ECCV2026 论文笔记 TODO

总计: 2738 篇 | 已完成: 2738 | 待更新: 0

• ∂DIBR: Differentiable Depth Image-based Rendering for Fast Novel View Synthesis | AC: 5284
• \(S^{2}\)-FracMix: Label-Preserving Self-Saliency Mixup Augmentation
• 2D Features Are All You Need for 3D Shape Understanding | AC: 5088
• 2K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Prediction
• 340 FPS Reflection-free Video from Spikes Modulated by a Rapidly Rotating Polarizer | AC: 4598
• 360° Image Perception with MLLMs: A Comprehensive Benchmark and a Training-Free Method | AC: 4124
• 360Anything: Geometry-Free Lifting of Images and Videos to 360°
• 360CityArena: A Realistic Virtual Urban Navigation Benchmark for Embodied Agents | AC: 5213
• 3D FaceShell: Attribute Transfer in 3D Face Avatars as a VLM Defense Mechanism | AC: 3820
• 3D Field of Junctions: A Noise-Robust, Training-Free Structural Prior for Volumetric Inverse Problems
• 3D Gaussian Splatting Compression with Object Scalability | AC: 4180
• 3D Gaussian Texture for Real-time Mesoscale Appearance Synthesis and Rendering | AC: 5185
• 3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement | AC: 4208
• 3D-Aware VLMs with Implicit and Explicit Geometries | AC: 3224
• 3D-Layout-R1: Structured Reasoning for Language-Instructed Spatial Editing | AC: 4525
• 3D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identification | AC: 5389
• 3D-ReGen: A Unified 3D Geometry Regeneration Framework | AC: 5538
• 3DGS3: Joint Super Sampling and Frame Interpolation for Real-Time Large-Scale 3DGS Rendering | AC: 3945
• 3DWay: Generalizing Robot Manipulation via 3D Consistent Waypoints | AC: 4788
• 3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering | AC: 5396
• 4D-VGGT: A SpatioTemporal Foundation Model for Dynamic Scene Geometry Estimation | AC: 3366
• 4DGS360: 360° Gaussian Reconstruction of Dynamic Objects from a Single Video | AC: 4866
• A Benchmark and Multi-Agent System for Instruction-driven Cinematic Video Compilation | AC: 3921
• A Benchmark for Heterogeneous Stereo Deblurring with Physically- and Epipolar-constrained Cross Attention | AC: 3687
• A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP
• A Comprehensive Analysis about Unsupervised Outlier Detection for Images | AC: 5320
• A Dual-space Patch-driven Complementary Learning Framework for Semi-supervised Multi-organ Segmentation | AC: 3317
• A Dual-Transformer Architecture with Cross-Attention for Multi-Camera View Recommendation | AC: 5242
• A Mechanism-Driven Theory of Phase Transitions in Active Learning
• A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models | AC: 3665
• A Scalable Vector Graphics Latent Space | AC: 5250
• A scalar per patch from pre-trained ViTs enables fast moving navigation in the real world
• A second-order theory of texture for depth from focus | AC: 3452
• A Simple Baseline with Placement Prior for Point-Supervised Oriented Object Detection | AC: 5334
• A²-Edit: Precise Reference-Guided Image Editing of Arbitrary Objects and Ambiguous Masks | AC: 4028
• A4-Agent: An Agentic Framework for Zero-Shot Affordance Reasoning | AC: 3311
• Abstract the Layout, Focus the Detail: A Dual-Granularity Representation Framework for Zero-Shot 3D Visual Grounding | AC: 5726
• AC3S: Adaptive Conditioning for 3D-Aware Synthetic Data Generation
• AccelAes: Accelerating Diffusion Transformers for Training-Free Aesthetic-Enhanced Image Generation | AC: 4669
• Accelerated Likelihood Maximization for Diffusion-based Versatile Content Generation
• Accelerating Diffusion Models via Equal-Risk Caching | AC: 5300
• Accelerating Diffusion Transformers with Gaussian Process Rectified Feature Cache | AC: 5921
• Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction
• Accelerating Text-to-Video Generation with Calibrated Sparse Attention | AC: 3436
• Accurate Zero-shot Quantization via Hierarchical Teacher-Assistant Distillation | AC: 4699
• Achieving Subcategorical Erasure in Text-to-Image Models | AC: 4524
• ActionParty: Multi-Subject Action Binding in Generative Video Games | AC: 4221
• ActionPlan: Future-Aware Streaming Motion Synthesis via Frame-Level Action Planning | AC: 5269
• Activation Quantization of Vision Encoders Needs Prefixing Registers | AC: 5152
• ActiveStructure: Plane Scene Graph-Guided Active 3D Gaussian Splatting | AC: 5184
• Actor as Its Own Critic: Unifying Region Understanding and Localization via CycleGRPO | AC: 4730
• Ada-VNNs: Adaptive Equivariance for Vector Neural Networks | AC: 4500
• AdaBoosting Text Prompts for Vision-Language Models
• AdaBridge-SR: Adaptive Bridge Matching for Real-World Image Super-Resolution | AC: 5676
• AdaDexGrasp: Adaptive Dexterous Grasping via 3D Visuo-Tactile Representation Fusion | AC: 5885
• ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs
• Adapting MLLMs for Nuanced Video Retrieval | AC: 4071
• Adaptive Latent Trajectory Anchoring for Action Segmentation Dataset Condensation | AC: 4115
• Adaptive Neural Dynamics for Robust Geometric LiDAR-Inertial State Estimation on UAVs | AC: 3654
• Adaptive Noise Covariance Scheduling under Riemannian Metrics for Diffusion Models | AC: 3974
• Adaptive Spectrum-Aware Feature Disentangled Network for Small Object Detection
• AdaptiveSplat: Texture Aware Controllable 3D Gaussian Allocation for Feed-Forward Reconstruction | AC: 4240
• AdaThinking-E: One-Token Entropy Regulation for Adaptive Thinking | AC: 4501
• Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods
• Adversarial Attack and Disturbance Detection by Hadamard-Coded Output Representations for Object Detection and Semantic Segmentation | AC: 5869
• Adversarial Score Distillation for Stable One-Step Diffusion in Real-World Image Super-Resolution | AC: 4022
• AerialMetric: Benchmarking and Adapting UAV Monocular Metric Depth Estimation in the Real World
• AeroVLA: A Vision-Language-Action Model for UAV Navigation via Minimalist End-to-End Control | AC: 5844
• AFFMAE: Scalable Vision Pre-Training for High-Resolution Microscopy Segmentation on Desktop Hardware
• Affogato: Open-Vocabulary Affordance Grounding with Automated Data Generation at Scale
• Affordance-Guided Diffusion Prior for 3D Hand Reconstruction | AC: 4223
• AGE: Agentic Gaussian Editing in 3D Scenarios | AC: 5221
• Agent-OBJ: Prompt-Driven 3D Adversaries for Multi-Modal Perception | AC: 5027
• Agentic Collaborative Cognition for Zero-Shot 3D Understanding
• AgentVLN: Towards Agentic Vision-and-Language Navigation | AC: 3693
• Aggregating Cross-Domain Knowledge via Learnable Tokens for Multi-Teacher Distillation | AC: 5104
• AHOY! Animatable Humans under Occlusion from YouTube Videos with Gaussian Splatting and Video Diffusion Priors
• AIMold: An Autonomous AI-based Pipeline for Complex Mold Design | AC: 5227
• AirSplat: Alignment and Rating for Robust Feed-Forward 3D Gaussian Splatting | AC: 3540
• AirZoo: A Unified Large-Scale Dataset for Grounding Aerial Geometric 3D Vision
• AiSCREAM: Absolute Target Localization with Language-Conditioned Cross-View Alignment for Autonomous Vehicles | AC: 4382
• Align and Segment: Unsupervised Learning for Building Segmentation From Misaligned Labels | AC: 5445
• Aligning Anything: Hierarchical Motion Estimation for Video Frame Interpolation | AC: 5280
• Aligning Human Sense: Calibrated Distributional Reward Learning for Video Generation | AC: 3296
• AlignMorph: Tuning-Free Diffusion Image Morphing via Explicit Semantic Transport | AC: 4288
• Allo{SR}2: Rectifying One-Step Super-Resolution to Stay Real via Allomorphic Generative Flows | AC: 3463
• AlphaRad: Grounded Zero-Shot Classification in Chest Radiology via α-Corrected Binary Cross Entropy and Factorized Latent Supervision | AC: 3412
• AMCI: Unlock the Potential of Large Multimodal Models for Fine-grained Open-world Classification via Adaptive Memory Context Injection | AC: 3437
• AMCoNav: Asynchronous Multi-module Collaborative Framework for Embodied Visual Navigation | AC: 5222
• Amplify, Aggregate, and Adjust: VideoMAE-based Holistic-Subtle Aggregation for Micro-Action Recognition | AC: 4219
• An Inverse-Adversarial and Difficulty-Adaptive Robust Vision-Language Model | AC: 3380
• Analytic Bayesian Uncertainty for LiDAR Segmentation: A Single-pass Generative Approach | AC: 5831
• Analyzing and Improving Training-Free Fast Sampling of Text-to-Image Diffusion Models | AC: 3912
• AnaPFL: When Closed-Form Solutions Meet Generalization and Personalization in Personalized Federated Learning | AC: 4595
• Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models | AC: 4828
• Anchor Forcing: Anchor Memory and Tri-Region RoPE for Interactive Streaming Video Diffusion | AC: 3196
• Anchored, Not Graded: Vision-Language Models Fail at Slant-from-Texture Perception
• AnchorGUI: Asymmetric Memory for Dual-Scale Learning in GUI Navigation | AC: 4292
• Anchoring and Steering Diffusion: Enhancing the Faithfulness of Text-to-Image Generation at Inference Time | AC: 5400
• Anchoring on Reality: Breaking the Pseudo-Target Ceiling in Makeup Transfer
• AnchorPrune: Relevance-Anchored Contextual Expansion for Visual Token Pruning | AC: 4172
• AnchorSplat: Fast and Structure Consistent Detail Synthesis for Gaussian Splatting | AC: 4233
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories | AC: 5000
• AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution | AC: 4173
• ANFI: Rethinking Neighbor Feature Interaction in Person Re-ID | AC: 5111
• Anomaly Factory 3D: A Modular Framework for Diverse Pseudo-Anomaly Synthesis in Unsupervised 3D Anomaly Detection | AC: 4995
• Anti-Prompt: Image Protection against Text-Guided Image-to-Video Generation | AC: 3308
• Any to Full: Prompting Depth Anything for Depth Completion in One Stage | AC: 3803
• AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation | AC: 5144
• AnyGround3D: Towards Grounding Any 3D Object in the Wild via 2D-to-3D Lifting | AC: 3160
• AnyMatch: Supercharging Universal Multi-Modal Image Matching with Large-Scale Single-View Images
• AnyStyle: A Single LoRA is Sufficient for Image-Guided Style Transfer | AC: 4851
• AnyView: Synthesizing Any Novel View in Dynamic Scenes | AC: 4566
• APT: Anchor-aligned Perturbations for Tamper Localization in Fully Regenerated Images | AC: 4048
• AquaStereo: Enabling Underwater Stereo Matching via Depth-Conditioned Diffusion and Geometry Self-Distillation | AC: 4868
• AR-CoPO: Align Autoregressive Video Generation with Contrastive Policy Optimization
• AracNet: Revealing Debiasing Signals across Layers with Shallow Monitors | AC: 4940
• ARC-Loc: Leveraging Azimuthal Ray Convergence as a Geometric Cue for Direct Cross-View Localization | AC: 3676
• ArcAD: Anomaly-Rectified Calibration for Cold-Start Supervised Anomaly Detection | AC: 5146
• Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection | AC: 3983
• ARGENT: Adaptive Hierarchical Image-Text Representations | AC: 5595
• ARGOS: Who, Where, and When in Agentic Multi-Camera Person Search | AC: 4039
• Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes | AC: 3446
• ARMS: Anchor–Relational Motion Streaming for Seamless Solo-Social Motion Transitions | AC: 5555
• Art Beyond Semantics: Sheaf-Informed Contrastive Learning for Multi-Relational Representations | AC: 5435
• ART-VSR: Adaptive Rectified Trajectories for One-Step Video Super-Resolution | AC: 4653
• Articulat3D: Reconstructing Articulated Digital Twins From Monocular Videos with Geometric and Motion Constraints
• Articulated Object Reconstruction from Rest-State Observation | AC: 4279
• ARVAR: Accelerating Visual Autoregressive Model via Attention Retrospect | AC: 3564
• ASSCG: Just-Right Gating over Chattering for Fast–Slow LLM Planning in Autonomous Driving | AC: 3354
• ASTAD: 非对称风格迁移实现自动驾驶合成到真实域的适应
• Asymmetric Anchoring: Opening the Black Box of MLLMs for Forgery Detection | AC: 5294
• Atlas is Your Perfect Context: One-Shot Customization for Generalizable Foundational Medical Image Segmentation | AC: 3573
• ATOMIC: A Domain-Specific Vision-Language Model for Transmission Electron Microscopy | AC: 5128
• ATP-Bench: Towards the Agentic Tool Planning for MLLM Interleaved Generation | AC: 3485
• Attention is Case-Sensitive | AC: 3409
• Attention Misses Visual Risk: Risk-Adaptive Steering for Multimodal Safety Alignment | AC: 4363
• Attention-based Vision-Language Memory for Spatial Reasoning | AC: 4166
• Attention-DP3: Spatially Object-aware 3D Diffusion Policy via Geometry-aligned Attentional Conditioning | AC: 4203
• Attention-Logit Steering to Compositional Generalization for Continual VQA | AC: 5723
• Attribute Token Arithmetic: Disentangled and Continuous Semantic Control for Visual Autoregressive Models | AC: 3951
• Audio-Visual Camera Pose Estimation with Passive Scene Sounds and In-the-Wild Video
• Audio-Visual Continual Test-Time Adaptation without Forgetting | AC: 4051
• Auto3R: Automated 3D Reconstruction and Scanning via Data-driven Uncertainty Quantification | AC: 3391
• AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labels | AC: 3815
• Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration | AC: 4257
• AutoPhyX: Automatic Text-Condition Physics Property Generation | AC: 4701
• Autoregressive Image Generation Needs Only a Few Lines of Cached Tokens | AC: 4010
• AutoSpeed: Annotation-Free Stage-Adaptive Motion Speed Learning for Robot Manipulation
• AutoV: Loss-Oriented Ranking for Visual Prompt Retrieval in LVLMs | AC: 3550
• AutoWeather4D: Autonomous Driving Video Weather Conversion via G-Buffer Dual-Pass Editing | AC: 4102
• AV2T-Gen: Aerial Visible to Thermal Generation with Environment and Vehicle State Guidance | AC: 3919
• AViTS：Adaptive Spatiotemporal Token Selection for Efficient Dynamic-Resolution Generation | AC: 3330
• AVQ-Attention: Adaptive Vector-Quantized Attention | AC: 4988
• AVSplat:Dense-View Feed-Forward 3D Gaussian Splatting with Assist-View Preconditioning | AC: 3993
• AVSR-Diff: Scale-Agnostic Diffusion Priors for Temporally Consistent Arbitrary-Scale Video Super-Resolution
• AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation
• Axolotl3D: a Unified Framework for Faithful 3D Shape Completion | AC: 3723
• BAAF: Universal Transformation of One-Class Classifiers for Unsupervised Image Anomaly Detection | AC: 5489
• Back-Tracking from Clarity: Self-Learning to See Text from Afar | AC: 3551
• Background Blurring Matters: Improving Visual Grounding by Merging Text-Irrelevant Tokens | AC: 5081
• BackTranslation2.0 -- A Linguistically Motivated Metric to Assess Sign Language Production
• BaFCo: A Document Understanding Benchmark for Complex Bangla Form Comprehension | AC: 5793
• BATQuant: Outlier-Resilient MXFP4 Quantization via Learnable Block-wise Optimization | AC: 4636
• Bayesian Self-Attention with Local Pixel Correlations for Lightweight Denoising Transformers | AC: 4718
• Bayesian Uncertainty Attribution-Guided Fine-Tuning for Open-Set Action Recognition | AC: 5989
• BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Models | AC: 5972
• Be Tangential to Manifold: Discovering Riemannian Metric for Diffusion Models | AC: 4638
• Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning | AC: 4647
• Benchmarking Dynamic Affective Reasoning: A Viewer-Centric Video Emotion Dataset | AC: 4633
• Benchmarking Federated Learning & Knowledge Distillation for Point Cloud Classification | AC: 3844
• Benchmarking MLLMs on Mistake Recognition and Explanation in Single-Step Components of Cooking | AC: 5187
• Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench | AC: 5536
• Benchmarking Vision-Language Models for Microscopic Plant Image Understanding | AC: 4108
• Better Call CineCrew: Consistent Ultra-Long Narrative-to-Film Generation | AC: 3661
• BeTTER: Diagnose the Illusion of Embodied Reasoning in Vision-Language-Action Models | AC: 5364
• BEV-GS: Feed-forward Gaussian Splatting in Bird’s-Eye-View for Road Reconstruction | AC: 4436
• BEVLM: Distilling Semantic Knowledge from LLMs into Bird's-Eye View Representations | AC: 4104
• BEVOpen3D: Towards Open-World 3D Object Detection in Bird's-Eye-View | AC: 3368
• Beyond 2D Matching: A Unified Single-Stage Framework for Geometry-Aware Cross-View Object Geo-Localization | AC: 3796
• Beyond Absolute Scores: Relative Edit-induced Difference for Generalizable Image Aesthetic Assessment | AC: 4698
• Beyond Aesthetics: Quantifying Information Loss in Turbid Scenes | AC: 4433
• Beyond Alignment: A Generative Matching Paradigm via Flow Matching for Zero-Shot Skeleton-Based Action Recognition | AC: 4234
• Beyond Artifacts: Real-Centric Envelope Modeling for Reliable AI-Generated Image Detection | AC: 3942
• Beyond Atomic Layouts: Compositional Design Understanding with Vision-Language Models | AC: 4079
• Beyond Attention: Convolutional Global Context for Remote Sensing Change Detection | AC: 3835
• Beyond Categorical Matching: Intra-Class Graded Relevance Estimation for Cross-Modal 3D Retrieval | AC: 5096
• Beyond Common Sense: Grounding Logical Anomaly Detection in Inspection Criteria | AC: 4468
• Beyond Dense Futures: World Models as Structured Planners for Robotic Manipulation | AC: 3187
• Beyond Description: Cognitively Benchmarking Fine-Grained Action for Embodied Agents | AC: 4331
• Beyond Disjoint Tasks: Towards More Natural Continual Learning for Vision-Language Models | AC: 3239
• Beyond Filter Pruning: Top-K Spatial Selection for Efficient Neural Networks | AC: 4622
• Beyond Final Answers: CRYSTAL Benchmark for Transparent Multimodal Reasoning Evaluation | AC: 4913
• Beyond Fixed Luminance: Towards Panchromatic and Orthochromatic Image Colorization | AC: 3712
• Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives | AC: 3394
• Beyond Inpainting: Unleash 3D Understanding for Stable Camera-Controlled Video Re-rendering | AC: 3874
• Beyond Isolated Objects: Relationship-aware Open Vocabulary Scene Understanding via 3D Scene Graph Analysis | AC: 4812
• Beyond Isolated Scans: Cross-Phase Alignment of Structure and Topology for 3D Medical Pretraining | AC: 5629
• Beyond Language: Grounding Referring Expressions with Hand Pointing in Egocentric Vision | AC: 4119
• Beyond Linear Shortcuts: Rectifying Diffusion Preference Optimization with Intrinsic Generative Geometry | AC: 5151
• Beyond Random Sampling: Distribution-Aware Alignment for Semi-Supervised Medical Image Segmentation | AC: 5497
• Beyond Script Family Boundaries: Towards Unified Open-Set Scene Text Recognition | AC: 5199
• Beyond Sequential Distance: Inter-Modal Distance Invariant Position Encoding | AC: 3562
• Beyond the Black Box: Identifiable Interpretation and Control in Generative Models via Causal Minimality | AC: 4260
• Beyond the Boundary: RL-Driven Solution Space Exploration for Blind Face Restoration | AC: 4123
• Beyond Time Shifts: Adapting Omni-LLM as a Reference-Free Evaluator for Generative Audio-Visual Models | AC: 4882
• Beyond Where to Look: Trajectory-Guided Reinforcement Learning for Multimodal RLVR | AC: 5594
• BeyondMasks: Evaluating Causal and Physical Consistency in Video Object Removal | AC: 4665
• BeyondSight: Object Permanence for End-to-End Autonomous Driving | AC: 5981
• BiCE-HG: A Bi-Conditional Egocentric Hand Gesture Dataset for Intelligent Reality Systems | AC: 5982
• BioMedVR: Confusion-Aware Mixture-of-Prompt Experts for Biomedical Visual Reprogramming
• BioMTBee: Biologically Constrained Multi-View Template-Based 3D Reconstruction of Bumblebee | AC: 5834
• BIP: Bi-level Information Transfer and Completion Prompting for Visual Recognition with Missing Modalities | AC: 4101
• BiSLW: Bi-Spectral Latent Watermarking for Generative Diffusion Models | AC: 5476
• BitRIC: Efficient Neural Compression of LiDAR Range Images via Hierarchical Bitplanes | AC: 5317
• BLASt3R: Bundle Adjustment of Any Image Set with Multi-View Matching and Monocular priors | AC: 3420
• BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing | AC: 5075
• Blind to Position, Biased in Language: Probing Mid-Layer Representational Bias in Vision-Language Encoders for Zero-Shot Language-Grounded Spatial Understanding | AC: 3141
• BLOB-Q: Boosting Low Bit ViT Quantization via Global Optimization on Model Distortion | AC: 5591
• Boba: Batched Simulation for Physics-Based Gaussian Digital Twins | AC: 4947
• Boosting 6D Object Pose Estimation via Monocular Depth Cues | AC: 5757
• Boosting Correspondence Learning with Structure-Aware Estimator | AC: 4879
• Boosting Text-Driven Video Segmentation via Geometry-Aware Distillation | AC: 4230
• Bootstrapping Articulated 3D Reconstruction from 2D Image Collections | AC: 5953
• Bottom-up modeling of repeated elements via single image analysis-by-synthesis | AC: 3696
• Bounding-Box Trajectories Matter for Video Anomaly Detection | AC: 5841
• Boxer: Robust Lifting of Open-World 2D Bounding Boxes to 3D | AC: 4536
• BrainFIBRE: A Foundation Model via Information Decomposition for Brain Microstructure
• BrainRiem: Riemannian Prototype Learning for Source-Free Cross-Site Brain Network Diagnosis
• Break Visual-Linguistic Asymmetry: Unleashing VLM's Cross-Modal Potential for General Face Forgery Detection | AC: 4883
• Breaking High Confidence: Practical Face Impersonation under High-Security Thresholds | AC: 5875
• Breaking Rigidity in Adversarial Patch Attacks | AC: 5898
• Breaking the Model Forgetting Cycle in Long-Incremental 3D Object Detection | AC: 5691
• BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoning | AC: 4696
• BRepFacetGen: Reverse Engineering B-Reps By Generative Face Segmentation | AC: 4344
• BrepLLM: Enabling Large Language Models to Understand Boundary Representations
• Bridge-UniPS: Bridging Calibrated Photometric Stereo toward Universal Photometric Stereo | AC: 3325
• Bridging Online and Offline Handwriting via Differentiable Physical Rendering | AC: 3674
• Bridging the Geometry Mismatch: Frequency-Aware Anisotropic Serialization for Thin-Structure SSMs | AC: 5356
• Bridging Theory and Practice in Source-Free Domain Adaptation via Adversarial Proxy Perturbation | AC: 5270
• Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction
• Bridging Vision and Language Concepts through Optimal Transport Semantic Flow | AC: 5811
• Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models | AC: 3613
• BWAFDA: Block-wise Weighted Attention Fusion with Detail-aware for No-Reference Image Quality Assessment | AC: 4196
• C2E: Boosting Ego-Only 3D Object Detection via Multi-Teacher Contrastive Knowledge Distillation | AC: 4362
• C3-Bench: A Context-Aware Change Captioning Benchmark
• C3ASD: Multi-Level Consistency-Driven Representation Learning for Robust Active Speaker Detection | AC: 4432
• CabinSI: Omni-Cabin Spatial Reasoning through Explicit Visual Cognitive Maps | AC: 3315
• Calibrate Before Adapt: Training-Free Pseudo-Label Calibration for Semi-Supervised Cross-Domain Few-Shot Detection | AC: 5788
• CAM3R: Camera-Agnostic Model for 3D Reconstruction | AC: 5512
• Cambrian-P: Pose-Grounded Video Understanding | AC: 4080
• CameraAnything: Refilming Videos with Arbitrary Camera Control | AC: 3926
• Can Vision Models Truly Forget? Mirage: Representation-Level Certification of Visual Unlearning | AC: 3178
• CanoVerse: 3D Object Scalable Canonicalization and Dataset for Generation and Pose | AC: 3600
• Capacity Overflow: A Blind Spot for Backdoor Attacks in Vision MoE | AC: 3523
• Capacity-Controlled Multi-View Stylization of 3D Gaussian Splatting
• CaPCL: Caption-Preserved Continual Learning for Text-to-Image Retrieval | AC: 5212
• CapFrame: Text-Instructed Viewpoint Grounding in 3D Gaussian Scenes via Geometric Pseudo Labels | AC: 4479
• Caption Bottleneck Models | AC: 5814
• Caption Bottleneck Models | AC: 5814
• Capturing Spectral and Spatial Patterns for Federated Remote Sensing Segmentation | AC: 5810
