaccepted
880. Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal Modelsaccepted
881. Dr. Seg: Revisiting GRPO Training for Visual Large Language Models through Perception-Oriented Designaccepted
882. Dr.Occ: Depth- and Region-Guided 3D Occupancy from Surround-View Cameras for Autonomous Drivingaccepted
883. Draft and Refine with Visual Expertsaccepted
884. Drainage: A Unifying Framework for Addressing Class Uncertaintyaccepted
885. DreamOmni2: Multimodal Instruction-based Generation and Editingaccepted
886. DreamSAC: Learning Hamiltonian World Models via Symmetry Explorationaccepted
887. DreamSR: Towards Ultra-High-Resolution Image Super-Resolution via a Receptive-Field Enhanced Diffusion Transformeraccepted
888. DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prioraccepted
889. DreamStereo: Towards Real-Time Stereo Inpainting for HD Videosaccepted
890. DreamStyle: A Unified Framework for Video Stylizationaccepted
891. DreamingComics: A Story Visualization Pipeline via Subject and Layout Customized Generation using Video Modelsaccepted
892. Drift-Resilient Temporal Priors for Visual Trackingaccepted
893. Drive My Way: Preference Alignment of Vision-Language-Action Model for Personalized Drivingaccepted
894. DriveCombo: Benchmarking Compositional Traffic Rule Reasoning in Autonomous Drivingaccepted
895. DriveLaW: Unifying Planning and Video Generation in a Latent Driving Worldaccepted
896. DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Drivingaccepted
897. DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planningaccepted
898. DrivePTS: A Progressive Learning Framework with Textual and Structural Enhancement for Driving Scene Generationaccepted
899. DriveVLN: Towards Mapless Vision-and-Language Navigation in Autonomous Drivingaccepted
900. DriverGaze360: OmniDirectional Driver Attention with Object-Level Guidanceaccepted
901. Driving on Registersaccepted
902. Dropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splattingaccepted
903. Dual Ascent Diffusion for Inverse Problemsaccepted
904. Dual Band Thermal Videography: Separating Time-Varying Reflection and Emission Near Ambient Conditionsaccepted
905. Dual Graph Regularized Deep Unfolding Network for Guided Depth Map Super-resolutionaccepted
906. Dual-Agent Reinforcement Learning for Adaptive and Cost-Aware Visual-Inertial Odometryaccepted
907. Dual-Estimator: Decoupling Global and Local Semantic Shift for Drift Compensation in Class-Incremental Learningaccepted
908. Dual-Granularity Memory for Efficient Video Generationaccepted
909. Dual-Level Confidence based Implicit Self-Refinement for Medical Visual Question Answeringaccepted
910. Dual-Level Hypergraph Generation for Addressing Feature Scarcity in Whole-Slide Image Classificationaccepted
911. Dual-Prototype-Guided Multi-task Learning for Unsupervised Anomaly Detection and Classificationaccepted
912. Dual-branch Distilled Transformer for Efficient Asymmetric UAV Trackingaccepted
913. Dual-level Adaptation for Multi-Object Tracking: Building Test-Time Calibration from Experience and Intuitionaccepted
914. Dual-level Adapter Boosting Prompt-free Curvilinear Structure Segmentationaccepted
915. DualMirage: Hunting Stealthy Multimodal LLM Agents via CAPTCHAs with Contour and Adversarial Illusionsaccepted
916. DualPrim: Compact 3D Reconstruction with Positive and Negative Primitivesaccepted
917. DualReg: Dual-Space Filtering and Reinforcement for Rigid Registrationaccepted
918. DualSplat: Robust 3D Gaussian Splatting via Pseudo-Mask Bootstrapping from Reconstruction Failuresaccepted
919. Duala: Dual-Level Alignment of Subjects and Stimuli for Cross-Subject fMRI Decodingaccepted
920. DuetMerging: Synergizing Dynamic and Static Strategies for Mitigating Task Interference in Model Mergingaccepted