• CAR-MIL: Counterfactual Attention Regularization for Multiple Instance Learning | AC: 5292
• CARE: Causally-Aligned Reasoning Exploration for Medical Large Language Models | AC: 4809
• CaRe: Critical Parameter Rectification for Efficient Visual Modeling | AC: 5148
• CASA: Cross-Attention over Self-Attention for Efficient Vision-Language Fusion | AC: 5264
• CasaMaestro: Multi-View Panoramas for House-Scale 3D Reconstruction | AC: 4013
• CascadeProto: Cascaded Cross-Modal Prototype Purification via Entropy-Aware Learning for Few-Shot 3D Point Cloud Segmentation | AC: 5339
• Cast and Attached Shadow Detection via Iterative Light and Geometry Reasoning | AC: 5072
• CAST3D: Customizing Arbitrary 2D Assets into 3D World | AC: 5114
• Category-Level 3D Correspondence in Camera Space via Morphable Object Priors | AC: 4455
• Category-Level Articulated Object Pose Estimation via Pose–Shape Hypothesis Generation and Verification | AC: 5234
• Causal Intervention in Concept Bottleneck Models | AC: 5376
• Causal Yet Future-Aware: Dual-Path Temporal Modeling for Online Action Segmentation | AC: 5567
• CausalDrive: Real-time Causal World Models for Autonomous Driving | AC: 3753
• CausalVAE as a Plug-in for World Models: Towards Reliable Counterfactual Dynamics | AC: 5710
• CCFM: Collision-Constrained Flow Matching for Safety-Critical Scenario Generation | AC: 5969
• CellFluxRL: Biologically-Constrained Virtual Cell Modeling via Reinforcement Learning | AC: 5479
• Ceptor: Vision-Language Model-Infused Diverse Guidance for Detecting Anything | AC: 5558
• CerDETR: Cell-Prior Empowered DETR for Cervical Lesion Detection | AC: 3977
• CFM: Language-aligned Concept Foundation Model for Vision | AC: 4197
• CGCC: Towards Generalizable Clothes-Changing Person Re-Identification | AC: 5721
• CGCE: Classifier-Guided Concept Erasure in Generative Models | AC: 4668
• Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens | AC: 4447
• CHARTSTYLE-100K: A Large-Scale Dataset for Structured Visualization Style Transfer | AC: 5569
• Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation | AC: 4161
• ChronoFlow Policy: Unifying Past-Future Interaction Flow in Visuomotor Policy Learning | AC: 3245
• ChronusOmni: Improving Time Awareness of Omni-Modal Large Language Models | AC: 4007
• CiQi-Agent: Aligning Vision, Tools and Aesthetics in Multimodal Agent for Cultural Reasoning on Chinese Porcelains | AC: 5941
• Circuit-MLLM: Topological Logic-Guided Latent-Space Visual Reasoning for Circuit Schematic Understanding | AC: 4463
• City-Level 3D Surface Reconstruction with Viewpoint Orientation Partitioning and Scene Completion | AC: 4098
• CL-Anomaly: Layer-Adaptive Mixture-of-Experts with Multimodal Large Language Model for Continual Learning in Anomaly Detection | AC: 3905
• CL4D: Contrastive Language–4D Pretraining for Vision-Language Reasoning in Dynamic Scenes | AC: 4532
• CLARITY: Medical World Model for Guiding Treatment Decisions by Simulating Context-Aware Disease Trajectories in Latent Space | AC: 4671
• CLDefocus: Physically Grounded Compound-Lens Defocus Blur Synthesis | AC: 5065
• ClearText-Video: A Large-Scale Text-Centric Video Dataset Bridging Video Restoration and Scene-Text Enhancement | AC: 3992
• CLIMP: Contrastive Language-Image Mamba Pretraining | AC: 5469
• Clinical Cognition Alignment for Gastrointestinal Diagnosis with Multimodal LLMs | AC: 4616
• CLIP-AUTT: Test-Time Personalization with Action Unit Prompting for Fine-Grained Video Emotion Recognition | AC: 5438
• CloSeR: Unified Relational Distillation from Closed-Set Teachers for Category Discovery | AC: 3386
• Closing the Capacity–Convergence Gap: Globally Optimal Configuration of Implicit Neural Representations | AC: 4964
• Clue Matters: Empower Video Reasoning with Brain-Inspired Latent Clue Learning | AC: 4320
• CLUE-VAD: Structured Semantic Clues for Understanding Explainable Events in Video Anomaly Detection | AC: 4744
• ClusterStyle: Modeling Intra-Style Diversity with Prototypical Clustering for Stylized Motion Generation | AC: 3740
• CMCC-ReID: Cross-Modality Clothing-Change Person Re-Identification | AC: 4076
• CMDer: Controllable Mode Decomposition-Based Single Motion Synthesis with Diffusion | AC: 4490
• CMDR: Contextual Multimodal Document Retrieval | AC: 5332
• CMDS-AD: Cross-Modal Dual-Stream Decoupling for Few-Shot Anomaly Detection
• CMuon: Accelerating and Stabilizing Diffusion Transformer Training via Chunked Momentum Orthogonalization | AC: 5960
• Co-evolving Representations in Joint Image-Feature Diffusion | AC: 5490
• Co-Steer: Cross-Modal Collaborative Steering for Jailbreaking MLLMs | AC: 4111
• Coarse-to-fine Contrast: A Hybrid Self-supervised Method for Non-rigid 3D Shape Matching | AC: 4319
• CoCo-IR: Conversational Composed Image Retrieval | AC: 4038
• CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation | AC: 3171
• CoDePose: Multi-View 3D Human Pose Estimation via Coupled 2D-3D Denoising Diffusion | AC: 5550
• Coding with Eyes: Visual Feedback Unlocks Reliable GUI Code Generating and Debugging | AC: 5263
• CogniCred: A Dataset and Benchmark for Cognitive Credential Forgery Detection | AC: 5845
• CoGoal3D: Collaborative 3D Object Detection with 3D-Aware Fusion and Refinement | AC: 3950
• CogSENet: Blind Image Deblurring with Blur-Conditioned Semantic Routing and Explicit Frequency Fusion
• CoIn: Comprehensive 2D-3D Inpainting with Gaussian Splatting Guidance | AC: 4201
• COLA: Continual Orthogonal Low-Rank Adaptation for Class-Incremental Learning | AC: 5464
• CollectionLoRA: Collecting 50 Effects in 1 LoRA for Deployment | AC: 4163
• Color Pass-Through via Camera-Display Coupling | AC: 4780
• ColorFM: An Optimization-to-Learning Framework for Color Transfer via Flow Matching | AC: 4628
• CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts | AC: 4776
• CoMaTrack: Competitive Multi-Agent Game-Theoretic Tracking with Vision-Language-Action Models | AC: 3708
• Combating Textual Noise and Redundancy: Entropy-Aware Dense Visual Token Pruning | AC: 3558
• Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification | AC: 4105
• CoMind: Understanding Collaborative Human Activity from Multiple Minds and Views | AC: 3588
• Compact and Structurally Transparent Cervical Cytology with Geometry-Driven Features and Closed-Form Attention | AC: 3896
• Compact Low-Cost Hyperspectral Imaging via Angular-to-Spectral Diversity Conversion | AC: 3677
• COMPASS: Grounding Composition-Intent Guidance in Unified Multimodal Models | AC: 5394
• Complex-Valued 2D Gaussian Representation for Computer-Generated Holography | AC: 3347
• ComplexMimic: Human–Scene Interaction Imitation in Complex 3D Environments | AC: 3457
• Composing Driving Worlds through Disentangled Control for Adversarial Scenario Generation | AC: 3714
• Compositional Non-Face Re-Identification Pressure under Cumulative Vision Releases | AC: 4562
• Comprehensive language–image pre-training for 3D medical image understanding | AC: 5833
• Comprehensive Robustness Analysis of LiDAR-based 3D Object Detection in Autonomous Driving | AC: 4486
• Concept-as-Tree: A Controllable Synthetic Data Framework Makes Stronger Personalized VLMs | AC: 4499
• Concept-to-Pixel: Prompt-Free Universal Medical Image Segmentation | AC: 4207
• Condensing Large-Scale Datasets Directly with Minimal Information Loss
• Conditional Flow Matching for Visually-Guided Acoustic Highlighting | AC: 4418
• ConfCtrl: Enabling Precise Camera Control in Video Diffusion via Confidence-Aware Interpolation | AC: 3892
• Confidence-Based Mesh Extraction from 3D Gaussians | AC: 3645
• ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning | AC: 4462
• Consistent Feature Transport for Image Relighting | AC: 5578
• Consistent Monocular Depth Estimation with Contact Region Boundary-Aware Refinement | AC: 4672
• Consistent Video-to-Video Translation via Explicit Correspondences | AC: 3572
• Constrained Rotation Optimization: Revisiting Crop-Based Gaze Estimation | AC: 4912
• Constructing and Interpreting Digital Twin Representations for Visual Reasoning via Large Language Models and Reinforcement Learning | AC: 4591
• Context Blindness in DPO: Mitigating Object Hallucination in MLLMs via Context-Calibrated Preference Optimization | AC: 5807
• Context-Aware Joint Alignment for Cross-Scene Hyperspectral Image Classification | AC: 4764
• Context-Interactive Reasoning for Group Activity Detection | AC: 5406
• ContextFlow: In-Context Flow Matching for Robot Manipulation | AC: 4946
• Continuous Adversarial Flow Models | AC: 4980
• Continuous Heart Rate Variability Estimation from Egocentric Systems for Skill Assessment | AC: 5338
• Continuous Speculative Decoding for Autoregressive Image Generation
• ConTrack: Constrained Hand Motion Tracking with Adaptive Trade-off Control | AC: 3535
• Contrastive Conditional–Unconditional Alignment for Long-tailed Diffusion Model | AC: 4581
• Contrastive-Guided Self-Supervised Latent Visual Reasoning for Hallucination Mitigation | AC: 5118
• Control-DINO: Feature Space Conditioning for Controllable Video Diffusion | AC: 4902
• ControlHair: Synergizing Physics Simulator and Video Diffusion for Controllable Dynamic Hair Rendering | AC: 5370
• Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints
• Controllable Generative Reference for Stereo Image Compression via Reliability-Aware Gating | AC: 5305
• Controlling Embedding Spaces with Text-Conditioned Transformations | AC: 4034
• Controlling Motion Transfer in Diffusion Transformers via Attention Heads | AC: 3621
• Conversational Human Audio-visual Talking Dialogue Generation | AC: 4941
• Cooking beyond Frames: A Stereo Event Camera Dataset in the Kitchen | AC: 5281
• CooperScene: Multi-Modal Cooperative Autonomy Benchmark with C-V2X Communication Characterization
• Coordinate Singularities Break Conformal Coverage for Gaze and Head Pose | AC: 5387
• CORE-V: Chain-Of-thought REasoning for Image Editing with Visual Interaction | AC: 3188
• CoReLIN: Constraint-based Reasoning for Zero-shot Lifelong Interactive Navigation | AC: 4588
• Correlation-Weighted Multi-Reward Optimization for Compositional Generation | AC: 5063
• CortexVideo: A Semantic-Spatial Dual-Anchor Framework for High-Fidelity fMRI-to-Video Reconstruction | AC: 4246
• CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates | AC: 5459
• COSY: Compositional 3DGS Synthesis for Disentangled Human Head Editing | AC: 3814
• CoSyncDiT: Cognitive Synchronous Diffusion Transformer for Movie Dubbing | AC: 3458
• CoToGrasp: Contact-Topology-Conditioned Dexterous Grasp Synthesis via Canonical Workspace Learning | AC: 5196
• CountEx: Fine-Grained Counting via Exemplars and Exclusion | AC: 3925
• Counting Trees from Satellite Imagery with Noisy Supervision | AC: 3817
• CoverPrune: Coverage-Driven Token Pruning for 3D VLMs via Optimal Transport | AC: 5259
• COVERT: Privacy-Preserving Covariant Obfuscation for VLMaaS via Exact Reparameterization and Tailored Tuning | AC: 5261
• CRAG-MM-Diagnostics: Enabling Stage-Wise Analysis of Knowledge-Intensive VQA | AC: 5125
• CRD-Net: Frequency-Adaptive Feature Injection and Change Decoupling for Building Damage Assessment | AC: 5684
• CRISP: Calibration-Aware Visual State Space Duality for Remote Sensing Image Segmentation | AC: 5624
• CritiqueDriveVLM: From Verifier-Guided Reinforcement Learning to Latent Thought Distillation for Autonomous Driving | AC: 4408
• Cross-Resolution Distribution Matching for Diffusion Distillation | AC: 5323
• Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers | AC: 4819
• Cross-Species Animal Re-Identification with Semantic Consistency Learning | AC: 5754
• Cross-View Yaw Estimation in Location Uncertainty with Line-Aligning Yaw Scoring | AC: 4552
• CrossFeat: Bridging Imaging Modalities in Feature Descriptor Space | AC: 5937
• CrossView: Can Vision-Language Models Reason Across Cameras? | AC: 5961
• CS-TTA: Preserving Concept Sensitivity in Test-Time Adaptation | AC: 3699
• CSS-BA: Gate Guided Column Space Search for Bundle Adjustment | AC: 5249
• CTEPM: Continuous-Time Event Process Memory for Long-Video Language Models | AC: 5848
• Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorations | AC: 3774
• CtrlCoMo: Controllable Co-Speech Motion Generation with Gesture–Action Disentanglement | AC: 5059
• Cube-Splat: High-Fidelity 360° Gaussian Splatting SLAM via Cubemap Factorization and Adjoint-Consistent Optimization | AC: 4224
• CubicSplat: Differentiable Vector Graphics via Error-Bounded Forward Relaxation | AC: 5391
• CulinaryCut: A Physics-aware Vision-Language-Action Benchmark for Food Cutting via Material Point Method | AC: 5439
• CURE: Contextual Debiasing and Unbiased Refinement for Training-Free Open-Vocabulary Semantic Segmentation | AC: 5573
• CURE: Cumulative Knowledge Reuse for Efficient Device-Server Hybrid Inference in Vision-Language Models | AC: 5036
• Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning
• Curvature-Guided Mixing for MLLM Adaptation
• CurveStream: Boosting Streaming Video Understanding in MLLMs via Curvature-Aware Hierarchical Visual Memory Management | AC: 5915
• CUST : Clustered Unit-level Similarity Transformer for Lightweight Image Super-Resolution | AC: 4220
• CustomX: Unified Character, Action, and Scene Customization in Video World Models
• CVSBench: A Comprehensive Benchmark for Cross-view Spatial Reasoning and Dreaming | AC: 3401
• Cycle-World: Mitigating Error Accumulation in Long-term Video World Models via Reverse-Prediction Cycle Consistency | AC: 5343
• D-Rex : Diffusion Rendering for Relightable Expressive Avatars | AC: 4921
• D-VLAM: Differential Vision and Language Mixing for Rehearsal Free Continual Learning | AC: 5836
• D2PO: Optimizing Diffusion Samplers via Dynamic Preference | AC: 5175
• D²R²OSR: Degradation-Disentangled Representation for Real-World Omnidirectional Image Super-Resolution | AC: 5315
• D3F-IR: Dual-Domain Deterministic Flow Matching for Visible-to-Infrared Translation | AC: 4599
• DA-F2F: Domain-Adaptive Object Detection with Feature-to-Feature Modulation and Alignment | AC: 3682
• DA-MergeLoRA: Hypernetwork-Based LoRA Merging for Few-Shot Test-Time Domain Adaptation | AC: 4515
• DANTE-W: Diffuse Albedo Neural Texturing in the Wild | AC: 5031
• DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognition | AC: 3612
• DAPS++: Rethinking Diffusion Inverse Problems with Decoupled Posterior Annealing | AC: 5944
• DARE to Mitigate Hallucination: Dual-path Auto-Regressive-aware Editing | AC: 3801
• DARL: Efficient Document-to-Markup Generation via Look-Ahead Diffusion Trajectory Sampling | AC: 5755
• DART: Deformable Adaptive Reasoning with Temporal Queries for Online Skeleton-Based Action Recognition | AC: 3850
• DART: Difficulty-Adaptive Routing for Zero-Shot Video Temporal Grounding | AC: 4030
• DASAM3D: A Unified Foundation Model for Enhanced 3D Scene Reconstruction and Segmentation | AC: 4783
• DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression | AC: 4843
• Data-Free Client Contribution Estimation via Logit Maximization for Federated Learning | AC: 5964
• DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space | AC: 4727
• DCARL: A Divide-and-Conquer Framework for Autoregressive Long-Trajectory Video Generation | AC: 4282
• DDStereo: Efficient Dual Decoder Transformers for Stereo 3D Road Anomaly Detection | AC: 4686
• DE2TR: Dual Evidence Detection Transformer for Video Temporal Grounding | AC: 5412
• Debiased Textual Prompt Tuning for Enhancing Unknown Class Discovery | AC: 5403
• DecepGPT: Schema-Driven Deception Detection with Multicultural Datasets and Robust Multimodal Learning | AC: 3797
• DeCo: Zero-Shot Anomaly Generation through Decoupling and Recoupling | AC: 4318
• Decoding Children’s Gait Behavior | AC: 3161
• Decoding Multimodal Causality: End-to-End Multimodal Mediation Pathways Inference | AC: 3479
• DeCoFlow: Structural Decomposition of Normalizing Flows for Continual Anomaly Detection | AC: 4729
• Decompose, Compare, and Decide: Multimodal LLMs are Implicit Few-Shot Learners | AC: 5414
• Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces
• DeCoPatch: Revealing Causal Latent Subspaces in Vision-Language Models for GUI Grounding | AC: 4189
• Decoupled Illumination Priors for Spatially Controllable Multi-View Indoor Scene Relighting | AC: 3256
• DecoupleGS: Interactive 3D Gaussian Splatting for End-to-End Autonomous Driving Testing | AC: 5765
• Decoupling Complexity from Scale in Latent Diffusion Model | AC: 4100
• Decoupling Moment from Event for Video Temporal Grounding | AC: 4663
• Deep Noise Label Learning via Effective Rank Reduction | AC: 5804
• Defect-aware Hybrid Prompt Optimization for Zero-Shot Multi-type Anomaly Detection and Segmentation | AC: 5970
• Defending from GeoLocalization through Adversarial Road Trips | AC: 4426
• DefenseSplat: Enhancing the Robustness of 3D Gaussian Splatting via Frequency-Aware Filtering
• DeforM: Reasoning-Guided Physics-Aware Video Generation via Spatial-Temporal Masking | AC: 3443
• Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models | AC: 4930
• Deformable and Multi-view Gradient-Aligned Physical Adversarial Camouflage | AC: 5397
• Deformable Triangle Splatting: Flexible Primitives for Real-Time Radiance Field Rendering | AC: 3724
• Degradation-Robust and Temporally Consistent Infrared–Visible Video Fusion via One-step Diffusion Framework | AC: 5285
• DeGuNet: Depth-Guided Ultra-Compact Backbones for Efficient LiDAR-Camera 3D Detection | AC: 4114
• Delaunay Canopy: Building Wireframe Reconstruction from Airborne LiDAR Point Clouds via Delaunay Graph | AC: 3930
• Delayed Bidirectional Alignment via Disentangled Audio Semantics for Audio-Visual Segmentation
• Delineating Knowledge Boundaries for Honest Large Vision-Language Models | AC: 5732
• DeltaDeno: Zero-Shot Anomaly Generation via Delta-Denoising Attribution | AC: 4406
• DeLux: Cross-Modal Local Artifact Restoration in Video Using Neuromorphic Data | AC: 4262
• Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability | AC: 4821
• DeMuS: Learning Decoupled Matching and Scoring for Batch Zero-Shot Industrial Anomaly Detection | AC: 3717
• Demystifing Video Reasoning | AC: 4731
• Denoised Variance-Based Pruning with Optimal Brain Bias Compensation | AC: 3650
• Denoising the Deep Sky: Physics-Based CCD Noise Formation for Astronomical Imaging | AC: 3316
• Denoising-Enhanced Coarse-to-Fine Infrared Small Target Detection with Attention Prior-Guided Knowledge Distillation
• Denoising-GS: Gaussian Splatting with Spatial-aware Denoising | AC: 4248
• Dense Dynamic Scene Reconstruction and Camera Pose Estimation from Multi-View Videos | AC: 4583
• Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views
• Dense Video Understanding with Inter-tokenization Acceleration | AC: 3614
• Depth-guided Multi-view Exposure Bracketing for HDR Robot Vision | AC: 5101
• DeRA: Decoupled Representation Alignment for Video Tokenization | AC: 3946
• Describe-Then-Act: Proactive Agent Steering via Distilled Language-Action World Models | AC: 4412
• Detect by Track: Making Detector-Free Matcher Trackable | AC: 3971
• Detecting Backdoors in Object Detection via Pre-NMS Prediction Distribution Shift | AC: 5600
• DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection | AC: 3881
• DETR is Secretly a Multispectral Detector: Zero-Parameter Adaptation via Semantic Alignment | AC: 5395
• DETRAM: End-to-end DEtection, Tracking and Recovery of HumAn Meshes | AC: 4979
• DeWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priors
• DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis | AC: 3194
• DG-Force: Disentangling and Gathering Forensic Cues is Needed for Image Manipulation Localization | AC: 4416
• DH-VLM: Dual-Horizon Cooperative Latent Reasoning for Autonomous Driving | AC: 5819
• DiaDem: Advancing Dialogue Descriptions in Audiovisual Video Captioning for Multimodal Large Language Models | AC: 3456
• Diagnosing Aerial-View Object Detectors with Foundational Image Generative Models | AC: 5592
• Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagrams | AC: 3381
• DICE: Disentangled Instance-Class knowlEdge prompt tuning via SAE for Vision-Language Models | AC: 5616
• DiCoBench: Benchmarking Multi-Image Fine-Grained Perception via Differential and Commonality Visual Cues
• DICT: Data Injection and Contrastive Trajectory Refinement for Conditional Image Generation with Diffusion Models | AC: 5857
• Different Changes Require Different Reasoning: Change-Type-Specialized Experts for Robust Change Captioning | AC: 3949
• Differentiable Polarized Path Tracing | AC: 5251
• DiffGI: Differentiable Geometry Images for High-Fidelity Thin-Shell 3D Generation | AC: 5678
• DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models | AC: 3667
• Difficulty-Conditioned Attribute-Specific Restoration for Low-Light Image Enhancement | AC: 3707
• DiffPro: Joint Timestep and Layer-Wise Precision Optimization for Efficient Diffusion Inference | AC: 3584
• DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxies | AC: 3382
• DiffRGD: An Inference-Time Diffusion Guidance Through Riemannian Gradient Descent | AC: 5262
• DiffUE: Enhancing Utility-Unlearnability Trade-off of Unlearnable Examples via Diffusion Autoencoders | AC: 5633
• DiffuPrompt: Adapting Video Foundation Models to 3D Medical Volumes via Latent Trajectory Priors | AC: 5340
• Diffusion Image Generation with Explicitly Modeling of Data Manifold Geometry | AC: 4916
• Diffusion Integrated Gradients: Controllable Path Generation for Flexible Feature Attribution
• Diffusion Model as a Generalized Segmentation Learner | AC: 4901
• Diffusion Models are Open-World Affordance Learners: Leveraging Generative Priors for 3D Affordance Learning | AC: 3990
• Diffusion to Obfuscation: Time-Adaptive Synthesized Generation Against Gradient Leakage Attacks in Federated Learning | AC: 5017
• Diffusion-based dual-view reflection removal | AC: 3182
• Diffusion-Based Immersive Visual Reasoning | AC: 3526
• Diffusion-Based Material Regularization for Physics-Based Inverse Rendering
• Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models | AC: 5042
• DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models | AC: 4441
• DiffVP:Differential Visual Semantic Prompting for LLM-Based CT Report Generation | AC: 5024
• DiGS-Avatar: Single-Image Animatable 3D Human Reconstruction via UV-Space Diffusion | AC: 3991
• DIGS: Differentiable, Incremental, Global, Scalable Pruning for Language Models | AC: 5076
• DiNBV-Grasp: Real-Time Distance-Aware Two-Stage Next-Best-View for Robotic Grasping | AC: 4360
• DINO-SLAM: DINO-Informed RGB-D SLAM for Neural Implicit and Explicit Representations | AC: 3777
• DINOde: Continuous Vision-Text Alignment for Open-Vocabulary Semantic Segmentation | AC: 3756
• DINOv3D: 2D-3D Joint Optimization for Unified Spatial Understanding | AC: 4298
• Direct Autoregressive Diffusion Distillation via Error-aware Causal Pretraining | AC: 3201
• Direct Diffusion Score Preference Optimization via Stepwise Contrastive Policy-Pair Supervision | AC: 4303
• Director: Instance-aware Gaussian Splatting for Dynamic Scene Modeling and Understanding | AC: 5035
• Discovering Geometric Biases in 3D Face Reconstruction: A Curvature-Aware Spectral Framework for Fairness Evaluation | AC: 5850
• DiscoVL: Unveiling Disentangled Cross-Modal Representation Learning via Orthogonal Adversarial Regularization for Vision-Language Models | AC: 5039
• Discrete Diffusion Bridges for Spatiotemporally Aligned Image Translation and Generation | AC: 3280
• Discrete Diffusion Models with MLLMs for Unified Medical Multimodal Generation | AC: 3279
• Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing | AC: 4254
• DisentangledTMR: Privacy-Preserving Skeleton Motion Retargeting via Factorized Transformers | AC: 5993
• Disentangling and Reusing Interaction Cues for Zero-Shot HOI Detection | AC: 3343
• Disentangling Hallucinations: Orthogonal Semantic Projection for Robust Interpretability | AC: 5456
• Disentangling Pictorial Cue Understanding from Language Bias in VLMs via Depth Ordering Task | AC: 3295
• Disentangling Rotation and Translation from SE(3)-Equivariant Features for Shape Assembly | AC: 4377
• DisRM: Reward Modeling as Discriminative Prediction | AC: 5189
• Distill on a Diet: Efficient Knowledge Distillation via Learnable Data Pruning
• Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation
• Distribution Matching Distillation Meets Reinforcement Learning | AC: 4350
• Distribution-Alignment Bridge for Uncertainty-Aware Text-to-Video Retrieval | AC: 5107
• DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer | AC: 5415
• DiTailed: Ensuring Visual Object Consistency in Text-Image-to-Image Flow Matching Models | AC: 3539
• DiTex4D: Direct Text-Driven 4D Generation with Structured Latent Diffusion | AC: 3779
• DIVA: Instruction-Aware Vision Token Pruning via Dual-Probe Attention Discrepancy | AC: 4758
• Dive into the implicit biases of low-rank vision-language alignment | AC: 4041
• DIVER: Disentangling Camera–Object and Active–Passive Motion for Video Generation | AC: 5541
• DiverseAD: A Large-Scale Driving Dataset with Diverse Atmospheric Conditions | AC: 4645
• DiverseVAR: Balancing Diversity and Quality of Next-Scale Visual Autoregressive Models | AC: 4304
• Diversity-Aware View Partitioning for Scalable VGGT | AC: 5571
• Divide and Align: Disentangled Vision-Language Learning for Text-Based Person Anomaly Search | AC: 3501
• Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models
• DivRL: Disentangled Self-Similarity Rewards for Diverse Subject-Driven Generation
• DLGStream: Dynamic Language-embedded Gaussian Splatting for Open-vocabulary Enabled Free-viewpoint Video Streaming
• DnA: Denoising Attention for Visual Tasks | AC: 3828
• Do Flat Minima Improve Sparse Novel View Synthesis? | AC: 3745
• Do Multimodal LLMs Understand Intraoral Dental Data? Dataset, Platform, and Baselines | AC: 4678
• Do Not Leave a Gap: Hallucination-Free Object Concealment in Vision-Language Models | AC: 5662
• Do Vision Language Models Recognize Visual Ambiguity? | AC: 5100
• DocLayout-VL: A Foundational Model for Hierarchical, Open-set, and Promptable Document Layout Segmentation | AC: 4756
• DoCoG: Mask-based Multi-Type Grounded Chain-of-Thought for Document QA | AC: 3695
• Doe-2: 3D Representation World Model for Unified Driving Scene Forecasting | AC: 3909
• DOGE: Differentiable Bézier Graph Optimization for Road Network Extraction | AC: 4405
• Domain Adaptation with Adaptive Imagination for Visual Reinforcement Learning under Limited Target Data | AC: 5440
• Domain Adaptive Object Detection via Dual-Stream Bilevel-Cycle Optimization | AC: 5159
• Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts
• Domain Generalization via Text-Anchored Information Bottleneck | AC: 3763
• Don't Let the Video Speak: Audio-Contrastive Preference Optimization for Audio-visual Language Models | AC: 4991
• Don’t Mask Out the Background! Natural-Light Photometric Stereo via Illumination Reconstruction | AC: 5632
• Don't Settle at the Mode! Mitigating Diversity Collapse in Pretrained Flow Models via Feature Self-Guidance
• Don’t Starve the Boundaries: Boundary-Constrained Label Propagation for Weakly Supervised 3D Segmentation | AC: 5688
• Don’t Teach Instability, Teach Robustness: Selective Sensitivity Gating for Adversarial Robust Distillation | AC: 3233
• Dotting the Eye: An Intent-Driven Image Retouching Agent for Visual Focus Enhancement | AC: 4878
• DP-BOA: Dirichlet-Process Birth-or-Assign for On-the-Fly Category Discovery | AC: 4517
• DPGS: A Diffusion-Prior Guided Framework for Large-Scale 3D Gaussian Splatting Reconstruction | AC: 4885
• DR-GS: Physically-Based Deformable and Relightable 2D Gaussians | AC: 4152
• DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfaces | AC: 3931
• DreamEdit3D: Personalization of Multi-View Diffusion Models for 3D Editing | AC: 4865
• DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing | AC: 4308
• DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising | AC: 4994
• DreamWorld: Geometry-Grounded Video Diffusion for 3D-Consistent World Modeling | AC: 5879
• Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off
• Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting | AC: 4877
• DRIFT: Difficulty-aware Rectified Flows for Through-plane MRI Super-Resolution | AC: 3862
• DriftScope: Measuring The Hidden Effects of Diffusion Model Adaptation
• DriveFine: Refining-Augmented Masked Diffusion VLA for Accurate and Robust Driving | AC: 3791
• Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout
• DriveVA: Video Action Models are Zero-Shot Drivers
• DriveWeaver: Point-Conditioned Video Inpainting for Controllable Vehicle Insertion in Autonomous Driving Simulation
• Driving like yourself: A Benchmark for Closed-Loop Personalized End-to-End Autonomous Driving | AC: 4140
• DroneFINE: Domain-Aware Parameter-Efficient Fine-Tuning of Vision-Language Detectors for Drone Images | AC: 4719
• Drop-In Perceptual Optimization for 3D Gaussian Splatting | AC: 4997
• DRPO: Disentangling Demographic Bias from Rewards for Fair Diffusion Alignment | AC: 3700
• DRS-VPT: Directly Re-localizing in Scenes using a Vision and Point Transformer | AC: 5967
• DSAR: Dual-Stream Autoregressive Modeling of Temporal Cloth Dynamics for Photorealistic Animatable Avatars | AC: 5116
• DSH-Bench: A Difficulty- and Scenario-Aware Benchmark with Hierarchical Subject Taxonomy for Subject-Driven Text-to-Image Generation | AC: 5789
• DTI: Dynamic Trajectory Initialization for Generative Face Video Super-Resolution
• Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs | AC: 3144
• Dual-Anchoring: Addressing State Drift in Vision-Language Navigation | AC: 3365
• Dual-End Consistency Model
• Dual-Generalization-aware Minimization for Continual Fine-Tuning of Vision-Language Models | AC: 3400
• Dual-Margin Embedding for Fine-Grained Long-Tailed Plant Taxonomy | AC: 4527
• Dual-Output Multi-Exposure HDR Reconstruction via SDR Fusion and Gain Map Inverse Tone Mapping | AC: 4299
• Dual-Prior Guided Null-Space Learning with Mixture-of-Splines for Arbitrary Medical Slice Super-Resolution
• DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generation | AC: 3378
• DualCount: Structurally Consistent Density and Point Modeling for Zero-Shot Object Counting | AC: 4922
• DualDiff3D: Dual Structure-Appearance Diffusion Priors for Reliability-Enhanced 3D Gaussian Splatting | AC: 4077
• DualResPS: Dual-Resolution Photometric Stereo Using a Frame-Event Hybrid Camera | AC: 5614
• DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM Agents | AC: 4393
• DuoFlow: JVP-Free Finite-Difference Mean Flows for One-Step Image Generation | AC: 4139
• Dynamic Cluster Data Sampling for Efficient and Long-Tail-Aware Vision-Language Pre-training | AC: 5266
• Dynamic Image Prompt Adapter for Scalable Zero-shot Personalized Text-to-Image Generation | AC: 4423
• Dynamic Inverse Rendering for Enhanced Material-Lighting Decomposition | AC: 5513
• Dynamic World Generation Made Efficient | AC: 3754
• Dynamic-Robust Photometric–Semantic Reconstruction for Open-Vocabulary 3D Scene Understanding | AC: 5806
• DynEval: Holistic Evaluations of T2I Generative Models in the Wild | AC: 5431
• E-M3RF: An Equivariant Multimodal 3D Re-assembly Framework | AC: 4467
• E-MOTION: A Dataset for Event-Based Scene Flow Estimation with Independent Moving Objects | AC: 5887
• E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation
• E-VLA: Event-Augmented Vision-Language-Action Model for Dark and Blurred Scenes
• E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenes | AC: 4639
• EAGS: Error-Aware Gaussian Splatting with Dual-Confidence-Guided Modeling for Uncalibrated Driving Scenes | AC: 4526
• Early Estimation of Language to Latent Alignment in Diffusion Models | AC: 5787
• EatVid-Bench: A Multimodal Fine-Grained Eating Behavior Video Dataset | AC: 5037
• ECC: Encoder-Centric Corruption for Fine-Grained Vision in VLMs | AC: 5759
• ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion | AC: 3372
• ECHO: Ego-centric Modeling of Human-Object Interactions | AC: 3503
• EchoStyle: Unlocking High-Fidelity Video Stylization with Reverse Data Synthesis | AC: 4480
• EchoVLA: Robotic Vision-Language-Action Model with Synergistic Declarative Memory for Mobile Manipulation | AC: 5886
• ECoSim: Data Efficient Fine-Tuning for Controllable Traffic Simulation | AC: 3709
• EcoVideo: Entropy-Orchestrated Video Generation Paradigm in Cloud-Edge Dynamics | AC: 3747
• ECTraj: Enhanced Consistency Training for Multi-Agent Trajectory Prediction | AC: 5593
• Edit in 2D, Verify in 3D: Reinforcement Learning for Multi-view Consistent Scene Editing
• Edit3r: Instant 3D Scene Editing from Sparse Unposed Images | AC: 5649
• EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing | AC: 4044
• Editing Everything Everywhere All at Once | AC: 5825
• EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learning | AC: 3910
• Efficient and High-Quality Depth Estimation via Pixel-Space Diffusion with Linear Attention | AC: 3448
• Efficient Camera Pose Augmentation for View Generalization in Robotic Policy Learning | AC: 4217
• Efficient Document Tampering Localization with Multi-Level Discrepancy Features and Unified DCT-Quantization Embedding
• Efficient Quantization-Aware Adaptation for Visual Foundation Models | AC: 3766
• Efficient RGB-T Object Detection via Sparse Cross-Modality Fusion
• EffiDINO: Task-Specific Model Pruning via Gram Anchoring Subspace Consistency | AC: 3322
• EFlow: Fast Few-Step Video Generator Training from Scratch via Efficient Solution Flow | AC: 5488
• EGGS: Explicitly Granular 3D Gaussian Splatting via Luma-Aware and Volume-Preserving Attribute Factorization | AC: 5695
• EGM: Efficient Visual Grounding Language Models | AC: 5363
• Ego-Human Motion Prediction with 3D-Aware LLM | AC: 5287
• Egocentric Procedure Parsing | AC: 4540
• Egocentric World Model for Photorealistic Hand Object Interaction Synthesis | AC: 3737
• EgoCogNav: Cognition-aware Human Egocentric Navigation | AC: 5014
• EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving | AC: 5735
• EgoEverything: A Benchmark for Human Behavior–Inspired Long-Context Egocentric Video Understanding in AR Environment | AC: 4529
• EgoExo-Con: Exploring View-Invariant Video Temporal Understanding
• EgoExoMoCap: Distributed Human Motion Capture via Ego- and Exocentric Body Tracking from Head-Mounted Devices | AC: 3703
• EgoGVAE: Ego-body Mesh Reconstruction via Guided Variational Autoencoder | AC: 5117
• EgoMAN: Interaction-Structured Reasoning for Egocentric 3D Hand Trajectory Prediction | AC: 4078
• EgoPHI: Estimating 3D Hand-Object Contact and Force from Egocentric Vision | AC: 5255
• EgoPolice: A Benchmark for Egocentric Video Understanding in High-Stakes Police Body-Worn Camera Footage | AC: 3471
• EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding
• EgoSim: Egocentric World Simulator for Embodiment Interaction Generation | AC: 3429
• EgoTraj: Real-World Egocentric Human Trajectory | AC: 5974
• EgoVITA: Learning to Plan and Verify for Egocentric Video Reasoning
• EGVLR: Evidence-Grounded Vision–Language Reinforcement for Anomaly Reasoning | AC: 4683
• ELDiff: When Evidential Learning Meets Text-to-Image Diffusion | AC: 4090
• ELHINN: Unifying Dense Crowd Simulation Across Scales via Eulerian–Lagrangian Hydrodynamics | AC: 3887
• Eliciting Self-Verification in Multimodal Reasoning Agents with Reinforcement Learning | AC: 5534
• ELT: Elastic Looped Transformers for Visual Generation | AC: 5671
• ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval
• Em-Garde: A Propose-Match Framework for Proactive Streaming Video Understanding | AC: 3478
• EM3M: An Electron Micrograph Dataset for Microstructural Segmentation and Generation | AC: 4128
• EMAG: Self-Rectifying Diffusion Sampling with Exponential Moving Average Guidance | AC: 4178
• Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings | AC: 3466
• EmbedCopilot: Evaluating Vision-Language Models for Hardware-Aware Embedded System Development | AC: 5157
• Embedding Rotation Invariance for Provable Multi-Oriented Scene Text Recognition | AC: 5792
• EmbodiedHead: Real-Time Listening and Speaking Avatar for Conversational Agents | AC: 4476
• EmbodiedVAE: Disentangled Video VAE for Efficient and Controllable Embodied Manipulation | AC: 3749
• EMOSH: Expressive Motion and Shape Disentanglement for Human Animation
• EmoteGPT: 3D Human Facial Expression from Natural Language Descriptions | AC: 4789
• End-to-End Training for Autoregressive Video Diffusion via Self-Resampling | AC: 4177
• EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models | AC: 4214
• Enhanced Neural Video Representation Compression with High Scalability | AC: 3413
• Enhancing Alignment for Unified Multimodal Models via Semantically-Grounded Supervision | AC: 4741
• Enhancing Embodied Reasoning and Grounding by Novel View Synthesis | AC: 4036
• Enhancing Interpretability in CLIP with Optimal Transport-based Submodular Optimization for Ophthalmic Imaging | AC: 3746
• Enhancing Pretrained Model-based Continual Representation Learning via Guided Random Projection | AC: 4914
• Enhancing prompt-image alignment evaluations via cyclic mutual information maximization | AC: 3848
• Enlightening Photographic Style Transfer with a Self-Supervised Photographic Embedding | AC: 3866
• Entropy-Controlled Flow Matching
• Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models | AC: 3559
• Environmental Change Detection for Real-World Change Analysis | AC: 4329
• EoS-FM: Can an Ensemble of Specialist Models act as a Generalist Feature Extractor? | AC: 5453
• EpiBench: Benchmarking Multi-turn Research Workflows for Multimodal Agents | AC: 5661
• EPO: Boosting 3D Foundation Models with Edge-based Pose Optimization
• Equivariant Symmetry-Aware Head Pose Estimation for Fetal MRI | AC: 4519
• EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal
• EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders | AC: 5716
• Error-Driven Scene Editing for 3D Grounding in Large Language Models | AC: 5846
• EruDiff: Refactoring Knowledge in Diffusion Models for Advanced Text-to-Image Synthesis | AC: 3736
• ESC: Emotional Self-Correction for Reliable Vision-Language Models | AC: 5933
• ESCAPE: Episodic Spatial Memory and Adaptive Execution Policy for Long-Horizon Mobile Manipulation | AC: 4211
• Escaping the Low-Frequency Bias: Adversarial Frequency Perturbation for Generalisable Gaze Estimation | AC: 3195
• ESNE: Efficient Surface Normal Estimation for LiDAR Point Clouds with Sequential Modeling and Variability Guidance | AC: 5656
• ESTANet: Efficient Online Error Detection in Procedural Videos via Prediction Inconsistency | AC: 3427
• Estimating Individual Tree Height and Species from UAV Imagery | AC: 3491
• Estimating Velocity and Spin of Spherical Objects from Rolling-Shutter Image(s) | AC: 4548
• ET-SAM: Efficient Point Prompt Prediction in SAM for Unified Scene Text Detection and Layout Analysis
• ETCH-X: Robustify Expressive Body Fitting to Clothed Humans with Composable Synthetic Data | AC: 4461
• Evaluating and Enhancing Negation Comprehension in Remote Sensing MLLMs
• Evaluating and Understanding Model Editing for Medical Vision Language Models | AC: 5932
• Evaluating Reasoning Coherence in Video Generative Models with Text and Visual Hints | AC: 5161
• Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations
• EVAR: Edge Visual Autoregressive Models via Principled Pruning | AC: 3596
• EvDiff: High Quality Video with an Event Camera | AC: 4296
• EVEE: Event-Based Online Adaptation for Matching on Unknown Targets | AC: 4141
• Event Stream-based Sign Language Translation: A High-Definition Benchmark Dataset and A Novel Baseline | AC: 4859
• Event-based Gaze Control Systems for Real-time Spin Estimation in Professional Ball Games | AC: 5829
• Event-based Sparse-view Background-Oriented Schlieren Tomography | AC: 3210
• Event-driven Motion Deblurring via Trajectory-based Kernel Reconstruction | AC: 3517
• Event-Driven Video Generation
• Event-LiDAR: 3D Eventification for Efficient Point Cloud Processing | AC: 3577
• EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use | AC: 5586
• EventSpecPS: Photometric Stereo with Multispectral Reflectance Using an Event Camera | AC: 4677
• EventSTU: Event-Guided Efficient Spatio-Temporal Understanding for Video-LLMs | AC: 4847
• EventVGGT: Exploring Cross-Modal Distillation for Consistent Event-based Depth Estimation | AC: 5713
• Every Dog Has Its Day, Probably: A Balanced Synthetic Benchmark and Probabilistic Modeling for 3D Dog Pose Estimation | AC: 5296
• Evidence Triangulation for Multimodal Fact-Checking in the Wild | AC: 4874
• Evidence-Backed Video Question Answering | AC: 3691
• EvoTok: A Unified Image Tokenizer via Residual Latent Evolution for Visual Understanding and Generation | AC: 3849
• EvoVLA: Self-Evolving Vision-Language-Action Model | AC: 3353
• EvoWorld: A World-Model-Centric Framework for Continuous Self-Evolution of Modular Embodied Skills | AC: 5417
• Ex-Sim(3)-Reg: 2D-3D Correspondence Pruning via Extended Sim(3) Registration | AC: 4129
• Exclusivity-Guided Mask Learning for Semi-Supervised Crowd Instance Segmentation and Counting | AC: 3326
• Exo2EgoPolicy: Pose-Aligned Cross-View Policy Learning | AC: 3823
• Expert Weaving: Marrying Masked AutoRegressive and Diffusion Models for Unified Image Restoration | AC: 3361
• ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos | AC: 5581
• Experts-Guided Unbalanced Optimal Transport for ISP Learning from Unpaired and/or Paired Data | AC: 4471
• Explainability-aware Frustum Attack: Exposing Structural Vulnerabilities in LiDAR-Based 3D Object Detectors | AC: 5021
• Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks
• Explicit Semantic–Spatial Alignment for Open-Vocabulary Object Detection | AC: 3568
• Exploiting Local Flatness for Efficient Out-of-Distribution Detection
• Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation | AC: 5803
• EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon Reasoning | AC: 5607
• ExPLoRe: Expert Patch-Level Loss Routing for Multi-Objective Masked Image Modeling
• ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving
• Exploring Efficient Reasoning Segmentation with Small Language Models | AC: 4052
• Exposing Implicit Vulnerabilities in Text-to-Image Models via Adversarial Agentic Probing | AC: 4945
• Exposure Bias Can Alleviate Itself via Directional and Frequency Rectification in Flow Matching | AC: 5433
• Extending a Large View Synthesis Model for Multi-view Panoptic Segmentation | AC: 5627
• Extreme Face Super-Resolution through Identity Fitting and Decoupling | AC: 5492
• F⁴Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting | AC: 5023
• Fabric Image Demoiréing Benchmark from Synthesis to Restoration
• Face Anything: 4D Face Reconstruction from Any Image Sequence
• FaceArmor: A Universal Facial Image Protection Against Diffusion-Based Manipulations | AC: 5785
• FaceMoE: Mixture of Experts for Low-Resolution Face Recognition
• FaCT-GS: Fast and Scalable CT Reconstruction with Gaussian Splatting | AC: 3541
• Fair and Faithful: A Diffusion-Enhanced Dataset and Hybrid State-Space Mamba for Face Super-Resolution | AC: 5068
• FAIR: Feature-Augmented Implicit Regularization for AI-generated Fake Image Detection | AC: 5812
• FairSteer: Cross-Attention Steering Towards a Fairer Text-Guided Image Generation | AC: 4571
• Falcon: Functional Assembly and Language for Compositional Reasoning in X-ray | AC: 5443
• Fast and Accurate Image Restoration with Rank Enhanced Linear Attention | AC: 5618
• Fast and Compact 3D Gaussian Splatting with Polarized Opacity Prior | AC: 3772
• Fast and Flexible Robustness Certificates for Semantic Segmentation | AC: 4498
• Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding | AC: 3164
• Fast and Scalable LiDAR Data Generation for Autonomous Driving Simulation without Raycasting | AC: 5477
• Fast Dynamic Prototypes for Unsupervised Anomaly Detection and Localization | AC: 3350
• Fast Sam 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recovery | AC: 4084
• Fast Spatial Memory with Scalable Elastic Test-Time Training | AC: 4558
• Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance | AC: 4640
• FastSTAR: Spatiotemporal Token Pruning for Efficient Autoregressive Video Synthesis | AC: 5679
• FD\(^2\): A Dedicated Framework for Fine-Grained Dataset Distillation
• FDM-MFVT: Few-step Sampling Diffusion Model for Mask-Free Virtual Try-On | AC: 4709
• FDR-Occ: Factorized Dense Routing for Full-Spectrum 3D Occupancy Prediction | AC: 3765
• FeatTracker: Short- and Long-Range Temporal Feature Consistency for Robust Underwater Object Tracking | AC: 3939
• FED-Bench: A Cross-Granular Benchmark for Disentangled Evaluation of Facial Expression Editing | AC: 5905
• FedDO: Dynamic Client Optimization for Adaptive Federated Learning | AC: 5635
• FeDepth: Federated Learning for Depth Estimation under Robot Heterogeneity | AC: 4387
• FedLAS: Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration
• FedMental: Topology-Aware Federated Prototype Learning for Polymorphic Multimodal Psychiatry | AC: 4289
• FedNASP: Federated Vision-Language Navigation with Adaptive Step-wise Personalization | AC: 3468
• FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs
• FeVOS: Foresight Expression Video Object Segmentation
• Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples
• FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Arbitrary Images | AC: 4823
• Fidelity- and Perception-Aware Local Implicit Attention for Arbitrary-Scale Image Super-Resolution
• Fill2SR: Repurposing Inpainting Diffusion Transformers for Real-World Super-Resolution | AC: 4460
• FillGS: Filling Observation Gaps in 4D Gaussian Splatting via Viewpoint-Time Selection and Generative Refinement | AC: 3622
• FILT3R: Latent State Adaptive Kalman Filter for Streaming 3D Reconstruction | AC: 4732
• Finding Highlight Images In Your Albums:From Benchmark To MLLM | AC: 5026
• FindingDory: A Benchmark to Evaluate Memory in Embodied Agents | AC: 4986
• Fine-Grained Text-to-Video Retrieval for Camera-Trap Data | AC: 5474
• FineEdit: Fine-Grained Image Edit with Bounding Box Guidance | AC: 4620
• FingerCap: Fine-grained Finger-level Hand Motion Captioning | AC: 3868
• Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models | AC: 5335
• Fisher-Routed Mixture of Experts for Federated Class-Incremental Learning | AC: 4485
• Fisheye3R: Adapting Unified 3D Feed-Forward Foundation Models to Fisheye Lenses | AC: 4264
• FitControler: Toward Fit-Aware Virtual Try-On | AC: 4018
• FixAnything: 3D-Consistent Rendering Refinement via Video Generative Priors | AC: 5531
• Fixed Reality, Diffused Possibility: Disentangling Stochastic and Deterministic Latent for Cluttered Grasping | AC: 4380
• Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models | AC: 4046
• Flash-DD: An Ultra Parameter-Efficient Approach to Dataset Distillation | AC: 4697
• Flash-Refine: Frustum-Guided Local Incremental Learning for Efficient 3D Gaussian Splatting Completion | AC: 5936
• FlashBEV: Fast and Memory-Efficient Exact BEV Transformation with IO-Awareness | AC: 5030
• FlashVLM: Text-Guided Visual Token Selection for Large Multimodal Models | AC: 4782