921. DuetSVG: Unified Multimodal SVG Generation with Internal Visual Guidanceaccepted
922. DuoGen: Towards Autonomous Interleaved Multimodal Generationaccepted
923. DuoMo: Dual Motion Diffusion for World-Space Human Reconstructionaccepted
924. DyFCLT: Dynamic Frequency-Decoupled Cross-Modal Learning Transformer for Multimodal Tiny Object Detectionaccepted
925. DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generationaccepted
926. DynBridge: Bridging Imagination and Control through Interaction Dynamics for Robot Manipulationaccepted
927. DynFusion: Rethinking Condition Fusion for Adaptive Multi-Conditional Text-to-Image Generationaccepted
928. Dynamic Black-hole Emission Tomography with Physics-informed Neural Fieldsaccepted
929. Dynamic Exposure Burst Image Restorationaccepted
930. Dynamic Important Example Mining for Reinforcement Finetuningaccepted
931. Dynamic Label Noise Suppression with Optimal Teacher Pool for Facial Expression Recognitionaccepted
932. Dynamic Logits Adjustment and Exploration for Test-Time Adaptation in Vision Language Modelsaccepted
933. Dynamic Magic: Unleashing Restricted Knowledge for Lifelong Person Re-Identificationaccepted
934. Dynamic Momentum Recalibration in Online Gradient Learningaccepted
935. Dynamic Stream Network for Combinatorial Explosion Problem in Deformable Medical Image Registrationaccepted
936. Dynamic Token Reweighting for Robust Vision-Language Modelsaccepted
937. Dynamic Visual SLAM using a General 3D Prioraccepted
938. Dynamic-Static Decomposition for Novel View Synthesis of Dynamic Scenes with Spiking Neuronsaccepted
939. Dynamic-eDiTor: Training-Free Text-Driven 4D Scene Editing with Multimodal Diffusion Transformeraccepted
940. DynamicGTR: Leveraging Graph Topology Representation Preferences to Boost VLM Capabilities on Graph QAsaccepted
941. DynamicTree: Interactive Real Tree Animation via Sparse Voxel Spectrumaccepted
942. DynamicVGGT: Learning Dynamic Point Maps for 4D Scene Reconstruction in Autonomous Drivingaccepted
943. Dynamics-Aware Preference Optimization for Vision-Language Modelsaccepted
944. Dynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From Videosaccepted
945. DynamicsBoost: Dynamic Plausible Video Generation via Annotation-Free Continuation Preference Optimizationaccepted
946. E$^2$-SCI: Elastic Edge-Cloud Speculative Decoding via Credit Inertiaaccepted
947. E-3DPSM: A State Machine for Event-based Egocentric 3D Human Pose Estimationaccepted
948. E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-trainingaccepted
949. E-comIQ-ZH: A Human-Aligned Dataset and Benchmark for Fine-Grained Evaluation of E-commerce Posters with Chain-of-Thoughtaccepted
950. E2EGS: Event-to-Edge Gaussian Splatting for Pose-Free 3D Reconstructionaccepted
951. E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Drivingaccepted
952. EDGS: Eliminating Densification for Efficient Convergence of 3DGSaccepted
953. EE-RL: Vision Language Guided Reinforcement Learning with Explorer and Expert model for End-to-End Autonomous Drivingaccepted
954. EEGiT: Teaching Vision Transformers to Understand the EEG signalaccepted
955. EG-3DVG: Expression and Geometry Aware Grounding Decoder for 3D Visual Groundingaccepted
956. EI-Part:Explode for Completion and Implode for Refinementaccepted
957. ELITE: Efficient Gaussian Head Avatar from a Monocular Video via Learned Initialization and Test-time Generative Adaptationaccepted
958. ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Video Understandingaccepted
959. ELVIS: Enhance Low-Light for Video Instance Segmentation in the Darkaccepted
960. ELiC: Efficient LiDAR Geometry Compression via Cross-Bit-depth Feature Propagation and Bag-of-Encodersaccepted