• FLEG: Feed-Forward Language Embedded Gaussian Splatting from Any Views via Compact Semantic Representation | AC: 5168
• FlexAM: Flexible Appearance-Motion Decomposition for Versatile Video Generation Control | AC: 4328
• FlexiAvatar: Unified 3D Gaussian Human Avatars Under Arbitrary Body Visibility | AC: 3675
• Flexible Control of 3D CT Generation via Text and Semantically-Defined Segmentation Prompts | AC: 3589
• FlexiBrain: Resolution-Agnostic Voxel-Level Encoding for Native fMRI | AC: 3953
• FLM-Occ: Feed-forward Likelihood Maximization for Efficient Indoor Occupancy Prediction
• Flow Straight to Reality: Perceptually Consistent Flow Matching for Efficient Image Restoration | AC: 5358
• Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flow | AC: 5342
• FlowDec: Temporal Conditional Flow Decorruptor for Robust Continuous Vision-Language Navigation
• FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generation
• FlowFace: Rectifying Identity Conditioning with Riemannian Geometry for Face Generation | AC: 3634
• FlowLess: Controlling Abstract Image Generation | AC: 5883
• FMA-Net++: Motion- and Exposure-Aware Joint Video Super-Resolution and Deblurring
• Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning | AC: 5359
• Focusing on What Matters: Saliency-Harnessing Accurate Routing for Diffusion MoE
• Follow-Your-Mind: Towards Inversion-Free Brain-Driven Visual Context Synthesis and Editing | AC: 3632
• Following Motion for Sequential Modeling in Video Frame Interpolation | AC: 4342
• Following the Flow: Advection-Consistent Modeling for Event-based Small Object Detection
• FontCopilot: Towards Generalist Multimodal Large Language Models for Holistic Chinese Font Engineering | AC: 3769
• Forecasting Animal Motion | AC: 3230
• ForeSea: AI Forensic Search with Multi-modal Queries for Video Surveillance | AC: 3832
• Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-View Videos | AC: 3899
• Forget, Anticipate and Adapt: Test Time Training for Long Videos
• Foundation Model Selection for Remote Sensing via a Constraint-Aware Agent | AC: 5448
• Foundation-Guided Representation Alignment for Multimodal Medical Image Registration | AC: 4413
• FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry | AC: 3189
• FoundDP: Revisiting Weak Disparity Observability in Dual-Pixel Depth Estimation | AC: 4903
• FoundYou: A Unified Model for Personalized Segmentation and Retrieval | AC: 3520
• Fourier Compressor: Frequency-Domain Visual Token Compression for Vision-Language Models | AC: 3240
• Fourier Self-Supervision for Fine-Grained Generalized Category Discovery | AC: 5739
• Fourier Splatting: Generalized Fourier encoded primitives for scalable radiance fields | AC: 5499
• Foveated Reasoning: Stateful, Action-based Visual Focusing for Vision-Language Models | AC: 3608
• FPicker: Topology-Guided Evolution for Filament Tracing in Low-SNR Microscopy | AC: 3758
• Fragmented Text Is Insufficient for Image Representation: Fine-Grained Correspondence in Multimodal Dataset Distillation | AC: 3895
• Frames2Residual: Spatiotemporal Decoupling for Self-Supervised Video Denoising | AC: 3163
• Free-Lunch Augmentation by Revisiting Diffusion-Based Data Generation for Cross-Domain Few-Shot Object Detection | AC: 5687
• Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction | AC: 3583
• Free‑CD: Probabilistically Decoupled Training-Free Open-Vocabulary Change Detection with Resolution-Invariant Feature Inversion | AC: 3392
• FreeFlow: A Bias-free Hierarchical Transformer for Optical Flow Estimation | AC: 3994
• FreeGen: Feed-Forward Reconstruction–Generation Co-Training for Free-Viewpoint Driving Scene Synthesis | AC: 3958
• FreeMEF: 可灵活处理任意帧数的多曝光融合Transformer
• FreeSwim: Revisiting Sliding-Window Attention Mechanisms for Training-Free Ultra-High-Resolution Video Generation | AC: 3869
• Freqformer: Image-Demoiréing Transformer via Effective Frequency Decomposition | AC: 3223
• FreqOrtho-SR: Frequency-Guided Orthogonal Expert Learning for Real-World Image Super-Resolution
• FreqPhys: Repurposing Implicit Physiological Frequency Prior for Robust Remote Photoplethysmography | AC: 3960
• Frequency Director: Learnable Mixture of Frequency Experts for Unified Concealed Scene Segmentation | AC: 4302
• From Blobs to Spokes: High-Fidelity Surface Reconstruction via Oriented Gaussians | AC: 5943
• From Draft to Draft-Free: One-Step Video Object Removal via Privileged Distillation and Fast Planting | AC: 4354
• From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for Video Generative Models | AC: 4366
• From Gaze to Meaning: An AI Agent for Unified Zero-Shot Grounding and Explanation | AC: 5517
• From Hallucination to Grounding: Diagnosing Visual Spatial Intelligence via CRISP
• From Illusion to Intention: Visual Rationale Learning for Reliable Evidence Acquisition | AC: 5432
• From Local Geometry to Global Pseudo-Labeling for Robust Positive–Unlabeled Learning under Covariate Shift | AC: 5916
• From Local to Global: A Progressive Reconstruction Network for Diffractive Snapshot Spectral Imaging | AC: 3979
• From Local Windows to Adaptive Candidates via Individualized Exploratory: Rethinking Attention for Image Super-Resolution | AC: 3355
• From Macro to Micro: Benchmarking Microscopic Spatial Intelligence on Molecules via Vision-Language Models | AC: 5210
• From Minimal Clinical Prompts to 3D: Spacing-Aware Prompt Propagation for Multimodal Prostate Lesion Segmentation in bpMRI | AC: 4544
• From Multi-Resolution Cells to Gigapixel Whole Slide Images Foundation Model for Computational Pathology | AC: 4422
• From Noise to Events: Conditional Diffusion for Event Data Augmentation | AC: 4025
• From One-to-One to Many-to-Many: Dynamic Cross-Layer Injection for Deep Vision-Language Fusion | AC: 5248
• From Open Loop to Closed Loop: A Test-Time Iterative Optimization Framework for Reference-Consistent Image Generation | AC: 3857
• From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation | AC: 4492
• From Perspective to Fisheye Depth Estimation and Open-Vocabulary Segmentation | AC: 4568
• From Phase to Phenomenon: Self-Supervised Learning of Subsurface Scattering with Minimal Phase-shift Inputs
• From Predictions to Embeddings: Dual Knowledge Distillation for Instance-Dependent Partial Label Learning | AC: 3786
• From Reasoning to Pixels: Grounded Medical Multimodal LLMs for VQA and Segmentation | AC: 5720
• From Reconstruction to Decision: A Post-Encoder Plug-in Adapter for Curvilinear Segmentation
• From Script to Shot: A Benchmark for Grounding Screenplays in Movies | AC: 5093
• From smooth to sharp: Frequency-Decoupled Latent Optimization for Realistic Image Generation | AC: 3716
• From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space | AC: 3460
• From Synchrony to Sequence: Exo-to-Ego Generation via Interpolation | AC: 5245
• From Visual Primitives to Semantic Masks: Fine-Grained Visual-Linguistic Alignment for Open-Vocabulary Remote Sensing Image Segmentation | AC: 3638
• Frozen CLIP Priors for Robust Self-Supervised Poisson Inverse Problems | AC: 5010
• FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation
• FSD-Net: Foundation-Guided Spatiotemporal Distillation for Video Polyp Segmentation | AC: 3627
• FSDC-DETR: A Frequency-Spatial Domain Collaborative DETR for Small-Object Detection | AC: 4611
• FST-SAM3: Taming SAM~3 with Frequency-Spatio-Temporal Refinement for Video Polyp Segmentation | AC: 5158
• FuDU: A Fuzzy Dual-dimension Uncertainty Framework for Streaming Active Learning in Industrial Defect Detection | AC: 5087
• Fully Rotation-Equivariant Spectral-Spatial Learning for Multispectral Object Detection | AC: 3207
• FUMO: Prior-Modulated Diffusion for Single Image Reflection Removal
• FUSE: A Flow-based Mapping Between Shapes | AC: 5871
• FUSE: Filter-Free Unified Spatiotemporal Estimation of SpO2 via Wave-Transport Modeling | AC: 5379
• FusionTrack: Collaborative Multi-Object Tracking with Arbitrary Multi-UAVs | AC: 4325
• G-ZAP: A Generalizable Zero-Shot Framework for Arbitrary-Scale Pansharpening | AC: 4894
• G2P: Gaussian-to-Point Attribute Alignment for Boundary-Aware 3D Segmentation
• G3AFT: Glance Guided Gradient Aligned Fine-Tuning for Visual Autoregressive Models | AC: 4720
• GAIA: A Data Flywheel System for Training GUI Test-Time Scaling Critic Models
• GaINeR: Geometry-Aware Implicit Neural Representation for Image Editing | AC: 3570
• GAINS: Gaussian-based Inverse Rendering from Sparse Multi-View Captures | AC: 4584
• GameWorlds: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents | AC: 5086
• GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models | AC: 3455
• GAP-Track: Bridging the Resolution Gap for Cross-Resolution RGBT Tracking | AC: 3545
• GARDEN: Gravity-Aligned Reconstruction of Disentangled ENvironments from RGB images | AC: 3985
• Gaussian Belief Propagation Network for Depth Completion
• Gaussian Volumetric Representation for Efficient Shear–Warp Visualization | AC: 5673
• GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation
• GaussianLens: Localized High-Resolution Reconstruction via On-Demand Gaussian Densification | AC: 4560
• Gaussians on Fire: High-Frequency Reconstruction of Flames | AC: 4870
• Gaze-to-text Generation: Beyond Categorical Decoding of Human Attention | AC: 3839
• GCMRD: Global Consistency Multi-teacher Robustness Distillation | AC: 3744
• GEAR-Seg: A Grounded Explainable Agent for Reasoning Segmentation and Data Engine | AC: 5462
• GeCo: Evaluating Geometric Consistency for Video Generation via Motion and Structure | AC: 4068
• GEM: Generative Supervision Helps Embodied Intelligence | AC: 3349
• GeMoE: Gating Entropy is All You Need for Uncertainty-aware Adaptive Routing in MoE-based Large Vision-Language Models | AC: 5568
• Gen2Balance: Generative Balancing for Long-Tailed Video Action Recognition
• GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherence
• GenAgent: Scaling Text-to-Image Generation via Agentic Multimodal Reasoning | AC: 3970
• Gender Bias in Vision-Language In-Context Learning | AC: 5561
• General Incomplete Multimodal Learning via Dynamic Quality Perception | AC: 5895
• General Self-Calibration with Varying Intrinsics | AC: 3851
• Generalizable Neural Reconstruction of High-Fidelity Surfaces via Sparse Volumetric Representations | AC: 4763
• Generalization and Memorization in Rectified Flow | AC: 5520
• Generalize LMMs to Versatile Visual Modalities via Fabricated Modality Synthesis | AC: 4864
• Generalized Biomedicine Discovery | AC: 4610
• Generating a Paracosm for Training-Free Zero-Shot Composed Image Retrieval
• Generating Multi-view Adversarial Examples for Visual Geometry Grounded Transformer | AC: 4361
• Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding | AC: 3262
• Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos | AC: 4241
• Generative Lane Topology Reasoning via Autoregressive Model with Geometry Prior
• Generative Manifold Distillation: Aligning Restoration Trajectories with the Natural Image Prior | AC: 5995
• Generative Refinement Network for Visual Synthesis | AC: 3639
• Generative Relightable Avatars | AC: 4531
• GenHOI: Generalized Hand-Object Pose Estimation with Occlusion Awareness | AC: 4706
• GenLCA: 3D Diffusion for Full-Body Avatars from In-the-Wild Videos | AC: 3890
• GenRecal: Generation after Recalibration from Large to Small Vision-Language Models | AC: 4989
• GenSP: Consistent Spherical Parameterization via Learning Shape Generative Models
• GEO-Detective: Unveiling Location Privacy Risks in Images with LLM Agents | AC: 5191
• Geo-DPO: Aligning Semantic Intent with Geometry for 3D Affordance Segmentation | AC: 5931
• Geo-ID: Test-Time Geometric Consensus for Cross-View Consistent Intrinsics
• GeoBrowse: A Geolocation Benchmark for Agentic Tool Use with Expert-Annotated Reasoning Traces | AC: 3259
• GeoCFM: Positive-Only Conditional Flow Matching for Mineral Occurrence Sampling | AC: 5907
• GeoDetect: Geometric Adversarial Detection for VLPs | AC: 3531
• GeoEdit: Geometry-Aware Object Editing via Dual-Branch Denoising
• GeoFlow: Efficient Driving Video Generation via Geometry-Aligned Priors | AC: 5297
• Geometric Context Transformer for Streaming 3D Reconstruction | AC: 3493
• Geometric Distillation from Rectified Stereo: Leveraging Epipolar Cues for Monocular Depth | AC: 3586
• Geometric Foundation Model Distillation for Efficient Lunar 3D Reconstruction | AC: 4419
• Geometric Gradient Rectification for Safe Open-Set Semi-Supervised Learning
• Geometric Probing for Isotropic Optimization Manifold in Sparse-View 3D Gaussian Splatting | AC: 5303
• Geometric Regularization for Long-Tailed Semi-Supervised Learning via Gaussian Feature Bridges | AC: 4113
• Geometry Grounding: Elevating Blind Distortion Correction with 3D Structural Priors | AC: 5203
• Geometry-Anchored Transport Framework for Exemplar-Free Class-Incremental Learning
• Geometry-Aware Single-Image 4D Synthesis via Dense Trajectory Generation | AC: 3965
• Geometry-Aware Spatio-Temporal Context Modeling for 4D Occupancy Forecasting | AC: 5843
• Geometry-Aware Style Transfer in 3D Gaussian Splatting
• Geometry-Aware Visual Representation for Remaining Useful Life Prediction | AC: 5418
• Geometry-Preserving Image Generation for 6D Object Pose Estimation | AC: 5858
• Geometry-Preserving in 3D Gaussian Splatting for LiDAR-Camera Extrinsic Calibration
• Geometry-Propagated Gaussian Splatting for Aerial Sparse Novel View Synthesis | AC: 5360
• GeoMix: Descriptor-Free Visual Localization via Global Context and Multi-Detector Training | AC: 4739
• GeoNVS: Geometry Grounded Video Diffusion for Novel View Synthesis
• GeoSolver: Scaling Test-Time Reasoning in Remote Sensing with Fine-Grained Process Supervision | AC: 3860
• GeoV2V: Geometry-Grounded Video Diffusion Model for Driving Scene Generation | AC: 5219
• GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generation | AC: 3217
• GH-ESD: Grounded Hypothesis-Driven Error Slice Discovery for Instance-Level Vision Tasks | AC: 4881
• GIDE: Unlocking Diffusion LLMs for Precise Training-Free Image Editing | AC: 5051
• GimbalDiffusion: Gravity-Aware Camera Control for Video Generation | AC: 3735
• GKDT: General Keypoint Detection Transformer
• Glance: Accelerating Diffusion Models with 1 Sample | AC: 3879
• GLARE: Towards Generalizable Detection of Latent Diffusion Images with Global-Local Reconstruction Error | AC: 4623
• GlassGS: Geometry and Concept-Aware 3D Gaussian Splatting for Reflective Enclosures | AC: 4381
• Global Graph-Validated Optimization for VLM-based 3D Indoor Scene Generation | AC: 4122
• Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection | AC: 5200
• Global Pose Control for Generative View Synthesis in Normalized Object Coordinate Space | AC: 3467
• Global-Local Dual Perception for MLLMs in High-Resolution Text-Rich Image Translation | AC: 5236
• GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens | AC: 5256
• GMODiff: One-Step Gain Map Refinement with Diffusion Priors for Efficient HDR Reconstruction | AC: 5422
• GO-Renderer: Generative Object Rendering with 3D-aware Controllable Video Diffusion Models | AC: 3257
• Going Deep: Deep Visual Prompting with LoTeP | AC: 5386
• Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing | AC: 3375
• GoodQ: 利用现成生成模型实现目标检测器的零样本量化
• GoStop: Reinforcement Learning for Adaptive Temporal Aggregation in Event-Based Feature Tracking | AC: 4118
• GR-GRPO: Graph-Diffused Credit for Autoregressive Image RL Alignment | AC: 4453
• GRADE: Benchmarking Discipline-Informed Reasoning in Image Editing | AC: 3710
• Gradient sparsity regularization for training unlearning-compatible models | AC: 4505
• GradingBench: Evaluating End-to-End Compositional Reasoning of MLLMs for Automated Exam Grading | AC: 4168
• GRAFT: Geometric Refinement and Fitting Transformer for Human Scene Reconstruction
• GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models | AC: 4694
• Granular Semantic Cognition for Visible-Infrared Person Re-Identification | AC: 3666
• Graph-GSReg: Leveraging 3D Scene Graphs for Gaussian Splatting Registration | AC: 5375
• GraphCPD: Coherent Point Drift for Point Cloud Registration via Graph Signal Processing | AC: 3792
• GraphVid: Interactive Graph-Controllable Video Generation | AC: 4972
• Grasp-Oriented Non-Prehensile Manipulation via Learning a Graspability Field | AC: 3490
• GRE-Diff: Gaussian Room Embeddings for Structured Layout Diffusion | AC: 3948
• GRF-Recon: Global Ray-Field Optimization for Long-Sequence Feed-forward Reconstruction | AC: 3776
• GridFlow: Structured Latent Flow for Seamless City-Scale 3D Point Cloud Generation | AC: 4452
• GridVQA-X: A Diagnostic Framework for Evaluating Multimodal Explainability Methods | AC: 5894
• Gripper-aware Vision Language Action Models | AC: 4272
• Ground3D-LMM: Fine-Grained 3D Point Grounding and Spatial Reasoning with LMM | AC: 4236
• Grounding Sim-to-Real Generalization in Dexterous Manipulation: An Empirical Study with Vision-Language-Action Models | AC: 5392
• Grounding World Simulation Models in a Real-World Metropolis | AC: 4936
• GroundingAnomaly: Spatially-Grounded Diffusion for Few-Shot Anomaly Synthesis | AC: 3947
• GroundSet: A Cadastral-Grounded Dataset for Spatial Understanding with Vector Data | AC: 4087
• Group3D: MLLM-Guided Semantic Grouping for Open-Vocabulary 3D Object Detection | AC: 4759
• GrowFields: Compositional 4D Neural Fields for Topology-Changing Plant Growth | AC: 5398
• GryphOne: Symbol-Aware Masked Diffusion for Structural Refinement in Offline Handwritten Mathematical Expression Recognition
• GTR: Guide-Then-Refine Token Compression for Training-Free Acceleration of Video-LLMs | AC: 5095
• Guardrail-Agnostic Societal Bias Evaluation in Large Vision-Language Models | AC: 3628
• Guide, Think, Act: Interactive Embodied Reasoning for Vision-Language-Action Model | AC: 4448
• GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation
• GuideMe: Benchmarking Multi-Domain Task Guidance and Intervention in Streaming Video | AC: 3337
• Guiding the Blind: Generalizing GUI Agents to Unseen Websites via Multimodal Tutorials | AC: 4245
• H-Adapter: Pose-Robust Hairstyle Transfer via Attention-Derived, Source-Aligned Hair Masks
• h-Flow: Flexible Flow-based Image Editing via Doob's h-Transform | AC: 5419
• H-SFP: Hierarchical Federated Learning with Decoupled Split-Model Prototyping | AC: 5748
• H2SVC: Head-aware Heterogeneous Streaming Video Cache for Online Video Understanding | AC: 5230
• Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting | AC: 3787
• HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving | AC: 3249
• HairOrbit: Multi-view Aware 3D Hair Modeling from Single Portraits | AC: 3893
• HairWeaver: Few-Shot Photorealistic Hair Motion Synthesis with Sim-to-Real Guided Video Diffusion | AC: 4554
• HandSCS: Structural Coordinate Space for Animatable Hand Gaussian Splatting | AC: 3877
• Harnessing SSL for Segmentation in 3D Microscopy with Noisy Labels and Hard Patches | AC: 4987
• HART: High-Resolution Annotation-Free Reasoning Technique through a Closed-loop Framework | AC: 5808
• HAS: Highlight-guided Attention Steering for Multimodal LLM Video Summarization | AC: 5965
• HASSL: Hierarchy-Aware Self-Supervised Learning Framework for Single Cell Microscopy | AC: 5169
• HAT-4D: Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration
• HCSU: A Dataset and Benchmark for Fine-Grained Historical Calligraphy Style Understanding | AC: 5409
• Head Avatars with Dynamic Explicit Hair | AC: 4281
• Heat Kernel Textures -- the Geodesic Gaussians That Do Not Splat | AC: 3652
• HER-Count: Learning Hyper-Exemplar Representation for Generalized Zero-Shot Object Counting | AC: 5155
• HERO: Enhancing Multimodal Faithfulness via Dynamic Entropy-Aware Reinforcement Learning | AC: 3620
• HERO: Heterogeneous Evidential Robust Object-Level Collaborative Perception | AC: 5572
• HHA: Hierarchical Hyperbolic Constraints for Imperceptible Point Cloud Attacks | AC: 4287
• Hi-DiT: Hybrid Latent-Pixel Diffusion Transformer for Image Generation | AC: 4794
• Hi-Nav: Hierarchical Framework for Continuous Vision-Language Navigation via Map Guidance and Waypoint Reasoning | AC: 5599
• HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising | AC: 3701
• HiChor: Hierarchical Choreography Generation from Pop Music with Choreographic Primitives | AC: 4335
• HIDA: A Human-Intuition-Guided Depth-Aware Framework for Zero-Shot Amodal Segmentation | AC: 3289
• HieDG: A Hierarchical Discrete Geometry-Guided Framework for Multi-Animal Tracking
• Hierarchical 3D Scene Graph Construction and Belief-based Planning for Semantic Navigation
• Hierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spaces | AC: 4229
• Hierarchical Hyperbolic Representation Learning for Aerial-Ground Person Re-Identification | AC: 3795
• Hierarchical Prompt Injector for Domain Generalization Segmentation | AC: 4750
• Hierarchical Spatial and Channel Aggregation for Cross-domain Few-shot Segmentation
• Hierarchical Style Aggregation for Versatile Chinese Handwriting Generation | AC: 3883
• High-Resolution Artwork Outpainting with Global Blueprint Guidance and Layout Control | AC: 5103
• High-speed Imaging through Turbulence with Event-based Light Fields | AC: 3748
• High-Throughput Event-Based Feature Detection and Tracking on an Embedded CPU | AC: 3601
• HighlightBench: Benchmarking and Diagnosing Markup-Driven Table Reasoning in Scientific Documents | AC: 5369
• HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-training
• HiPolicy: Hierarchical Multi-Frequency Action Chunking for Policy Learning | AC: 5381
• HippoCamp: Benchmarking Contextual Agents on Personal Computers | AC: 4004
• HiReFF: High-Resolution Feedforward Human Reconstruction from Uncalibrated Sparse-View Video | AC: 5349
• Histocomponent-driven Universal Model for Virtual Immunohistochemistry Multiplex Staining via Joint Manifold Evolution | AC: 3642
• Histogram-constrained Image Generation
• Histopathology Multi-modal Embedding for Pathology Composed Retrieval
• History-Aware Transformation of ReID Features for Multiple Object Tracking | AC: 4421
• HitMem: Hierarchical Temporal 3D Memory with Multi-Modal Context-Aware Retrieval for Dynamic Environments | AC: 5322
• HIVE: Understanding Post Hallucination Reasoning in Vision Language Models | AC: 4116
• HLRAD: High-dimensional Latent Representation for Unified Anomaly Detection | AC: 5190
• HNDiff: Haze-Noise Diffusion for Image Dehazing | AC: 3648
• HO-Flow: Generalizable Hand-Object Interaction Generation with Latent Flow Matching | AC: 3494
• HOIMask: Towards Generative Masked Modeling for Human Object Interaction Generation | AC: 4324
• Holistic Optimal Label Selection for Robust Prompt Learning under Partial Labels | AC: 3959
• Holo-Captioning: A Comprehensive Textual View of 3D Scenes | AC: 3445
• Holo360D: A Large-Scale Real-World Dataset with Continuous Trajectories for Advancing Panoramic 3D Reconstruction and Beyond | AC: 4047
• HoloTetSphere: Unified TetSphere Mesh Reconstruction for Physical Simulations | AC: 5717
• HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task | AC: 5762
• Honey, I Shrunk the Arc de Triomphe! | AC: 3739
• Horizon3D: Sparse Radar-Camera Fusion for Long-Range 3D Perception in Autonomous Driving
• HorizonRelight: Relighting Long-horizon Videos Consistently via Diffusion Transformers | AC: 4707
• How Far Are Video Models from True Multimodal Reasoning? | AC: 5699
• How Far Are Vision-Language Models from Constructing the Real World? A Benchmark for Physical Generative Reasoning | AC: 3659
• How to Teach Large Multimodal Models New Skills | AC: 4547
• HQ-DM: Single Hadamard Transformation-Based Quantization-Aware Training for Low-Bit Diffusion Models | AC: 5402
• HRDiT: Training-Free High-Resolution Image Generation with Off-the-Shelf Diffusion Transformer Models | AC: 4252
• HSD: Training-Free Acceleration for Document Parsing Vision-Language Models with Hierarchical Speculative Decoding
• HSDF-Lane: Height-Aligned Signed Distance Field with Semantic Lane Prior for 3D Lane Detection
• HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human–Scene Interactions | AC: 3313
• HUGE-Bench: A Benchmark for High-Level UAV Vision-Language-Action Tasks | AC: 4630
• Human Mesh Modeling for Anny Body | AC: 3422
• Human-Level Accuracy, Non-Human Strategies: Revealing Model-Human Divergence in Video Physical Reasoning | AC: 3722
• Humanoid Whole-Body Manipulation via Active Spatial Brain and Generalizable Action Cerebellum | AC: 3751
• HumanOmni-Speaker: Identifying Who said What and When | AC: 4632
• HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark | AC: 4926
• HVA-Fusion:Hierarchical Velocity-Aware 4D Radar-LiDAR Fusion for Robust 3D Object Detection | AC: 5272
• HVGCD:Rethinking Generalized Category Discovery through Hypothesis–Verification | AC: 4898
• Hybrid Advantage Estimation with Unified Critic for VLM Agentic Reinforcement Learning | AC: 3403
• Hybrid-LUT: Channel-Aware Hybrid Lookup Table and Filtering for Efficient Image Restoration | AC: 4755
• HybridSim: A Physics–Learning Hybrid Digital Twin for mmWave Human Sensing | AC: 5032
• HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding
• HyLaR: Hybrid Latent Reasoning with Decoupled Policy Optimization
• Hyper-Network Neural Functional Maps for Unsupervised Robust 3D Shape Matching | AC: 4035
• Hyperbolic Hierarchical Clustering for Visual Representation Learning | AC: 3152
• Hypothesis Graph Refinement: Hypothesis-Driven Exploration with Cascade Error Correction for Embodied Navigation | AC: 5207
• i-Design: Step-by-Step Graphic Layout Design with Progressive Aesthetic Policy Optimization | AC: 5750
• IACD: Iterative Adversarial Collaborative Detection via Dual-Perspective Blind Spot Discovery | AC: 5903
• IC-World: In-Context Generation for Shared World Modeling | AC: 4031
• ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning | AC: 3998
• Ice Cloud Geometry Retrieval with Calibrated Uncertainty from Passive Satellite Imagery | AC: 5781
• ICLAgent: Integrated Circuit Footprint Geometry Labeling via LMM-empowered Multi-Agent Framework | AC: 5260
• IConE: Batch Independent Collapse Prevention for Self-Supervised Representation Learning | AC: 4428
• ID-LoRA: Identity-Driven Audio-Video Personalization with In-Context LoRA | AC: 3277
• ID-PreFeR: ID-Preserving Face Restoration with Mixed Data Quality | AC: 3808
• IDeaL: Data-Free Multi-Teacher Distillation via Improved Dead Leaves | AC: 3438
• Identifiable Gated Residual Personalization for Federated Parameter-Efficient Fine-Tuning | AC: 5020
• Identifying and Resolving Pitfalls of Knowledge-Based VQA Benchmarks: Auditing, Repairing, and Augmenting
• Identity-Preserving Human Reconstruction from a Single Image via 3D Token Inference | AC: 3236
• If It's Not Efficient, It's Not Usable: Real-Time OOD Detection with Latent De-Biasing and High-Quality Negative Samples | AC: 4106
• Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation | AC: 4757
• Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models | AC: 3515
• iMED: A Multi-Endoscope Dataset for Surgical 3D Perception | AC: 5902
• IMMoE: Incomplete Multi-View Anomaly Detection via Mixture of View Experts Fusion | AC: 3989
• Implicit Neural Representation for Spherical Harmonics Reconstruction of Motion-Corrupted Fetal Diffusion MRI | AC: 4535
• Importance-Aware Low-Rank Distillation of Diffusion Transformers | AC: 4565
• Improved Immiscible Diffusion: Accelerating Diffusion Training by Reducing Miscibility | AC: 5637
• Improving Adversarial Robustness by Mitigating Instability through Relearning | AC: 5743
• Improving Adversarial Robustness via Activation Amplification and Attenuation
• Improving Image-to-Image Translation via a Rectified Flow Reformulation | AC: 5655
• Improving Knowledge Distillation Under Unknown Covariate Shift Through Confidence-Guided Data Augmentation | AC: 4487
• Improving Reasoning in Vision-Language Models via Perception Verified Self-Training | AC: 4944
• Improving Sparse-View 3DGS Generalization via Flat Minima Optimization
• In-context Region-based Drag: Drag Any Region to Any Shape
• In-Context Sync-LoRA for Portrait Video Editing | AC: 4473
• Incentive Noise and Structural Prior Infusion for Multi-Modal Object Re-Identification | AC: 3598
• Incentivizing Vision Language Models to Search for Long Video Question Answering | AC: 5917
• InceptionGS: Generative Bootstrapping for Large-Scale Gaussian Splatting under Unstructured View Sampling | AC: 5029
• Inclusive Interactive Collisions for Multi-View Consistent Compositional 3D Generation | AC: 3923
• Incremental Online Scene Reconstruction by 3D Gaussian Triangulation | AC: 3228
• Indelible Backdoors: On the Limits of Post-Training Defenses | AC: 5639
• IndoorSplat: Enhanced Indoor Scene Reconstruction with Structured 2D Gaussian Splatting | AC: 5326
• Inductive Visual Logic for Few-Shot Out-Of-Distribution Adaptation in VLMs | AC: 3863
• Inference-time Motion Calibration for Video Generation | AC: 3884
• Inference-Time Scaling of Diffusion Models via Progressive Seed Pruning | AC: 3518
• Infinite Gaze Generation for Videos with Autoregressive Diffusion | AC: 5022
• Infinite-Homography as Robust Conditioning for Camera-Controlled Video Generation | AC: 4255
• InfiniteDance: Scalable 3D Dance Generation Towards in-the-wild Generalization | AC: 3684
• Information-Regularized Attention for Visual-Centric Reasoning
• InfraNet: Quality-Aware RGB Guidance for Infrared Object Detection | AC: 3873
• InnoText: A Unified Model for Visual Text Generation and Editing | AC: 3140
• InSeg: Interactive Refinement via Intent Propagation for Point Cloud Semantic Segmentation | AC: 5194
• InsertAnywhere: Geometrically Grounded and Optics-Aware Video Object Insertion | AC: 4205
• InSpace: Structure-Aware 3D Indoor Scene Generation from a Single 360° Image | AC: 4474
• InstaEdit: Instant Image Editing via Optimized Noise Prediction | AC: 5247
• Instance Segmentation as Tracking: A New Paradigm for Multi-Small-Object Tracking with Event Cameras | AC: 4777
• InstanceControl: Controllable Complex Image Generation without Instance Labeling | AC: 5105
• Instant Expressive Gaussian Head Avatars at Over 100 FPS | AC: 4074
• InstantHDR: Single-forward Gaussian Splatting for High Dynamic Range 3D Reconstruction | AC: 3662
• InstantRetouch: Personalized Image Retouching without Test-time Fine-tuning | AC: 5900
• InstaPano: Zero-shot Instance Layout Controlled Panorama Generation Via Global Attention Fusion | AC: 3956
• InstGS: Shared-Template Gaussian Instancing for Object-Redundancy-Free Rendering | AC: 4199
• InstrAct: Towards Action-Centric Understanding in Instructional Videos | AC: 5457
• Integrated Forward–Inverse Network for Reconstruction for Lensless Image Reconstruction | AC: 5659
• Interact3D: Compositional 3D Generation of Interactive Objects
• Interaction-Aware 4D Gaussian Splatting for Dynamic Hand-Object Interaction Reconstruction | AC: 4896
• InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars | AC: 3402
• InterEdit: Navigating Text-Guided 3D Dyadic Human Motion Editing
• Interference-Aware Continual Vision–Language Learning via Instance-Level Expert Routing | AC: 4918
• Intermediate Text Representation Guided Text-to-Image Generation for Enhancing One-and-Only Alignment
• InterPet4D: A Multimodal 4D Human-Pet Interaction Dataset for Pet Motion Generation | AC: 5889
• Interpretation-Oriented Cloud Removal via Observation-Anchored Residual Flow with Geo-Contextual Alignment | AC: 5775
• Intra-Class Consistency Guided Class-Agnostic Event Segmentation | AC: 3689
• Intrinsically Stable Spiking Neural Networks: Overcoming the Performance Barrier in the Absence of Batch Normalization
• InverseCrafter: Efficient Video ReCapture as a Latent Domain Inverse Problem | AC: 4456
• Invisible Shortcuts: Why Vision Encoders Know Your Camera | AC: 4431
• IoUCert: Robustness Verification for Anchor-based Object Detectors | AC: 5436
• IP-SAM: Rethinking Prompt-Conditioned Segmentation for Prompt-Absent Deployment | AC: 5354
• IQA-T1: Tool-based Visual Evidence Reasoning for Image Quality Assessment | AC: 4383
• IREU: Identity-Related Encoder-Only Unlearning for Customized Portrait Generation
• IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Generation | AC: 3976
• IRIS: Intersection-aware Ray-based Implicit Editable Scenes | AC: 3495
• Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussions | AC: 4950
• ISAC: Training-Free Instance-to-Semantic Attention Control for Multi-Instance Generation
• Isotropic Embedding Perturbations for Robust Vision Language Encoders | AC: 5764
• iSyncTab: Learning Cross-Modal Feature Sequencing for Image-Tabular Data via Neural Synchrony | AC: 5442
• Iterative Perceptual Alignment for VLMs via Deterministic Reconstruction Feedback | AC: 5795
• Iterative Refinement of Semantic and Spatial Representations for Open-Vocabulary Camouflaged Object Segmentation | AC: 5124
• JacobianAvatar: Temporally Consistent Semi-rigid Avatar Reconstruction from a Monocular Video | AC: 5137
• JanusMesh: Fast and Zero-Shot 3D Visual Illusion Generation via Cross-Space Denoising
• Joint Alignment and Distillation for Video Generation via Sample-Guided Distribution Matching | AC: 5704
• JoVA: Unified Multimodal Learning for Joint Video-Audio Generation and Editing | AC: 4518
• JSON: Jigsaw Self-play Optimization for Normalizing Flows | AC: 3623
• Jumping the Landing Phase: Noise Variance Matching Enables Accurate Few-Step Inversion | AC: 4842
• K-Mask: Kinematic-Aware Masked Modeling for Controllable Text-to-Motion Synthesis | AC: 5839
• KATANA: Knowledge-Aligned Topology-Aware Neural Agents for RL-Driven Vision-Language Model Compression | AC: 5897
• Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding | AC: 5468
• Keep Your Friends Close, and the Right Neighbours Closer: Disaster-Conditioned Kernel-Regularized Graph Attention for Building Damage Classification | AC: 5471
• Keep-or-Drop? Adaptive Tokenizer for Compact Video Representation | AC: 5142
• Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding | AC: 4438
• Kilometer-Vision: A New Frontier for Large-Scale Spatial Awareness in VLMs | AC: 5940
• KineBench: Benchmarking Embodied World Models via IDM-Free Kinematic Grounding | AC: 5861
• KineticGS: Momentum-driven Coherent 4D Gaussian Splatting for Monocular Dynamic Scene Reconstruction | AC: 4910
• Kirin: Animal Motion Generation from In-the-Wild Video | AC: 3829
• Kiroshi: An Agentic Perception System for High-Accuracy Image Parsing | AC: 3681
• KISS-GS: 3D Gaussian Splatting Compression Kept Simple | AC: 4959
• Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models | AC: 3841
• Knowledge-Centric Agents for Workflow Generation in ComfyUI | AC: 4258
• Label-Free Text Prototype Adaptation for Open Vocabulary Segmentation | AC: 5217
• LACON: Training Text-to-Image Model from Uncurated Data | AC: 3253
• LaGen: Towards Autoregressive LiDAR Scene Generation
• LaMP: Learning Vision-Language-Action Policies with 3D Scene Flow as Latent Motion Prior | AC: 3193
• LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents | AC: 4542
• LangLoc: “Tell Me What You See” | AC: 3831
• Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures
• Large-Scale Light Field Synthesis from Videos Enables Geometrically Consistent Bokeh Editing | AC: 4582
• LARY: A Latent Action Representation Yielding Benchmark | AC: 5045
• LASER: A Corrective Lens for LVLMs via Visual Attention Preservation and Sink Suppression | AC: 3352
• Last-Layer-Centric Feature Recombination: Unleashing 3D Geometric Knowledge in DINOv3 for Monocular Depth Estimation | AC: 4725
• Latent Fusion: Decoding Consolidated 3D Geometry from Feed-forward Geometry Transformer Latents | AC: 5466
• Latent Visual Diffusion Reasoning with Monte Carlo Tree Search
• LatentPilot: Scene-Aware Vision-and-Language Navigation by Dreaming Ahead with Latent Visual Reasoning | AC: 3186
• LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion
• LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning | AC: 5864
• LaVPR: Benchmarking Language and Vision for Place Recognition | AC: 4546
• LaxMotion: Rethinking Supervision Granularity for 3D Human Motion Generation | AC: 4736
• Layer-Aware Video Composition via Split-then-Merge | AC: 4053
• Layer-Specific Prompt Fusion Discovery via Differentiable Search in Vision Foundation Models
• Layering Virtual Try-On | AC: 4142
• LayerVerse: Finding the Sweet Spot for KV-Injection in Training-Free Image Editing | AC: 4504
• Layout-Conditioned Autoregressive Text-to-Image Generation via Structured Masking
• LDC-MTL: Balancing Multi-Task Learning through Scalable Loss Discrepancy Control | AC: 5570
• LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detection
• LEAP-VLA: Latent-Enhanced Action Prototyping via Continuous Residual Latent Spaces for Vision-Language-Action Models | AC: 3297
• Learn Once, Edit Anywhere: Visual Direction Transfer for Diffusion Models
• Learn to Rank: Visual Attribution by Learning Importance Ranking | AC: 3507
• Learn to See the Unseen in Low-light Spike Streams | AC: 4185
• Learning 1-Bit LiDAR-based Localization with Auxiliary Objective | AC: 4181
• Learning Accurate Segmentation Purely from Self-Supervision | AC: 3867
• Learning Active Perception for Pixel-Space Reasoning via Visual-Intent Stratified GRPO | AC: 3757
• Learning Consistency in Reward Modeling for Multi-Modal Reasoning | AC: 5859
• Learning Ego-Centric BEV Representations from a Perspective-Privileged View: Cross-View Supervision for Online HD Map Construction | AC: 5994
• Learning Egocentric Cues from Exocentric Video using Privileged Egocentric Supervision | AC: 3825
• Learning from Adversity: Semantic-Aware Mask Refinement through Adversarial Perturbation | AC: 3154
• Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents
• Learning from Primitive: Probing Visual Reasoning of LVLMs via Counting | AC: 4811
• Learning from Reliable Negatives: Confidence-Anchored Test-Time Adaptation for GUI Grounding | AC: 4771
• Learning Generatable Mutual Distance for Scene-Aware Human Motion Generation | AC: 5753
• Learning Geometry-Aware Embedding Fields for Intrinsic Riemannian Mappings | AC: 4968
• Learning Global Camera Poses from Noisy View-Graphs for Structure from Motion | AC: 4243
• Learning Implicit Constitutive Laws for Dynamic 3D Gaussian Splatting from Monocular Videos | AC: 5073
• Learning Manifolds in High-D Point Embedding for Anisotropic Surface Approximation from Unstructured Point Clouds | AC: 5923
• Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders | AC: 4516
• Learning Physics-based Forward Model Corrections in Unrolled Networks for Diffuser-based Imaging | AC: 3268
• Learning Probabilistic Embeddings for Unsupervised Action Segmentation | AC: 3242
• Learning Probabilistic Prompt for Continual Learning | AC: 4309
• Learning Sample-wise Rank-Aware Interpolation Weights for Composed Visual Data Retrieval | AC: 4294
• Learning Semantic-Robust Change Detection via Semantic-Invariant Self-Distillation | AC: 5223
• Learning Spectral and Polarimetric Clues for One-to-Multimodal Novel View Synthesis | AC: 5962
• Learning Structurally Consistent Representations for Multi-View Radar Semantic Segmentation | AC: 5805
• Learning Structured Visual Compositional Representations for Weakly Supervised Referring Expression Comprehension | AC: 4394
• Learning to Attract and Repel: Dual Quality Margin Learning for Face Recognition (DQM-Face) | AC: 5862
• Learning to Balance: Decoupled Siamese Diffusion Transformer for Reference-Based Remote Sensing Image Super-Resolution | AC: 5910
• Learning to Compose: Revisiting Proxy Task Design for Zero-Shot Composed Image Retrieval
• Learning to Corrupt for Better Restoration | AC: 3767
• Learning to Deny: Action Denial in Multimodal Large Language Models
• Learning to Generate Rigid Body Interactions with Video Diffusion Models | AC: 3697
• Learning to Mask: Cross-Modal Noise Modulation for Hallucination Mitigation in Multi-modal Large Language Models | AC: 5722
• Learning to Recover Task Experts from a Multi-Task Merged Model | AC: 3618
• Learning to Stylize by Learning to Destylize: A Scalable Paradigm for Supervised Style Transfer | AC: 3668
• Learning to Suppress SPAD-based LiDAR Flare | AC: 4054
• Learning to Tessellate: Point Cloud Generation via Recursive Spectral Partitioning | AC: 4627
• Learning Transferable Dynamics Priors from Action to World Modeling
• Learning Video Dynamics with Predictive Differentiable Rendering
• Learning with Bilevel-Minimax Optimization for Efficient and Reliable Transfer Attacks | AC: 5683
• Learning Zero-Shot Subject-Driven Video Generation Using 1% Compute | AC: 5079
• Leaving the City: A Large-Scale Aerial Dataset for Cross-Season Localization in Unstructured Environments | AC: 5482
• LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning? | AC: 5613
• LEGO: Leveled Language Gaussian Splatting | AC: 5407
• LENS: Adaptive Spatio-Temporal Zooming for Keyframe Sampling in Long-Form Videos | AC: 4772
• LensStyle: Learning the Optical Aesthetics for Controllable Stylized Lens Effect Rendering | AC: 3542
• LEO-Fuse: A Modality- and Task-Agnostic Universal Framework for Multimodal Human Sensing | AC: 4825
• Less is More: A Simple yet Effective Object-Centric Prompting Strategy for Vision-Language Reasoning in Autonomous Driving | AC: 5576
• Less is More: Reducing Complexity in Vision-Language-Action Systems | AC: 3351
• Less Tokens, Better Forecasts: Sparse Residual Routing for Efficient Weather Prediction | AC: 3283
• LESV:Language Embedded Sparse Voxel Fusion for Open-Vocabulary 3D Scene Understanding | AC: 5237
• Let ViT Speak: Generative Language-Image Pre-training | AC: 3902
• Let's Reward Step-by-Step: Step-Aware Contrastive Alignment for Vision-Language Navigation in Continuous Environments | AC: 4367
• Leveraging Dark Knowledge for Intrinsic Multimodal Out-of-Distribution Detection | AC: 4990
• Leveraging Phase Information to Boost Unrolled Network Learning for Image Deblurring | AC: 4575
• LGD-Net: Leader-Guided Cross-Modal Dynamics for Hyperspectral and Panchromatic Image Fusion | AC: 3288
• LIBERO-Safety: A Comprehensive Benchmark for Physical and Semantic Safety in Vision-Language-Action Models
• LibraGen: Playing a Balance Game in Subject-Driven Video Generation | AC: 3221
• LiDAR-EVS: Enhance Extrapolated View Synthesis for 3D Gaussian Splatting with Pseudo-LiDAR Supervision | AC: 4594
• LiFlow: Flow Matching for 3D LiDAR Scene Completion | AC: 3569
• Lifting Ego World Models for Planning and Control | AC: 4962
• LightFusion: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation | AC: 5009
• LightSTAR: Efficient Visual Document Retrieval via Lightweight Selection with Vision-Adaptive Refinement
• Lightweight Online Reinforcement Learning for Block Decomposition of CAD Models | AC: 4710
• LIIFusion: Coarse-to-fine Framework for Generative MEF via Implicit Neural Representation | AC: 4269
• LINA: Learning INterventions Adaptively for Physical Alignment and Counterfactual Generation in Diffusion Models | AC: 4722
• LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature Caching | AC: 3327
• Linear Fusion MultiDiffusion for Fast Training-Free Spherical Panorama Generation | AC: 4928
• Linear Scaling Video VLMs for Long Video Understanding | AC: 3243
• LineGraph2Road: Structural Graph Reasoning on Line Graphs for Road Network Extraction | AC: 4703
• Linguistically-Aligned and Visually-Grounded Preference Optimization for Clinically-Augmented Medical Report Generation | AC: 5952
• LinStereo: Linear-Complexity Global Attention for Multi-Scale Iterative Stereo Matching | AC: 5658
• LipsFlow：神经形态 OT-CFM 在多说话人视觉语音识别中的首次探索
• Liquid Fusion of Heterogeneous Representations Towards General Salient Object Detection | AC: 4978
• LISA: Locality-Informed Speculative Decoding for Accelerating Autoregressive Image Generation | AC: 3385
• LiSTAR: Ray-Centric World Models for 4D LiDAR Sequences in Autonomous Driving | AC: 5672
• LiteGS: a high-performance framework to train 3dgs in subminutes via system and algorithm codesign | AC: 3854
• LiteMatch: Lightweight Zero-Shot Stereo Matching via Cost Volume Stabilization | AC: 4533
• Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length | AC: 4171
• LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing
• LiveK12Bench: Have Large Multimodal Models Truly Conquered High School-level Examinations? | AC: 4064
• LivingWorld: Interactive 4D World Generation with Environmental Dynamics | AC: 5110
• LlamaSeg: Image Segmentation via Autoregressive Mask Generation | AC: 3644
• LMGenDrive: Bridging Multimodal Understanding and Generative World Modeling for End-to-End Driving | AC: 5240
• LoCA: Spatially-Aware Low-Rank Convolutional Adaptation of Vision Foundation Models | AC: 5809
• Local Spacing-Aware Hungarian Matching for Stable Point-Supervised Crowd Counting | AC: 5304
• Local-to-global Cross-modal Coordination for Self-supervised RGB-T Tracking | AC: 4228
• Locality-Aware Continual Unlearning for Diffusion Models | AC: 5589
• LoGAN: Multilingual Font Localization with Generative Agents | AC: 4037
• LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory | AC: 3286
• LogFA: Efficient Feature-Space Data Augmentation for Egocentric Temporal Action Segmentation | AC: 3894
• LogicIR: Logic Gate Networks for Image Restoration
• LogiCo: A Unified Framework for Logical and Structural Anomaly Detection
• Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling | AC: 3433
• LoMa: Local Feature Matching Revisited | AC: 4073
• Long-term Traffic Simulation via Structured Autoregressive Modeling
• LongEgoRefer: A Benchmark for Long-Form Egocentric Video Referring Expression Comprehension | AC: 5385
• LongVQUBench: Benchmarking Long-Term Video Quality Understanding of Vision-Language Models | AC: 3592
• Look But Don't Touch with Sparse Autoencoders for Unlearning in Diffusion Models | AC: 4088
• Look Less, Think Faster: Joint Token-Compute Adaptation for Multimodal LLMs | AC: 3807
• Looking Back and Forth: Cross-Image Attention Calibration and Attentive Preference Learning for Multi-Image Hallucination Mitigation | AC: 4735
• LOOM: Weaving Geometry-Consistent Human-Object Interaction Videos via Progressive Curriculum Learning | AC: 4273
• LooseControlVideo: Directorial Video Control using Spatial Blocking | AC: 5401
• LoRC: Detecting AI-Generated Images via Low-Rank Collapse in the Semantic-Residual Space | AC: 5654
• Lost in the Tail: Addressing Geographic Imbalance in Urban Visual Place Recognition
• LoT-Pass: Long-term-robust Image Watermarking for Image to Video Generation
• Low-latency Event-based Object Detection with Spatially-Sparse Linear Attention | AC: 4497
• Low-Level Dataset Distillation for Medical Image Enhancement | AC: 5597
• Low-Rank Ternary Adaptation for Fine-Tuning Transformers | AC: 5924
• LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows | AC: 4770
• LUA: Latent Upscaling Adapter for Diffusion-Based Image Synthesis | AC: 5870
• LUCE: Constrained Curve-Domain Guidance for Training-Free Low-Light Enhancement with Hue-Preserving Decoupling | AC: 5653
• LumiDepth: Stable Monocular Depth in Multi-Illumination Scenes | AC: 5310
• Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision | AC: 3981