961. EMAD: Evidence-Centric Grounded Multimodal Diagnosis for Alzheimer's Diseaseaccepted
962. EMGauss: Continuous Slice-to-3D Reconstruction via Dynamic Gaussian Modeling in Volume Electron Microscopyaccepted
963. EMMA: Concept Erasure Benchmark with Comprehensive Semantic Metrics and Diverse Categoriesaccepted
964. EMMA: Extracting Multiple physical parameters from Multimodal Dataaccepted
965. EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Modelsaccepted
966. EMR-Diff: Edge-aware Multimodal Residual Diffusion Model for Hyperspectral Image Super-resolutionaccepted
967. ENC-Bench: A Benchmark for Evaluating Multimodal Large Language Models in Electronic Navigational Chart Understandingaccepted
968. ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specializationaccepted
969. EReCu: Pseudo-label Evolution Fusion and Refinement with Multi-Cue Learning for Unsupervised Camouflage Detectionaccepted
970. ESAM++: Efficient Online 3D Perception on the Edgeaccepted
971. EV-CGNet: Co-visible Focused 3D-guided 2D Event Keypoint Detection Networkaccepted
972. EVA: Efficient Reinforcement Learning for End-to-End Video Agentaccepted
973. EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generationaccepted
974. EVLF: Early Vision-Language Fusion for Generative Dataset Distillationaccepted
975. EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformeraccepted
976. EXOTIC: External Vision-driven Incomplete Multi-view Classificationaccepted
977. EagleNet: Energy-Aware Fine-Grained Relationship Learning Network for Text-Video Retrievalaccepted
978. EagleVision: A Dual-Stage Framework with BEV-grounding-based Chain-of-Thought for Spatial Intelligenceaccepted
979. EarlyTom: Early Token Compression Completes Fast Video Understandingaccepted
980. Easy2Hard: From Partially to Fully Unmatched Modalities as Negative Samples in Contrastive Learningaccepted
981. Easy3E: Feed-Forward 3D Asset Editing via Rectified Voxel Flowaccepted
982. EasyOmnimatte: Taming Pretrained Inpainting Diffusion Models for End-to-End Video Layered Decompositioaccepted
983. EasyV2V: A High-quality Instruction-based Video Editing Frameworkaccepted
984. EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generationaccepted
985. EchoPOSE: 6D Pose Estimation of Sparse Echocardiograms for Left-Ventricular 3D Shape Reconstructionaccepted
986. EchoVDiff: Cardiac-Cycle Echocardiography Video Generation from Arbitrary Single Frameaccepted
987. Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Modelsaccepted
988. Echoes of Ownership: Adversarial-Guided Dual Injection for Copyright Protection in MLLMsaccepted
989. EcoAlign: An Economically Rational Framework for Efficient LVLM Alignmentaccepted
990. EcoSplat: Efficiency-controllable Feed-forward 3D Gaussian Splatting from Multi-view Imagesaccepted
991. Edge-Focused Super-Resolution for Omnidirectional Images with Spherical Geometric Augmentationaccepted
992. Edge-RecViT: Efficient Vision Transformer via Semantic-Refined Dynamic Recursionaccepted
993. Edges Compete for Trust: Group Relative Edge Optimization for Building Reconstruction from Point Cloudsaccepted
994. Edit-As-Act: Goal-Regressive Planning for Open-Vocabulary 3D Indoor Scene Editingaccepted
995. Edit-aware RAW reconstructionaccepted
996. Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceiversaccepted
997. EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editingaccepted
998. EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editingaccepted
999. Editprint: General Digital Image Forensics via Editing Fingerprint with Self-Augmentation Trainingaccepted
1000. EduDiag: A Benchmark for Educational Diagnostic Reasoning with Error Tracing and Correction on Large Multimodal Modelsaccepted

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