• LumiTokens: 3D Relighting via Token-Space Lighting Transformation | AC: 5551
• Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Generation
• LUNA: Learning Universal 3D Human Animation Beyond Skinning
• LVSPM: Long Sequence View Synthesis and Pose Estimation Model | AC: 4743
• M2Tok: Multi-head Multi-codebook Discrete Action Tokenization for Vision-Language-Action Models | AC: 4873
• M4-SAR: A Multi-Resolution, Multi-Polarization, Multi-Scene, Multi-Source Dataset and Benchmark for optical-SAR Object Detection
• MA-VLA: Multi-Arm Vision-Language-Action Model for Collaboration and Compositional Generalization | AC: 4202
• MAC-Splat: Multi-Attribute Consistency for High-Fidelity Sparse-View Reconstruction | AC: 4429
• Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs
• MagicMakeup: A Region-Controllable Diffusion Transformer for High-Fidelity Makeup-Transfer | AC: 5049
• MagicPrompt: Ultra-Lightweight Prompt Tuning for Video Generation | AC: 4150
• MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos | AC: 3770
• MagnetGS-Mesh: High-Quality Multi-Object Mesh Reconstruction via Adaptive Surface Optimization | AC: 5724
• Make Geometry Matter for Spatial Reasoning | AC: 3231
• Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars | AC: 4099
• Making Partial-Label Datasets Easier: A Simple Yet Highly Effective Data Augmentation for Deep Partial-Label Learning | AC: 4011
• MambaRaw: Selective State Space Modeling for Efficient 4K Raw Image Reconstruction
• MANGO: Unleashing Image Generation Capability of Unified Multimodal Models | AC: 3300
• Manifold-Aware Spectral Compaction: A Graph Signal Processing Perspective on Online Gaussian Reduction for 3DGS SLAM | AC: 4067
• Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs | AC: 3781
• Map2World: Segment Map Conditioned Text to 3D World Generation | AC: 5295
• MapDreamer: Aerial Imagery Conditioned Latent Diffusion For Lane Level Map Generation | AC: 3483
• Mapping the Concept Landscape: Structural Perception of Global Distributions for Transparent Data Pruning | AC: 5355
• MARché: Fast Masked Autoregressive Image Generation with Cache-Aware Attention | AC: 5698
• MArFE: Multi-Contrast MRI Arbitrary Scale Super-Resolution with Fourier Enhancement | AC: 3657
• MarineEVT: Advancing Event-Centric Marine Video Understanding via Visual Tool Reasoning | AC: 3324
• Mask-guided Semantic Alignment: Robust Learning with Noisy Labels via Temporal Attention Stability | AC: 4481
• Masked BRep Autoencoder via Hierarchical Graph Transformer | AC: 4133
• Masked Depth Modeling for Spatial Perception | AC: 3692
• MASS: Motion-Aligned Selective Scan for Refinement in Flow-Based Video Frame Interpolation
• Match-Any-Events: Zero-Shot Motion-Robust Feature Matching Across Wide Baselines for Event Cameras
• MATCH: Flow Matching for Multi-View Anomaly Detection
• MaterialFlow: Attribute-Disentangled Material Transfer via Trajectory-Aware Velocity Modulation | AC: 4889
• Matryoshka Gaussian Splatting | AC: 3234
• MAVFusion: Efficient Infrared and Visible Video Fusion via Motion-Aware Sparse Interaction
• MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control | AC: 3954
• Maximum Spanning Tree Guided Confidence and Sparse Graph for Robust Noisy Label Learning | AC: 4056
• MCPNet:Masked Coordinate Pooling-based Attention Network for Medical Landmark Detection | AC: 5336
• MCVL: Multi-Space Cross-View Learning for Aerial-Ground Person Re-Identification | AC: 4774
• ME-IQA: Memory-Enhanced Image Quality Assessment via Re-Ranking | AC: 4785
• MeanTalker: Efficient and Expressive Speech-Driven 3D Facial Animation via Geometric-Aware Mean Flow | AC: 5577
• Measuring 3D Spatial Geometric Consistency in Dynamic Video Generation | AC: 3555
• Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations | AC: 5828
• Mechanistic interventions for explainable digital pathology uncovers adversarial vulnerabilities | AC: 5311
• MED-LCDS: Multi-Expert-Domain CLIP Classification via Logit Calibration | AC: 4338
• MedCAGD: Context-Aware Gated Decoder for Efficient Medical Image Segmentation
• MedGSSR: Generalizable Medical Image Super-Resolution 3D Reconstruction via Hierarchical Feed-forward Gaussian Splatting | AC: 5867
• MediRound: Multi-Round Entity-Level Reasoning Segmentation in Medical Images | AC: 4042
• MedQ-Deg: A Multidimensional Benchmark for Evaluating MLLMs Across Medical Image Quality Degradations | AC: 3619
• MedRegion-CT: Region-Aware Multimodal Large Language Model via SlowFast Tokenization and Pseudo-Mask Guidance for 3D CT Report Generation
• MedRepBench: Benchmarking Structured Understanding of Medical Report Images | AC: 5138
• MedSPOT: A Workflow-Aware Sequential Grounding Benchmark for Clinical GUI | AC: 5938
• MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution | AC: 3771
• MegaFlow: Zero-Shot Large Displacement Optical Flow | AC: 3344
• MeGAS: Thermomechanical Dynamic Gaussian Splatting for Thermophysical Scene Editing
• MemLearner: Learning to Query Context Memory for Video World Models
• MemoBench: Benchmarking World Modeling in Dynamically Changing Environments | AC: 3594
• Memory Tree Guided Key Frame Querying for Efficient 3D Question Answering | AC: 5132
• Memory-Supported Synergistic Adaptation for Training-Free Test-Time Medical Image Segmentation | AC: 3417
• Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-Turn Editing | AC: 4121
• MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens | AC: 3215
• MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts
• Meric: A Unified Framework for Multimodal Music Generation and Retrieval via Representation Space Anchoring | AC: 3607
• MessyKitchens: Contact-rich object-level 3D scene reconstruction | AC: 5690
• MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors | AC: 4340
• Metric-Bench: Exploring In-context Spatial Metric Reasoning in VLMs for Indoor Scenes | AC: 4398
• MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources | AC: 4791
• MG-RWKV: Multi-Grained Context-Aware RWKV for Temporal Forgery Localization
• MG2-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation | AC: 3411
• MGI: Member vs Generated Inference
• MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech | AC: 4836
• MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation
• Mimicking Radiologists: A Coarse-to-Fine Framework with Structural Sparse Tokens for Dual-LLM Computed Tomography Report Generation | AC: 5195
• Mind2Cloud: EEG-to-Point Cloud Generation with Two-Granularity Diffusion Decoding | AC: 5955
• MindBlock: Probing Spatial Assembly and Structure in Unified Multimodal Models | AC: 4631
• MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning | AC: 4806
• MindFlow: Harmonizing Cognitive Semantics and Acoustic Dynamics for Facial Animation Generation in Dyadic Conversations
• MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding | AC: 3142
• MiNQVIS: Mitigating Noisy Queries for Robust Online Video Instance Segmentation | AC: 3617
• Minute4D: Training High-Fidelity 4D Gaussian Splatting in One Minute | AC: 5815
• MIRROR: Aligning Semantic Relations from Language to Image via Gromov-Wasserstein
• MirrorPPR: Exemplar-Based Portrait Photo Retouching
• Mitigate Modality-Asymmetric Forgetting via Stabilizing Visual Representations in CLIP-Based Class-Incremental Learning | AC: 4357
• Mitigating Modality and Language-Style Gaps for Zero-Shot Video Moment Retrieval | AC: 5215
• Mitigating Pose–Scale Discrepancy Bias and Reforming Multi-Support Reasoning for Few-Shot Semantic Segmentation | AC: 5584
• Mitigating Positional Leakage in 3D Masked Autoencoders for Robust Representation Learning | AC: 4798
• Mitigating Radar-Inertial Calibration Ambiguities via SO(3) Manifold Steering | AC: 4409
• Mitigating Sycophancy in Multimodal Chart Understanding via Vision-Grounded Verification | AC: 5590
• MixCompress: Mixture of Experts for Variable Rate Learned Image Compression | AC: 3527
• MixTTA: Low-Rank Cross-Channel Mixing for Reliable Test-Time Adaptation
• Mixture of Specialized Vision Experts: Unlocking Complementary Visual Insights for Faithful MLLM Reasoning | AC: 4465
• MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learning | AC: 5500
• MLP Splatting: Object-Centric Neural Fields | AC: 5496
• MLVC: 面向真实部署的多平台学习式视频编解码器
• MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning | AC: 4691
• MMAgent-R2: Learning to Rerank and Reject for Agentic mRAG | AC: 4250
• MMBU: A Massive Multi-modal Biomedical Understanding Benchmark to Probe the Perception Capabilities of Vision-Language Models | AC: 4567
• MMControl: Unified Multi-Modal Control for Joint Audio-Video Generation
• MMDiff: Extending Diffusion Transformers for Multi-Modal Generation | AC: 4977
• MMEarth-Bench: Global Model Adaptation via Multimodal Test-Time Training | AC: 4577
• mmIR: Frequency-Space Inverse Rendering for 3D Millimeter-Wave Radar ADC Synthesis | AC: 5636
• MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation | AC: 4334
• MMR-Bench: A Comprehensive Benchmark for Multimodal LLM Routing | AC: 5628
• MoAKE: Toward Unified All-in-One Action Quality Assessment via Mixture of Action Knowledge Experts | AC: 4649
• MoBa-GS: Learning a Spatially-Varying Motion Basis over a Dynamic Canonical Space for 4D Reconstruction | AC: 5617
• MobileManiBench: Simplifying Model Verification for Mobile Manipulation
• MobileOcc: A Human-Aware Semantic Occupancy Dataset for Mobile Robots | AC: 5480
• MobileSAM2: Lightweight Segment Anything in Images and Videos via Hypergraphical Knowledge Distillation | AC: 5947
• MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robots | AC: 3969
• MoCA3D: Monocular 3D Bounding Box Prediction in the Image Plane | AC: 4711
• MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics | AC: 4618
• MOCHA: Multi-modal Objects-aware Cross-arcHitecture Alignment | AC: 4917
• Modality-Aware Out-of-Distribution Detection for Multi-Modal Action Recognition | AC: 4417
• Mode-Conditioned Residual Calibration for Multi-Object Tracking | AC: 5156
• Modeling and Compensating Phase Error in High-speed 3D Reconstruction | AC: 4008
• ModTrack: Sensor-Agnostic Multi-View Tracking via Identity-Informed PHD Filtering with Covariance Propagation | AC: 5528
• ModuSeg: Decoupling Object Discovery and Semantic Retrieval for Training-Free Weakly Supervised Segmentation
• MoE-KD: Your Teacher Model is Worth Mixture-of-Experts for Knowledge Distillation | AC: 3138
• Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance | AC: 4484
• MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training | AC: 3966
• Moiré Video Authentication: A Physical Signature Against AI Video Generation
• MOJITO: Modal Joint Learning for Unified End-to-End Autonomous Driving | AC: 3415
• Molecular Identifier Visual Prompting and Verifiable Reinforcement Learning for Chemical Reaction Diagram Parsing | AC: 4646
• Molmo-Point: Better Pointing for VLMs with Grounding Tokens | AC: 4983
• MolmoWeb: Open Visual Web Agent and Open Data for the Open Web | AC: 4684
• MoMCE: Mixture of Modality and Cue Experts for Multimodal Deception Detection | AC: 3964
• MomentSeg: Moment-Centric Sampling for Enhanced Referring Video Object Segmentation | AC: 3213
• Momentum Guidance: Plug-and-Play Guidance for Flow Models | AC: 5526
• MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction | AC: 3312
• Monocular Avatar Reconstruction via Cascaded Diffusion Priors and UV-Space Differentiable Shading
• Monocular Models are Strong Learners for Multi-View Human Mesh Recovery | AC: 4937
• MonoSR: Open-Vocabulary Spatial Reasoning on Monocular Images
• Monte Carlo Energy Aggregation for Mobile 3D Gaussian Splatting
• Moonstone: A Multimodal Foundation Model and Benchmark for Lunar Remote Sensing | AC: 5779
• MOOZY: A Patient-First Foundation Model for Computational Pathology | AC: 4955
• MorphGS: Morphology-Adaptive Articulated Motion Transfer from Videos | AC: 4778
• MorphJEPA: Morphology-Aware Latent Prediction for Hyperspectral Images | AC: 4891
• MoScale: Autoregressive Next-Scale Prediction for Human Motion Generation and Editing | AC: 3276
• Motion Style Slider: Endpoint-Supervised Continuous Style Control for Human Motion Diffusion | AC: 5749
• Motion-aware Sparse Pipeline for Lightweight Object Tracking | AC: 5707
• MotionAnymesh: Physics-Grounded Articulation for Simulation-Ready Digital Twins | AC: 5693
• MotionAtlas: Detailed Region Captioning for Motion-Centric Videos
• MotionChain: Fine-Grained Video Motion Understanding via Structured Decomposition | AC: 4790
• MotionDreamer: Universal Skeletal Motion Generation for 3D Rigged Shapes | AC: 4359
• MotionEditGS: Editing Motion and Appearance of 4D Scenes from Monocular Video via Semantically Anchored Gaussians | AC: 4803
• MotionSplicer: Part-Based Motion Editing for 4D Volumetric Videos | AC: 5475
• MoVA：非对称双投影实现模块化长视频-文本对齐
• Moving Beyond More Views: Redundancy-Aware Ego–Exo Fusion for Proficiency Estimation | AC: 4893
• MPO: Single-Stream Policy Optimization for Efficient Text-to-Image Alignment | AC: 3963
• MSEditor: Toward Consistent Multi-Shot Video Editing | AC: 5638
• MSPL: Multi-Step Pseudo-Labeling for Open-Vocabulary Object Detection
• MSVS-VAE: Multi-Scale Anchored VecSet for High-Fidelity 3D Reconstruction | AC: 3880
• MTVDiff: Multimodal Conditional Latent Diffusion for Enhanced Thermal-to-Visible Face Translation | AC: 4826
• MuCHeR: Multi-Person Camera-Centric Human Detection, Mesh Recovery and Tracking | AC: 3419
• Multi-Anchor Distillation with Text-Guided Analytic Classifier for Continual Learning | AC: 3200
• Multi-Block-Attention-based Color Constancy | AC: 4849
• Multi-Channel Uncertainty-Weighted Score Matching for Conditional Diffusion in Medical UDA | AC: 4347
• Multi-dimensional Preference Alignment by Conditioning Reward Itself | AC: 3625
• Multi-Head Normalization for Wide Vision Transformers | AC: 4268
• Multi-History-Step SDE Inversion for Image Editing with Superior Regional Awareness | AC: 5667
• Multi-Hypothesis Test-Time Adaptation to Mitigate Underspecification | AC: 5455
• Multi-label Instance-level Generalised Visual Grounding in Agriculture | AC: 5097
• Multi-Modal Controlled Coherent Motion Generation | AC: 4899
• Multi-modal Knowledge Preserving Adapter for Embedding Backward Compatibility | AC: 3658
• Multi-modality Image Fusion under Adverse Weather: Mask-Guided Feature Restoration and Interaction
• Multi-scale Object-Aware Gaze Estimation via Geometric Reasoning
• Multi-THuMBS: Multi-person Tracking of 3D Human Meshes Beyond Video Shots | AC: 3183
• Multi-View Foundation Models | AC: 3913
• Multi-view Multi-vehicle Driving Dataset for Novel View Synthesis | AC: 4000
• Multi4D: High-Fidelity Dynamic Gaussian Splatting via Multi-Level Competitive Allocation
• MultiHaystack: Benchmarking Multimodal Retrieval and Reasoning over 40K Images, Videos, and Documents | AC: 3784
• MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Model | AC: 5663
• MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning | AC: 3713
• Multiple Images Distract Large Multimodal Models via Attention Fragmentation | AC: 3440
• MUSE: Unlocking Timestep as Native Task Steering for One-Step Dense Prediction | AC: 4752
• Music-to-Dance Generation via Atomic Movements | AC: 5601
• MuSix: Multi-scale Mixture of World Models for Embodied Agents in Evolving Environments
• MuSViT: A Foundation Vision Model for Sheet Music Representation | AC: 4829
• MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing | AC: 5277
• MV-GEL: Language-Driven Multi-View Geometric Entity Localization on Meshes | AC: 4469
• MV-STRIDE: Enabling MLLMs to Master Multi-View Spatial Reasoning via Hierarchical Capability Modeling | AC: 5718
• MV2GF: Multi-view Pedestrian Detection with a Visual Geometric Foundation Model | AC: 3498
• MVFusion-GS: Motion-Variance Guided Temporal Attention for High-Quality Dynamic Gaussian Splatting | AC: 5347
• MVGS: Multi-view Regulated Gaussian Splatting for Novel View Synthesis | AC: 4315
• MVI2V: Human Centric Image to Video Generation with Multiview Consistent Appearance | AC: 5286
• MVPruner: Dynamic Token Pruning for Accelerating Multi-view Vision-Language Models in Autonomous Driving | AC: 5547
• NaLA: A 3D Native LLM Layout Agent for High-quality 3D Scene Generation
• NanoVSR: Towards Real-Time Video Super-Resolution on Edge Devices | AC: 5988
• NaP-Control: Navigating Diffusion Prior for Versatile and Fast Character Control | AC: 3499
• NAPA: Natively Multimodal Autoregressive Perception Architecture | AC: 5487
• Narrative-Driven Paper-to-Slide Generation via ArcDeck | AC: 3590
• NarrativeTrack: Evaluating Entity-Centric Reasoning for Narrative Understanding | AC: 5493
• Natural Image Pretraining Improves Abstract Reasoning | AC: 5527
• Natural Language Camera Movement Understanding | AC: 5465
• NaVLM-PVC: Progressive Visual Compression for Efficient Native-Resolution Encoding in MLLMs | AC: 4176
• NavWM: A Unified Navigation World Model for Foresight-Driven Planning
• NearID: Identity Representation Learning via Near-identity Distractors | AC: 5494
• NegAS: Negative Label Guided Attention and Scoring for Out-of-Distribution Object Detection with Vision-Language Models
• NegROI: Click-Centric Uncertainty-Guided Refinement with Scene-Conditioned Negative Prompts for Robust Interactive 3D Segmentation | AC: 5410
• NEOMAP: Novel-View Synthesis via Noise Initialization by Manifold Alternating Projection | AC: 3167
• NeSy-Route: A Neural-Symbolic Benchmark for Constrained Route Planning in Remote Sensing | AC: 4443
• NeuIDO: Neural Intrinsic Dynamics Operator for Physics-Informed 4D World Models | AC: 4635
• Neural Collapse-Inspired Multi-Label Federated Learning under Label-Distribution Skew | AC: 4065
• Neural Gate: Mitigating Privacy Risks in LVLMs via Neuron-Level Gradient Gating
• Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction | AC: 5015
• NeuralDMD: Interpretable Untrained Neural Network for Imaging from Sparse and Noisy Observations | AC: 5966
• NeuralGarSim: Geometry-agnostic Garment Simulation with Neural Fields | AC: 5963
• Neuromorphic X-ray Computed Tomography | AC: 3529
• NeuroRefiner: Morphology-Aware Multi-Agent Refinement for 3D Fluorescence Microscopy Neuron Segmentation | AC: 3235
• Nexels: Neurally-Textured Surfels for Real-Time Novel View Synthesis with Sparse Primitives | AC: 3898
• Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priors
• NGPS: Structure-Preserving Self-Supervised Denoising via Neighbor-Guided Patch Sampling
• No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairs
• Noise is a Good Teacher: A Noise-Driven Framework for Robust Collaborative Perception | AC: 4449
• Noise-Robust Face Recognition via Non-target Similarity Distribution Guided Sample Selection | AC: 5198
• Noise-Robust Facial Expression Recognition via Mamba-driven Neighbor Weight Refinement | AC: 5837
• NoisEasier: Test-Time Noise Optimization for Text-to-Video Generation | AC: 3738
• NoiseTilt: Noise-Tilted Reverse Kernels for Diffusion Reward Alignment
• NoPA: Non-Parametric Online 3D Scene Graph Generation | AC: 5441
• Not All Prediction Targets Keep Training-Free Diffusion Guidance on the Manifold
• Novel View Synthesis as Video Completion | AC: 5472
• NumColor: Precise Numeric Color Control in Text-to-Image Generation | AC: 3222
• NUN: Nested Unfolding Network for Real-World Concealed Object Segmentation | AC: 3842
• NURBS Splatting: A Unified Differentiable Rendering Framework for Vector Graphics
• NutriBench-Kitchen: Benchmarking Embodied AI for Nutrition Management | AC: 5302
• O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning | AC: 4659
• OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolution | AC: 4700
• OBBSeg: Irregular Lesion Segmentation under Oriented Bounding Box Annotations | AC: 5877
• ObjectForesight: Predicting 3D Object Trajectories from Human Videos | AC: 4086
• Objects as Audio-Visual Modal Sound Fields | AC: 3275
• Obliviate: Erasing Concepts from Autoregressive Image Generation Models
• OccDirector: Language-Guided Behavior and Interaction Generation in 4D Occupancy Space | AC: 4768
• Occlusion-Resilient Category-Agnostic Pose Estimation with Conditional Flow Matching | AC: 5709
• OCTA-SOT: Online Cross-Modal Trajectory Adjustment for RGBT Anti-UAV Single Object Tracking under Spatio-Temporal Misalignment | AC: 4855
• OCTOPUS: Multi-Agentic Universal Compositional Visual Retrieval | AC: 5802
• OctWorld: Long-Range World-Consistent Video Generation with Octree-based 3D Mapping | AC: 3852
• ODONet: Online Dynamic Offset Network for Visual Object Tracking | AC: 4749
• Odoriko: A Shape-Aware Multimodal Diffusion Framework for Human Motion
• Off the Planckian Locus: Using 2D Chromaticity to Improve In-Camera Color | AC: 3428
• Omni-RRM: Advancing Omni Reward Modeling via Automatic Rubric-Grounded Preference Synthesis | AC: 4833
• OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control | AC: 4712
• OmniColor: A Unified Framework for Multi-modal Lineart Colorization | AC: 4348
• OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning | AC: 3376
• OmniDance: Multimodal Driven Dance Video Generation with Large-scale Internet Data | AC: 4238
• OmniDS: Dual-Stream Context Fusion for Omnidirectional Depth from Fisheye Cameras | AC: 4619
• OmniFace: Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer | AC: 3175
• OmniFit: Multi-modal 3D Body Fitting via Scale-agnostic Dense Landmark Prediction | AC: 3290
• OmniForcing: Unleashing Real-time Joint Audio-Visual Generation | AC: 5147
• OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation | AC: 4251
• OmniLife360: A Benchmark for 3D Reconstruction from In-the-Wild 360° Captures | AC: 5681
• OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models | AC: 4317
• OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents | AC: 4395
• OmniNWM: Omniscient Driving Navigation World Models
• OmniPoint: Universal Monocular Metric Pointcloud from Any Camera | AC: 5560
• OmniPoser: Flexible Human Motion Recovery in the Wild with Masked Flow Matching | AC: 3818
• OmniSch: A Multimodal PCB Schematic Benchmark For Structured Diagram Visual Reasoning | AC: 3451
• OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video | AC: 5312
• OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams | AC: 3341
• OmniX: Any-view and Any-time 4D reconstruction via Feed-forward Trajectory Fields | AC: 3323
• OmniX: From Unified Panoramic Generation and Perception To Graphics-Ready 3D Scenes | AC: 5098
• On Geometric Understanding and Learned Priors in Feed-forward 3D Reconstruction Models | AC: 4861
• On Locality and Length-Generalization in Visual Reasoning | AC: 5922
• On Test-Time Scaling for Vision-Language Models
• On the Diffusibility of High-Dimensional Latents | AC: 3435
• On the Faithfulness of Post-Hoc Concept Bottleneck Models
• On the Plasticity Collapse in Continual Machine Unlearning | AC: 4534
• On the real-world generalisability of Optical Flow models | AC: 3889
• On the Reliability of Cue Conflict and Beyond | AC: 5605
• On the Vulnerability of Parameter-Level Defenses to Model Merging
• On-Orbit Real-Time Wildfire Detection Under On-Board Constraints | AC: 5325
• On-Policy Diffusion Reinforcement Learning Meets Off-Policy Quality Anchoring | AC: 5113
• One Demonstration Is Enough for Real-World Robotic Reinforcement Learning | AC: 5855
• One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models | AC: 3153
• One Slide, Many Views: Unifying Complementary Foundation Model Perspectives for WSI Analysis | AC: 3571
• One Trap to Block Them All: Defending Encoder Stealing via Isotropic Uniformity | AC: 4852
• One Video, One World: Turning Monocular Video into Physical 4D Scenes
• One-Shot Feed-Forward 360° Animatable Avatar via Inpainted UV-Space Gaussian Modeling | AC: 4657
• One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Control | AC: 4290
• OneHSI: A Unified Hyperspectral Foundation Model with Physical Consistency | AC: 4477
• OneVAE: Joint Discrete and Continuous Optimization Helps Discrete Video VAE Train Better | AC: 3920
• OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder | AC: 3181
• Online 3D Instance Segmentation at task-oriented granularity with Unposed Monocular Video | AC: 5139
• Online Reasoning Video Object Segmentation | AC: 3292
• Online Segment 3D Gaussians via Launching Virtual Drones | AC: 5801
• Online Versatile Incremental Learning: Towards Class and Domain-Agnostic Adaptation at Any Time | AC: 3800
• OnPoint: Offline-to-Online Multi-Level Distillation for Point-Supervised Online Temporal Action Localization
• OP3DSG: Open-Vocabulary Part-Aware 3D Scene Graph Generation for Real-World Environments
• OPAL: Orthonormal Prototype Alignment Learning for Interpretable Image Classification | AC: 5968
• Open Your Eyes: Benchmarking the Detection of Fabricated Realities and Weaponized Ethics in VLMs | AC: 5888
• Open-Vocabulary 3D Object Detection with Co-Distillation Discovery and Dual Guidance Robust Training | AC: 3975
• Open-Vocabulary BEV Segmentation with 3D-Aware Geometric Constraints
• Open-Vocabulary Long Term Action Anticipation | AC: 4830
• Open-Weather Robust 3D Detection via Dual-Critic Diffusion Alignment | AC: 5274
• OpenCVL: An Open, Diverse, and Large-Scale Dataset for Fine-Grained Cross-View Localization | AC: 3725
• OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial Agents | AC: 4838
• OpenGround: Planning-based Online Perception for Open-World 3D Visual Grounding | AC: 3487
• OpenPanoD: Aligning Multimodal Prompts and Spherical Representations for Open-Vocabulary Panoramic Detection | AC: 3246
• OpenSubject: Leveraging Video-Derived Identity and Diversity Priors for Subject-driven Image Generation and Manipulation | AC: 5863
• OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Based Video Editing | AC: 3261
• Optimization-Guided Diffusion for Interactive Scene Generation | AC: 5372
• Optimizing Mesh Animation from Video via Shape Flow Guidance | AC: 5106
• ORACLE-3D: Open-world Region-aligned Cross-modal Learning for Label-efficient 3D Scene Understanding | AC: 5557
• ORBIT: Overcoming Hallucination Risks via Bi-manifold Interaction and Traction | AC: 4765
• OREO: Fidelity Alignment in 3D Generation via On-the-fly Rendering-Editing Optimization | AC: 3159
• ORFC: Orthogonal Reparameterization for Low-Bitrate ViT Feature Coding | AC: 5830
• ORION: Ordinal Neural Collapse as a Representation Prior for Visual Navigation | AC: 3475
• OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure | AC: 3150
• Orthogonal Knowledge Refreshing for Domain-Incremental Object Detection | AC: 3414
• OrthoTailor: Geometric Orthogonalization for Conflict-Free Unified Fashion Generation | AC: 3484
• OrthoTrack: Continuous 6-DoF UAV Trajectory Estimation Anchored in Public Orthophotos
• OSOR: One-Step Diffusion Inpainting for Effect-Aware Object Removal | AC: 5390
• OSVE: One Step Video Editing with One Step Diffusion Models | AC: 5170
• OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models
• Out of Sight, Out of Mind? Evaluating State Evolution in Video World Models | AC: 4982
• OVGGT: O(1) Constant-Cost Streaming Visual Geometry Transformer | AC: 3719
• P-CORE: Self-Supervised Surface Consistency for Point-Based Neural Editing | AC: 4573
• P-MTP: Efficient Document Parsing via Multi-Token Prediction with Progressive Depth Scaling | AC: 5238
• P²Fusion: Prompt-based Progressive Infrared-Visible Image Fusion via Dual-Prior Distillation | AC: 5454
• P3-SAM: Native 3D Part Segmentation | AC: 4483
• PA-VAD: 基于扩散模型的纯伪异常视频异常检测
• PACO: Stabilizing Vision Embeddings along Local Paths for Robust Vision-Language Models | AC: 5070
• PaD-GS: Leveraging Distortion Map for Panoramic Gaussian Splatting | AC: 4125
• PADFormer: Pose-agnostic Anomaly Detection from Sparse View Images | AC: 3474
• PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion | AC: 3615
• Pano3D: Unified 3D Reconstruction and Panoptic Segmentation
• PanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-based 3D Visual Grounding
• PanoLess: Environment Reconstruction from Partial Reflective Views | AC: 3606
• Panoramic Affordance Prediction | AC: 3310
• PanoRec: Spatially-Structured Sequence Modeling for Multi-Granularity Panoramic Retrieval | AC: 5847
• PanoSAM2: Lightweight Distortion- and Memory-aware Adaptions of SAM2 for 360 Video Object Segmentation | AC: 4198
• ParaFlow: Parallel Sampling for Flow Matching Models | AC: 3185
• Parallax Portrait Matting | AC: 4407
• Parallel Vision Token Scheduling for Fast and Accurate Multimodal LMMs Inference | AC: 4244
• Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning | AC: 5745
• Parametric SDF for Dynamic Surface Reconstruction | AC: 4494
• PARL-VLA: Pruning-Aware On-Policy Reinforcement Learning for Vision-Language-Action Model | AC: 5429
• Parsimonious Flow Matching for Efficient Image Generation | AC: 4266
• PartCHOI: Part-Aware Guidance for Clothed Human-Object Interaction Generation | AC: 4787
• Partial Skeleton Visibility for Action Recognition: A Constrained Field-of-View Approach | AC: 5914
• PASDiff: Physics-Aware Semantic Guidance for Joint Real-world Low-Light Face Enhancement and Restoration | AC: 5868
• PASR: Pattern-Aware Scene-Conditioned Reasoning for Camouflaged Object Detection | AC: 5521
• PASTEL: Panoramic Alignment for Monocular 4D Scene Reconstruction | AC: 4227
• Path-JEPA: Path Signature Based Predictive Learning for Skeleton Action Recognition | AC: 4270
• Path-level Hindsight Instructions for Semantic Exploration in Vision-Language Navigation | AC: 3528
• Pathryoshka: Compressing Pathology Foundation Models via Multi-Teacher Knowledge Distillation with Nested Embeddings | AC: 4454
• Pathwise Test-Time Correction for Autoregressive Long Video Generation | AC: 4396
• Pay Attention to Attention Distribution: A New Local Lipschitz Bound for Transformers | AC: 5980
• Paying More Attention to Visual Tokens in Self-Evolving Large Multimodal Models
• PDF-Omni: Poincaré Dual Disk Distortion Field-based Recurrent Update for Omnidirectional Stereo Matching | AC: 4884
• PeCA: Palette Context Assisted Inference for Test-Time Paint-Bucket Colourisation on Animation Videos | AC: 4488
• Penetration-Free Compositional 3D Generation via Gaussian Surface Offset | AC: 5611
• Per‑Object IoU Forecasting for Deadline‑Aware Real‑Time Embedded Detection Control | AC: 4550
• Perceiving Better Moments: Cover Frame Reselection and Enhancement for Live Photos with the Live2K Dataset | AC: 4055
• PercepTax: Benchmarking Cross-Property Reasoning in Vision-Language Models | AC: 3591
• PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning | AC: 5004
• Perceptual Projection Pruning: Diversity-Aware Video Token Pruning for Multimodal Large Language Models | AC: 5817
• Persistent Robot World Models: Stabilizing Multi-Step Rollouts via Reinforcement Learning | AC: 5951
• PersonaDrive: Controllable Trajectory Prediction with Multi-Dimensional Driving Personas | AC: 3918
• Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising
• Personalize Your Large Vision-language Models With In-context Prompt Tuning | AC: 5580
• Personalized Reward Modeling for Text-to-Image Generation | AC: 4339
• Personalizing MLLMs via Reinforced Multimodal Reference Game | AC: 5181
• PGCR: Pose–Geometry Coupled Reasoning for Image-to-Point Cloud Registration | AC: 3995
• Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformer
• PhenoLeaf-TS: A Time-Series Benchmark for Leaf Instance Segmentation, Tracking, and Growth Stage Classification | AC: 5291
• PhenoLIP: Phenotype Guided Medical Vision–Language Pretraining | AC: 3929
• PHOSA: Photorealistic 3D Sign Avatar Modeling and Benchmark | AC: 4160
• PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Models | AC: 3450
• PhyEditBench: A Real-World Multi-Stage Benchmark for Physics-Aware Image Editing
• PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation
• PhyMAGIC: Physical Motion-Aware Generative Inference with Confidence-guided VLM | AC: 5519
• PhysAlign: Learning Physical Priors for Dynamical Event-Driven Video Generation via Representation Alignment | AC: 3309
• PhysChoreo: Physics-Controllable Video Generation with Part-Aware Semantic Grounding | AC: 5160
• PhysConvex: Physics-Informed Dynamic Convex Fields for Reconstruction and Simulation | AC: 4613
• PhysDrape: Learning Explicit Forces and Collision Constraints for Physically Realistic Garment Draping | AC: 3672
• PhysEdit: Physically Consistent Image Editing via Causal Enforcement | AC: 5273
• PhysFlowNet: Learning Canonical Latent Manifolds via Spatio-Spectral Physics Priors for Underwater Object Detection | AC: 3641
• Physically Grounded 3D Generative Reconstruction under Hand Occlusion using Proprioception and Multi-Contact Touch
• Physically Grounded Dual-Opacity Gaussian Splatting for Joint RGB-TIR Reconstruction | AC: 5920
• Physically Grounded Monocular Depth via Nanophotonic Wavefront Encoding | AC: 4092
• Physics Meets Perception: A Reinforcement Learning Framework for Unpaired Real-World Image Dehazing | AC: 3780
• Physics Question Scene Graph: Fine-grained Evaluation of Physical Plausibility in Text-to-Video Generation
• Physics-Grounded Disentangled Flow Modeling for Brain Disease Progression Trajectory | AC: 4530
• Physics-Guided Deep Learning for Linear Mueller Matrix Acquisition | AC: 5705
• PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation | AC: 4493
• PhysPO: Physics-Aware Local Preference Optimization for Physically Consistent Video Diffusion | AC: 3783
• PhysRAG: Enhancing Physics-Awareness in Video Generation via Retrieval-Augmented Generation
• PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models | AC: 3673
• PIAvatar: Physically Interactive Avatars via Deformation Gradient Decoupling
• PIC: Revisiting INR for Image Coding with Fast Encoding and Sub-Millisecond Decoding | AC: 5351
• PIPBench: A Profile-Inclusive Framework for Personalized Image Generation Evaluation | AC: 3174
• Pistachio: Towards Synthetic, Balanced, and Long-Form Video Anomaly Benchmarks | AC: 4165
• Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image | AC: 5860
• Pixel Ignores, Superpixel Sees: Adverse Weather Image Restoration via Semantic-Center SSM | AC: 5163
• Pixel-wise Geo-registration of Drone and Satellite Images | AC: 5574
• Pixel-wise Planarity for High-Precision Monocular Plane Segmentation | AC: 5701
• PixelPilot: Scalable Vision-Language-Action Models for End-to-End Autonomous Driving | AC: 3906
• PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion | AC: 4605
• PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation | AC: 5420
• PixVOD: Pixel-Distributed Direct Visual Odometry and Depth Estimation | AC: 5906
• PKINet-v2: Towards Powerful and Efficient Poly-Kernel Remote Sensing Object Detection | AC: 3211
• PLOT: Pseudo-Labeling via Object Tracking for Monocular 3D Object Detection
• Plug-and-Play Attention Linearization for Pretrained Transformers | AC: 4971
• Plug-and-Play Traffic Element Awareness for End-to-End Autonomous Driving | AC: 3305
• PMGC-SimVP: Parametric Multi-scale Gated Convolution for Global Ionospheric TEC Prediction | AC: 3338
• POET: Preference Optimization for Enhanced Text-to-Image Generation | AC: 4253
• Point Diffusion Mamba: Unified Diffusion-State-Space Modeling for Single-View 3D Reconstruction under Data Scarcity | AC: 5866
• Point Ladder Tuning: Parameter-Efficient Hierarchical Adaptation for 3D Point Cloud Understanding | AC: 4283
• Point2Pose: Occlusion-Recovering 6D Pose Tracking and 3D Reconstruction for Multiple Unknown Objects Via 2D Point Trackers | AC: 5929
• Pointer-CAD v2: Plan-Then-Construct CAD Generation with Dimension-Aware Parametric Precision
• PointGT: Simultaneous Geometric and Textural Editing for Point-Based Representations | AC: 4572
• PointLAM: Local Attentive Mamba for Efficient Point-based 3D Object Detection | AC: 3454
• PointSplat: Compact Gaussian Splatting via Human-Centric Prediction | AC: 3962
• Pol-CACTI: A System and dataset forHigh-Speed Polarized Video Compressive Imaging | AC: 4391
• PolarAPP: Beyond Polarization Demosaicking for Polarimetric Applications | AC: 4389
• Policy-Based Tuning of Autoregressive Image Models with Instance- and Distribution-Level Rewards | AC: 4210
• PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models
• PolyLayout: Multi-room Manhattan Layout Estimation | AC: 5890
• Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation
• Poppy: Polarization-Based Plug-and-Play Guidance for Enhancing Surface Normal Estimation | AC: 5532
• Pose Anything Anywhere: Model-free Object Poses from Arbitrary References
• PoseImageNet: Pose Estimation for Extensive Classes Based on Rich Structure Prototypes | AC: 5328
• PoseShield: Neural Collision Fields for Human Self-Collision Resolution
• PosterCopilot: Toward Layout Reasoning and Controllable Editing for Professional Graphic Design | AC: 4148
• Posterior Augmented Flow Matching | AC: 4579
• Posterior Samplings are Missing Modalities Generators for Medical Image Translation | AC: 3287
• PPTArena: A Benchmark for PowerPoint Editing | AC: 4154
• Practice Makes Perfect: From Explicit Decomposition to Reinforced Latent Planning in Text-to-Human Motion | AC: 5797
• Precise Video-to-Audio Generation with Cross-Modal Alignment in Latent Space | AC: 4130
• Predicting Consequences and Reinforcing Navigation Policies with Latent World Models | AC: 4904
• Predictive Photometric Uncertainty in Gaussian Splatting for Novel View Synthesis | AC: 5011
• Predictive Structure Improves Video Diffusion Dynamics | AC: 3444
• Prefill-Time Interventions against Adversarial Attacks on Large Vision-Language Models | AC: 3805
• Preserving Knowledge across Space and Time for Continual Video Deepfake Detection | AC: 4132
• Preventing Expert Collapse in MoE-dVLMs via Modality-Wise Norm Alignment | AC: 5736
• Prevention over Correction: Learning Aligned Representations in One-shot Federated Learning | AC: 4293
• PrimitiveUDF: Primitive-Based Unsigned Distance Fields for Surface Reconstruction from Point Clouds | AC: 5770
• PrintAnything: Learning Geometric Plan Map for 3D Printing G-code Generation from Unoriented Point Clouds | AC: 5719
• Prior-Conditioned Gaussian Discriminants for Generalizable AI-generated Image Detection | AC: 5771
• PriorEye: Geospatial Visual Priors for End-to-End Autonomous Driving
• PriorMaskMap: Robust Online Vectorized Map Construction with Biased Priors | AC: 4184
• PriorPose: Reference-Guided Joint Deformation and Alignment for Category-Level Object Pose Estimation | AC: 4182
• PRISM-VO: Scale-Aware Visual Odometry Using Photometric Plenoptic Bundle Adjustment | AC: 3250
• PRISM: Latent Composition Consistency for Single-Image Reflection Removal | AC: 5668
• PriSM: Parsing and Style-Mixed Consistency for Unsupervised Domain Adaptation in Facial Landmark Detection | AC: 4082
• PRISM3D: Probabilistic Refinement and Robust Initialization for Physically Consistent Scene Modeling under Extreme Motion Blur | AC: 4814
• PriSplat: Propagating Reliable Multi-view Information for Distractor-Free 3DGS | AC: 4019
• Pro-Pose: Unpaired Full-Body Portrait Synthesis via Canonical UV Maps | AC: 4538
• ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models
• Probe, Anchor, and Amend: Active Test-Time Adaptation of Vision-Language Models | AC: 5393
• Probing the 3D Object-Level Understanding of Pre-Trained Detection Transformers | AC: 5986
• Progression as Latent Drift: Generative Forecasting of Slow-Evolving Pathologies | AC: 4445
• Progressive and Localized Super-Resolution of 3D Objects via Localized Latent Voxel Diffusion | AC: 5216
• Progressive Pose-Guided 4D Animal Reconstruction from Monocular Video
• Progressive Representation Learning for Multimodal Sentiment Analysis with Incomplete Modalities | AC: 4858
• Progressively Spiral Mamba Fusion for Multimodal Tracking | AC: 3752
• ProGVC: Progressive-based Generative Video Compression via Auto-Regressive Context Modeling | AC: 4799
• ProLaViT: Learning Progressive Latent Visual Thoughts in Structured Latent Space | AC: 3335
• Prompt2Effect: Training-Free Image-to-Video Model Specialization via LoRA Generation
• ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering | AC: 5675
• Proposal Score Realignment Guided by Semantic Completeness for Weakly Supervised Temporal Action Localization | AC: 5348
• ProSR: Semantic-Prototype-Guided Discrete Modeling for Physically Consistent SAR Super-Resolution | AC: 3383
• Prosthesis-Aware 3D Human Pose Estimation: A Dataset and Benchmark for RSP Users | AC: 3649
• Proteus: Model Leakage-Induced Adversarial Attack in Federated Learning | AC: 4662
• Proto-Gaussian: MRI Modality Translation Based on Learnable Structural Prototypes and 2D Gaussian Splatting | AC: 5283
• ProtoFair: Fair Self-Supervised Contrastive Learning via Pseudo-Counterfactual Pairs
• ProtoMappingNet: Interpretable Hierarchical Prototypes through Relational Prototype Mappings | AC: 4345
• Prototype Normalization: Optimizing Prototype Separation for Heterogeneous Federated Learning | AC: 4679
• Prototype-Conditioned Imagination for Compositional Zero-Shot Learning | AC: 3968
• Provable and Robust Wavefront Sensing via Self-Reference Interferometry | AC: 5546
• Proximity-CLIP: Text-Guided Semantic Proximity Learning for Zero-Shot Anomaly Detection | AC: 4954
• Proximity-Constrained Counterfactual Decoding for Hallucination-Robust Medical VQA | AC: 4924
• Prune Once: Retraining-Free Task-Agnostic Pruning for Vision-Language Models | AC: 5854
• PS-MOT: Cultivating Instance Awareness from Point Seeds for Multi-Object Tracking
• Pseudo-Stereo Inputs: A Solution to the Occlusion Challenge in Self-Supervised Stereo Matching | AC: 5357
• PUF: Plug-and-Play Uncertainty-Aware Fusion for Online 3D Scene Graph Generation | AC: 5405
• Purify then Guide: Rethinking Domain Generalization for Multimodal Face Anti-Spoofing | AC: 4621
• Push–Pull Attentional Anchoring for Diffusion Concept Erasure | AC: 3986
• Pushing the Limits of High-Resolution Weather Forecasting through Data Scaling | AC: 4737
• PuzLM: Solving Jigsaw Puzzles with Sequence-to-Sequence Language Models | AC: 3768
• PWM-ArtGen: Part World Model for Articulated Object Generation | AC: 4915
• PyraE2E: Enhancing End-to-End WSI Analysis via Cross-Scale Super-Resolution | AC: 3340
• Q-BridgeNet: A Quantization Network for Cross-Lingual Sign Language Translation | AC: 5559
• Q-REAL: Towards Naturalness and Distortion Evaluation for AI-Generated Content | AC: 3806
• Q-TriM: Question-Guided Tri-Modal Attention for Audio–Visual Question Answering | AC: 4713
• QASA: Quality-Guided K-Adaptive Slot Attention for Unsupervised Object-Centric Learning | AC: 4841
• QCA: Query- and Content-Aware Keyframe Selection for Long Video Understanding | AC: 4927
• QST-SAM: Leveraging Cross-modal Instructions for Few-shot Referring Video Object Segmentation | AC: 4775
• QSVideo: Query-Conditioned Semantic Temporal Retrieval for Video Understanding | AC: 5884
• QualiTeacher: Quality-Conditioned Pseudo-Labeling for Real-World Image Restoration | AC: 3655
• Quantile‑Adaptive Temperature Scaling for Confidence Calibration | AC: 4026
• QuantV2X: A Fully Quantized Multi-Agent System for Cooperative Perception
• Query-Kontext: An Unified Multimodal Model for Image Generation and Editing | AC: 3482
• Quick ViTs: Speeding up Vision Transformers through Equivariance | AC: 4032
• QVAM: Query-guided View-aware Adaptive Modulation for Aerial-Ground Person Re-Identification | AC: 3396
• Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding | AC: 3901
• QWERTY: Training-Free Motion Control via Query-Warped Video Diffusion Transformers | AC: 4226
• R-ESC: Robustly Erasing Space Concepts via Stochastic Feature Remapping | AC: 4410
• R2M: Real-Aware Residual Model Merging for Robust and Generalizable Deepfake Detection | AC: 5164
• R3DP: Real-Time 3D-Aware Policy for Embodied Manipulation | AC: 3816
• R3RECON: Radiance-Field-Free Active Reconstruction via Renderability | AC: 4911
• RA-SOD: Reliability-Aware RGB-T Salient Object Detection under Modality Degradation | AC: 3933
• Racing in Volume with Flow Ensembles | AC: 4522
• RadarGen: Automotive Radar Point Cloud Generation from Cameras | AC: 4188
• RADIANCE: Relative Adaptive Denoising with IP-Adapter for Novel Concept Enhancement | AC: 4164
• RADmesh: Remesh-Aware Mesh Deformation | AC: 4557
• RAE-NWM: Navigation World Model in Dense Visual Representation Space | AC: 5038
• RAF: Reliability-Aware Fusion of Camera, LiDAR, and 4D RADAR for Robust 3D Object Detection in Adverse Weather | AC: 4159
• RAG-3DSG: Enhancing 3D Scene Graphs with Re-Shot Guided Retrieval-Augmented Generation | AC: 4850
• RAGA: Real Time Ray Traced Gaussian Shadow Casting for 3DGS Avatar-Scene Interaction
• RainODE: Continuous-Time Precipitation Forecasting with Latent Neural ODEs | AC: 4156
• Rank-Aware Hyperbolic Alignment for Vision–Language Dataset Distillation
• Ranked Activation Shift for Post-hoc Out-of-Distribution Detection | AC: 3387
• RankT2I: A Submodular Framework for Discovering Interpretable and Diverse Semantics in Text-to-Image Models | AC: 3836
• Rapidly Deploying On-Device Eye Tracking by Distilling Visual Foundation Models | AC: 5564
• RaPTGS: Render-Agnostic Post-Training Compression of 3D Gaussian Splatting | AC: 5498
• RASA: Disentangled Spatial-Motional Priors for Cross-Identity Character Animation | AC: 5123
• RAU: Reference-based Anatomical Understanding with Vision-Language Models | AC: 3449
• Raw-JPEG Adapter: Efficient Raw Image Compression with JPEG | AC: 3260
• RawGen: Learning Camera Raw Image Generation | AC: 3314
• Ray-Path-Aware Virtual Point Removal on 2D Layer-Wise Nearest Point Map | AC: 3932
• RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video | AC: 3434
• Raymap-Guided Coupling for Drift-Robust Unposed Feed-Forward 3D Reconstruction | AC: 4942
• RayMap3R: Inference-Time RayMap for Dynamic 3D Reconstruction | AC: 4600
• RayRoPE: Projective Ray Positional Encoding for Multi-view Attention | AC: 4570
• RaysUp: Ultra-light Universal Feature Upsampling via Geometry-Aware Ray Representation
• RBE-Flow: Recurrent Bayesian Estimation on Feature Manifolds for Cross-Modal Registration
• RCEdit-500K: Reference Completion for Image-Conditioned Image Editing | AC: 5946
• Rdm: Re-conceptualizing Distribution Matching as a Reward for Diffusion Distillation | AC: 5666
• ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding | AC: 5893
• Read or Ignore? A Unified Benchmark for Typographic-Attack Robustness and Text Recognition in Vision-Language Models | AC: 4589
• REAL-OW: Rehearsal-free Open World Object Detection with Low-Rank Adaptation and Dual-Stage Objectness Modeling | AC: 5205
• Real-Time LiDAR Gaussian Splatting SLAM via Geometry-Aware Covariance Coupling | AC: 3180
• Real-Time Source-Free Object Detection
• ReAL: Reference-to-Image (R2I) Aware Latent Diffusion for Image Super-Resolution | AC: 5013
• Real5-OmniDocBench: A Full-Scale Physical Reconstruction Benchmark for Robust Document Parsing in the Wild | AC: 5777
• RealDyadic: Synthesizing Realistic Dyadic 3D Dialogue with Neural Appearance Priors | AC: 5048
• RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards | AC: 3927
• REALM: An RGB and Event Aligned Latent Manifold for Cross-Modal Perception | AC: 5120
• ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP | AC: 3291
• Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective | AC: 4563
• Reasoning with Memory: A Temporal Granularity-Adaptive Framework for Training-Free Long Video Understanding | AC: 3813
• Reasoning-Guided Part-Level Visual Grounding via Reinforcement Learning | AC: 5998
• ReCamDriving: LiDAR-Free Camera-Controlled Video Synthesis for Novel Trajectories | AC: 4170
• RECO: Region-Aware Compensation for Extrinsic Perturbations in Roadside 3D Detection | AC: 5882
• Recognizing Co-Speech Gestures in-the-Wild | AC: 3706
• Recolour What Matters: Region-Aware Colour Editing via Token-Level Diffusion | AC: 4439
• ReconDreamer-RL: Enhancing Reinforcement Learning via Diffusion-based Reconstruction | AC: 4510
• ReconPhys: Reconstruct Appearance and Physical Attributes from Single Video | AC: 4952
• ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views | AC: 4425
• Reconstructing 3D Human-Object Interaction via a Unified Triplane Space | AC: 5140
• Reconstructing Dense Depth of Dark Scenes with Sparse LiDAR, Noisy Events, and Blurry RGB | AC: 5218
• Reconstructing Humans and Objects in Interaction using Large Reconstruction Models | AC: 3826
• Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations | AC: 4539
• Reconstruction-Anchored Diffusion Model for Text-to-Motion Generation | AC: 4478
• Rectified Embedding Flow Learning for Aerial Multi-view  Geo-localization | AC: 4458
• Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention | AC: 4766
• Recurrent Cross-View Object Geo-Localization | AC: 3957
• Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation | AC: 5714
• ReDesign: Recovering Editable Design Structures from Raster Images via Agentic Decomposition | AC: 3480
• REDistill: Robust Estimator Distillation for Balancing Robustness and Efficiency | AC: 3941
• RefAlign: Representation Alignment for Reference-to-Video Generation
• RefDiT: Local Attribute Guidance in Reference-Based Image Generation | AC: 5626
• Reference-Free Quality Assessment for Virtual Try-On via Human Feedback | AC: 5449
• REFINE: Super-efficient Pruning for 3D Gaussian Splatting via Rendering-Free Primitive Importance | AC: 3858
• Reflect-R1: Evidence-Driven Reflection for Self-Correction in Long Video Understanding | AC: 4235
• ReflectCAP: Detailed Image Captioning with Reflective Memory | AC: 5761
• Reflecting Process Expertise in Procedural Material Generation | AC: 4974
• Reflection-aware generative novel view synthesis | AC: 4040
• Reflection-Aware Reasoning for Non-Line-of-Sight Pedestrian Localization | AC: 4784
• ReFP-AD: Rectified Flow Preconditioning for Energy-Based Anomaly Detection | AC: 5380
• RefracGS: Novel View Synthesis Through Refractive Water Surfaces with 3D Gaussian Ray Tracing | AC: 3476
• ReGen3D: Generalizable Unified Representation Learning for 3D Understanding | AC: 4559
• RegHead: Non-Humanoid Head Blendshapes via Feed-Forward Registration | AC: 5674
• Region-Aware Test-Time Scaling for Compositional Image Generation | AC: 4058
• Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching | AC: 4993
• REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion | AC: 4457
• RegRet: Enhancing Region-Level Retrieval in Large Multimodal Models | AC: 5367
• ReGRPO: Reflection-Augmented Policy Optimization for Tool-Using Agents | AC: 3251
• RegVGGT: Sustainable Visual Geometry Grounding for Streaming via Regulated Memory | AC: 4644
• ReinDriveGen: Reinforcement Post-Training for Out-of-Distribution Driving Scene Generation | AC: 3685
• Reinforcement Learning for Multimodal Diffusion Language Models via Bidimensional Trajectory and Thought Optimization | AC: 4295
• Reinforcing Video Reasoning with Focused Thinking | AC: 4876
• Reinforcing Vision-Language Models for Image Quality Assessment with Grounding Process Rewards | AC: 5542
• ReInGS: Re-Initializing 3D Gaussians against Sparsity Discrepancy in Few-Shot Novel View Synthesis | AC: 5651
• RelAfford6D: Relational 6D Affordance Graphs for Constraint-Driven Robotic Manipulation | AC: 4027
• Relaxed Rigidity with Ray-based Grouping for Dynamic Gaussian Splatting | AC: 4602
• Reliability-Aware 3D Geometric Injection for Universal Person Re-identification | AC: 5424
• Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning | AC: 3298
• ReliefSAM: A Geometry-Augmented Multi-Prior Adapter for Bas-Relief Segmentation | AC: 4796
• Remembering Across Blocks: Topology-Conditioned Block-Progressive Memory for Skeleton-Based Action Recognition | AC: 5958
• ReMoMask: Retrieval-Augmented Masked Motion Generation | AC: 3469
• Render-FM: Feedforward Model for Real-time Photorealistic Volumetric Rendering
• Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback | AC: 4907
• REON-NVS: Real-Time Online Novel-View Synthesis from Sparse-View Videos | AC: 3904
• RePer-360: Releasing Perspective Priors for 360\(^\circ\) Depth Estimation via Self-Modulation
• RePL: Pseudo-label Refinement for Semi-supervised LiDAR Semantic Segmentation | AC: 3561
• RePlan: Reasoning-Guided Region Planning for Complex Instruction-Based Image Editing | AC: 3410
• Representation Alignment for Just Image Transformers is not Easier than You Think | AC: 4716
• Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction | AC: 5276
• Repurposing Geometric Foundation Models for Multi-view Diffusion | AC: 3136
• ReQuest: Rethinking-based Question-Aware Frame Selection for Long-Form Video QA | AC: 4667
• ReShift: Aha-Moment-Driven Reasoning-Level Backdoor Attacks on Vision-Language Models
• Residual-Guided Expert Specialization for Incomplete Multimodal Learning
• ResilPhase: Plug-and-Play Phase Mapping and Noise-Resilient Macro-Trajectory Extrapolation for Diffusion Acceleration
• Resolution-Agnostic Neural Operators for Multi-Rate Sparse-View CT | AC: 3602
• RESOLVE: A Multi-Resolution and Multi-Modal Dataset for Roadside Cooperative Perception
• ReSplat: Learning Recurrent Gaussian Splatting | AC: 3147
• Restoring Linguistic Grounding in VLA Models via Train-Free Attention Recalibration | AC: 5241
• ReTarget: Representation Transformation via Adversarial Regularization for Geometric Misalignment | AC: 4692
• Rethink Backdoor Robustness in Vision Transformers | AC: 3605
• Rethinking Adversary in Semantic Segmentation: An Out-of-Distribution Perspective | AC: 4016
• Rethinking Attention Reallocation for Multimodal Emotion Recognition | AC: 4402
• Rethinking Continual Anomaly Detection on the Edge: Benchmarking Under Realistic Industrial Conditions
• Rethinking Cross-Spectral Image Generation via Shared-Specific Representation | AC: 4507
• Rethinking Detection Calibration: A Coordinate Perspective | AC: 4330
• Rethinking Garment Conditioning in Diffusion-based Virtual Try-On: Decouple, Don't Denoise
• Rethinking IRSTD: Single-Point Supervision Guided Encoder-only Framework is Enough for Infrared Small Target Detection | AC: 3698
• Rethinking Prototype-based Similarity Learning for Few-Shot Object Detection
• Rethinking Pseudo-Labels: Multi-Granularity Supervision for Domain Adaptive Object Detection | AC: 4746
• Rethinking Real-World MRI Denoising: Learning from Physical Noise | AC: 4880
• Rethinking Reward Signals in Video GRPO: When Scores Become Targets | AC: 5060
• Rethinking Robust Adversarial Concept Erasure in Diffusion Models | AC: 5067
• Rethinking Temporal Modeling in Visual Object Tracking via Decoupled Auxiliary Supervision | AC: 4704
• Rethinking Token Reduction for Diffusion Models via Output-Similarity-Awareness | AC: 5702
• Rethinking Training & Inference for Forecasting: Linking Winner-Take-All back to GMMs
• Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs | AC: 5562
• Retrieving and Refining Winning Noise Tickets for Diffusion-Based Motion Generation | AC: 5018
• REVA-PO: Stabilizing Reinforcement Learning for Chest X-ray Report Generation | AC: 5622
• REVEAL: Reasoning-Enhanced Forensic Evidence Analysis for Explainable AI-Generated Image Detection | AC: 5044
• Revisiting Autoregressive Models for Generative Image Classification
• Revisiting Avatar-As-Image: High-Fidelity Registration is All You Need | AC: 3431
• Revisiting Deepfake Detection: BCNet for Robust Generalization Beyond Semantic Dependence | AC: 5201
• Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptation
• Revisiting Scene Graph Generation from the Perspective of Detector-Conditioned Reachability | AC: 4956
• Revisiting the Volumetric Data of 4DME: Compression, Extension and Benchmarking for Micro-Expression Analysis | AC: 5913
• ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video | AC: 3274
• Reward Lightning: Fast Video Generation via Homologous Preference Distillation | AC: 4259
• Reward Modeling for Computer-Using Agent from Video Execution | AC: 5001
• ReynoldsFlow: Physics-Inspired Spatiotemporal Flow Representation for Video Understanding | AC: 5619
• RGB-Pointmap Pretraining for Unified 3D Scene Understanding | AC: 4049
• RGBT-GroundBench: Visual Grounding Beyond RGB in Complex Real-World Scenarios | AC: 5428
• RhymeFlow: Training Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling | AC: 5329
• RIGS: Radar-Informed Gaussian Splatting for Uncertainty-Aware 3D Occupancy and Motion Prediction | AC: 5796
• Ring Forcing: Towards Precise Long-Term Memory for Autoregressive Video Diffusion | AC: 3155
• RiO-DETR: DETR for Real-time Oriented Object Detection | AC: 3395
• RL-AWB: Deep Reinforcement Learning for Auto White Balance Correction in Low-Light Night-time Scenes | AC: 3360
• RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios
• Roam2Room: A Unified Floorplan-to-Furnished Framework for Controllable Indoor Scene Generation | AC: 4326
• ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generation | AC: 3669
• Robobench: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models as Embodied Brain | AC: 4213
• RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks | AC: 5252
• RoboGesture: Real-Time Semantic-aligned Co-Speech Gestures Generation for Humanoid Interaction | AC: 5133
• RoboMirror: Understand Before You Imitate for Video to Humanoid Locomotion | AC: 4062
• RoboStream: Weaving Spatio-Temporal Reasoning with Memory in Vision-Language Models for Robotics | AC: 3802
• RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures | AC: 5587
• Robust 3DGS-based SLAM via Adaptive Kernel Smoothing | AC: 5891
• Robust and Efficient Monocular 3D Gaussian SLAM for Kilometer-Scale Outdoor Scenes | AC: 4689
• Robust onion: Peeling Open Vocab Object Detectors Under Noise | AC: 5437
• Robust Self-Supervised Cross-Modal Super-Resolution against Real-World Misaligned Observations | AC: 3885
• Robust Trajectory Distillation: Hybrid Reweighting Meets Teacher-Inspired Targets | AC: 5228
• Robust Zero-shot Anomaly Detection under Limited Auxiliary Anomaly Priors
• Robustness Emerges Early in Training Dynamics, but Is Not Preserved | AC: 5025
• Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification | AC: 5235
• RobustRDP: Advancing Reaction Diagram Parsing via Synthetic-to-Real Data Scaling and Robustness-Oriented Training | AC: 5682
• Rolling Shutter Camera Self-Calibration | AC: 4929
• Rolling Shutter Relative Pose Estimation Made Practical | AC: 3730
• RoMa v2: Harder Better Faster Denser Feature Matching | AC: 3967
• RoME: Robust Mixture of Low-Rank Experts against Multiple Adversarial Perturbations | AC: 5012
• RoomPlanner: Reachability-Aware View Sampling for Text-to-Room 3D Gaussian Splatting | AC: 5856
• ROSE: Real-Time Open-World Scene Understanding from Monocular Video via Compact Multimodal 4D Scene Graphs | AC: 4795
• Rosetum3D: A Large-Scale 3D Vision Dataset from Preharvest Roses | AC: 4364
• Rotate Your Character: Revisiting Video Diffusion Models for High-Quality 3D Character Generation | AC: 4179
• RotateAttention : RoPE-Aware Rotation and Range Rectification for INT4 Quantized Attention in Video Generation | AC: 5842
• ROVA: Are Video Reasoning Models Ready to Go Outside?
• RPM-Distill: Physiology-guided Adaptive Cross-modal Distillation for Robust Remote Physiological Measurement | AC: 5486
• RSICCLLM: A Multimodal Large Language Model for Remote Sensing Image Change Captioning
• RT-DETRv4: Painlessly Furthering Real-Time Object Detection with Vision Foundation Models | AC: 4033
• RT-RMOT: A Dataset and Framework for RGB-Thermal Referring Multi-Object Tracking | AC: 5378
• RT-SDGOD: Real-Time Single-Domain Generalized Object Detection | AC: 3294
• RTE-FM-Dehazer: Radiative Transfer Equation Inspired Flow Matching for Real-World Image Dehazing | AC: 4242
• RubricRL: Simple Generalizable Rewards for Text-to-Image Generation | AC: 4070
• Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification | AC: 4813
• RUTaL: Residual Upcycling with Task Ladder for Efficient Multi-Task Learning | AC: 4754
• S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresight | AC: 3407
• S2Gest: Split-Scan State Space Models for Dynamic Hand Gesture Recognition | AC: 3811
• S3-Prune: Stability-Aware Token Budgeting for Long-Form Video-Language Models | AC: 5149
• SA-ResGS: Self-Augmented Residual 3D Gaussian Splatting for Next Best View Selection | AC: 3511
• SA-V2V: Training-Free Subject-Aware Video-to-Video Personalization | AC: 4816
• Saber: Anchoring Semantics to Scale-Aware Kinetic Salience for Zero-Shot Skeleton Action Recognition | AC: 4247
• SAEdit: Token-Level Control for Continuous Image Editing via Sparse Autoencoder | AC: 3936
• SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers | AC: 4083
• Safe Generalization: Mitigating Catastrophic Forgetting in Single-Source Multi-Organ Segmentation via Collaborative Causal Learning | AC: 3794
• Safe Responses Matter: Output-Aware Safety Guardrail Mitigate Over-Refusal in MLLMs | AC: 4143
• SAFE-EQA: Semantic-Aware Efficient Exploration for Embodied Question Answering | AC: 5316
• SAFE-Pruner: Semantic Attention–Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation | AC: 5092
• SafeGuard: A Multi-Agent Perception-Reasoning Framework for Social-Risk AI-Generated Video Detection | AC: 4333
• SAFER-Activities: A Dataset for Smart Assessment of Fall Events and Routine Activities | AC: 5760
• SafeSAE-VLA: Interpreting OpenVLA Progress Dynamics with Sparse Feature Analysis | AC: 5740
• Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation
• SAM-MT: Real-Time Interactive Multi-Target Video Segmentation | AC: 4388
• SAM+D: Parameter-Efficient Dimensional Lifting of SAM-Family Models via Depth-Routed LoRA and Depth Shifting | AC: 3465
• SAM2Matting: Generalized Image and Video Matting
• SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video | AC: 3481
• Same Person, Different Depiction: Counterfactual Evaluation of Vision-Language Models on Individuals with Limb Deficiencies | AC: 3172
• Same Pool, Different Answer: Stable Best-of-N Selection for Vision-Language Models | AC: 5077
• SAMPLe: A Sharpness Aware Minimization based Optimizer for Prompt Learning in Vision-Language Models | AC: 5535
• SAND: Stage-Aware Noise Decomposition for Training-Free Diffusion Guidance | AC: 4835
• SARA: Structure-Aware Riemannian-Guided Alignment for Drone Image-Text Retrieval | AC: 5102
• SARIF: Segment Anything for Robust Image Forensics
• Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction | AC: 4673
• Scalable Cross-embodiment Dexterous Grasping via Morphology-Prior Diffusion | AC: 3663
• ScAle: Attention Head Scaling as a Minimal Adapter for Spatial Reasoning in Vision–Language Models
• SCALE: Semantic-Calibrated Guidance Enhancement for Prompt-Faithful Diffusion | AC: 5514
• Scale3D: Autoregressive Modeling for Large Outdoor Scene Generation | AC: 4654
• Scaling Dense Prediction with Latent Decoding | AC: 3184
• Scaling Laws for Black-box Adversarial Attacks | AC: 3565
• Scaling Multi-Reference Image Generation with Dynamic Reward Optimization | AC: 4779
• Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action Alignment | AC: 5640
• Scaling Whole-Slide Pathology Foundation Model Pretraining with Billions Off-the-Shelf Tokens | AC: 3938
• ScanFocus: A Coarse-to-Fine Framework for Spatio-Temporal Video Grounding | AC: 3191
• SCDL: Synergistic Confidence-Dispersion Learning for Semi-Supervised Video Polyp Segmentation | AC: 5934
• ScenarioControl: Vision-language Controllable Vectorized Latent Scenario Generation | AC: 4905
• Scene Generation at Absolute Scale: Utilizing Semantic and Geometric Guidance From Text for Accurate and Interpretable 3D Indoor Scene Generation | AC: 4751
• SceneDiff: A Benchmark and Method for Multiview Object Change Detection | AC: 3827
• SceneHI: High-Resolution 3D-Consistent Scene Texturing with Controllable Illumination | AC: 3190
• Schroedinger’s Cat: Probabilistic Representation and Prediction of Potential Scene Kinematics | AC: 3549
• Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility | AC: 3472
• SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation
• Score-Based Matching with Target Guidance for Cryo-EM Denoising | AC: 4661
• SCORE: SubDistribution-aware Collaborative Knowledge Reinforcing for Cloth-Hybrid Lifelong Person Re-Identification | AC: 4057
• SCoT: Similarity-guided Conflict-aware Task Consolidation for Continual VQA | AC: 4496
• ScrollScape: Unlocking 32K Image Generation With Video Diffusion Priors | AC: 3944
• SD3.5-Flash: Distribution-Guided Distillation of Generative Flows | AC: 4024
• SDSA: Shallow-Deep Squeezing Adapter for Vision-Language Models | AC: 4475
• SDUM: A Scalable Deep Unrolled Model for Universal Cardiac MRI Reconstruction | AC: 4489
• SE-DETR: Explicit Semantic Exploration for Generalizability and Distinguishability in Video Temporal Grounding | AC: 5708
• SEAR: Simple and Efficient Adaptation of Visual Geometric Transformers for RGB+Thermal 3D Reconstruction | AC: 5733
• Sector-Level Cross-View Geo-Localization with Implicit Orientation via Azimuthal Scanning | AC: 5145
• See & Sniff: Learning Visuo-Olfactory Representations
• See Only When Needed: Context-Aware Attention Intervention for Hallucination-Free LVLMs | AC: 3907
• SeeClear: Reliable Transparent Object Depth Estimation via Generative Opacification | AC: 3732
• Seeing as Humans Do: Learning from Motion to Segment Anything Without Supervision | AC: 4996
• Seeing Fast and Slow: Learning the Flow of Time in Videos | AC: 4379
• Seeing Isn't Orienting: A Cognitively Grounded Hierarchical Benchmark for Object Orientation in MLLMs | AC: 5553
• Seeing Through Circuits: Faithful Mechanistic Interpretability for Vision Transformers | AC: 5516
• Seeing Through the Weights: Privacy Leakage in Scene Coordinate Regression | AC: 5226
• Seeing to Ground: Visual Attention for Hallucination-Resilient MDLLMs | AC: 5522
• Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation
• Seeing What Matters: Lesion-Aware High-Resolution Patch Discovery and Fusion for Chest X-ray Report Generation | AC: 5225
• Seek to Segment: Active Perception for Panoramic Referring Segmentation | AC: 4212
• SeekFlow: Synergizing Radiology and Pathology Foundation Models for Precision Oncology via Knowledge-Guided Evidence Flow | AC: 3653
• Seen2Scene: Completing Realistic 3D Scenes with Visibility-Guided Flow | AC: 4521
• SEERBench: A Spatial Ego-Exo Reasoning Benchmark for MLLMs with a Simple Yet Effective Baseline | AC: 5109
• SegDiff: Segmented Trajectory Diffusion for Consistent and Adaptive Robot Manipulation | AC: 3934
• SegFly: A 2D-3D-2D Paradigm for Aerial RGB-Thermal Semantic Segmentation at Scale | AC: 5999
• Segmentation-Guided Homography Estimation for Long-Term Planar Tracking | AC: 5987
• Segmenting Visuals With Querying Words: Language Anchors For Semi-Supervised Image Segmentation | AC: 3331
• Segmenting, Fast and Slow: Real-Time Open-Vocabulary Video Instance Segmentation with Dual-Path Processing
• SegPAR: Class-Centric Decision-Based Sparse Attack for Semantic Segmentation | AC: 4370
• SegVGGT: Joint 3D Reconstruction and Instance Segmentation from Multi-View Images | AC: 4072
• Selective Synergistic Learning for Video Object-Centric Learning | AC: 3321
• Self-Evolving Agentic Image Restoration via Deliberate Planning and Intuitive Execution | AC: 3370
• Self-Evolving Just-In-Time Memory for Proactive Embodied Safety | AC: 5121
• Self-Evolving MCP-GUI Agents via Automated Environment Generation and Experience Learning | AC: 5852
• Self-Improving Diffusion Classifiers with Minority Preference Optimization | AC: 5692
• Self-supervised Garment Dynamics with Persistent Wrinkles
• Self-transcendence: Is External Feature Guidance Indispensable for Accelerating Diffusion Transformer Training? | AC: 3320
• SelfMOTR: Revisiting MOTR with Self-Generating Detection Priors | AC: 5383
• SEM-ROVER: Semantic Voxel-Guided Diffusion for Large-Scale Driving Scene Generation | AC: 5233
• Semantic Browsing: Controllable Diversity for Image Generation
• Semantic Generative Tuning for Unified Multimodal Models | AC: 3778
• Semantic-Anchored Evidential Fusion for Domain-Robust Whole-Slide Survival Analysis | AC: 4369
• Semantic-Aware, Physics-Informed, Geometry-Grounded Weather Synthesis | AC: 3762
• Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding | AC: 3226
• Semantically Aligned Gradient-Driven Context-Preserving Image Editing | AC: 5901
• SemCityLoc: Aerial 6DoF Localization Using Semantic 3D City Models
• SemGAN: A Semantic and Hierarchical Adversarial Network for 3D Human Pose Estimation | AC: 3711
• SemLight: Distilled Semantic–Geometric Fusion for Efficient Local Feature Matching | AC: 5382
• Sen-Cap: Sensor-Flexible and Noise-Resilient Human Motion Capture via LiDAR-Camera Integration | AC: 4655
• Sentinel: Embodied Cooperative Spatial Reasoning and Planning | AC: 4967
• SENTRY: SAM2-Enhanced Neighbor-Aware and Temporally Reasoned Memory for Visual Tracking
• Sequential Visual Place Recognition: Exploiting Trajectory Priors for Robust Localization | AC: 4095
• Setting the Stage: Text-Driven Scene-Consistent Image Generation | AC: 4149
• SFD-Net: Sharp Feature Detection Network Based on Local Geometric Features | AC: 5657
• SFDATrack: Generalized Source-Free Domain Adaptive Tracking Under Adverse Weather Conditions
• SFKD: Spatial–Frequency Joint-Aware Heterogeneous Knowledge Distillation via Multi-Level Wavelet Spectral Interaction | AC: 5232
• SFM: Taming State Space Models for Text-to-Motion via Spatial-Frequency Modeling | AC: 4637
• SGC-Lane: Monocular 3D Lane Detection with Standard-Definition Map Guidance and Lane Completion | AC: 4312
• SGP2: Coarse-to-Fine Controllable Multimodal Remote Sensing Image Generation | AC: 3377
• SGQA: Semantic-Geometric Quality Alignment for Training-Free Few-Shot Instance Segmentation | AC: 3301
• Shared LoRA Subspaces for almost Strict Continual Learning | AC: 3502
• SharpGS: Sharpness-Preserving 3D Gaussian Splatting with Differentiable Blur-Driven Density Control | AC: 4346
• ShellMaker: Language-Guided Exterior Completion under Structural Constraints
• SHIFT: Motion Alignment in Video Diffusion Models with Adversarial Hybrid Fine-Tuning | AC: 3988
• SHINE-PPG: Non-Lambertian Intrinsic Decomposition for Illumination-Robust rPPG | AC: 5703
• Short-to-Long Functional Connectivity Transfer via Structure-Aware Latent Diffusion | AC: 5608
• ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling | AC: 3227
• Show Me Examples: Inferring Visual Concepts from Image Sets | AC: 5416
• SHReg: Strictly Rotation-Equivariant Point Cloud Registration via Spherical Harmonics | AC: 5268
• SICAGE: Speaker-Independent Culture-Aware Gesture Generation using TED4C-L Dataset
• SIFT: Self-Imagination Fine-Tuning for Physically Plausible Motion in Video Diffusion Models
• SIGMA-Lane: Scale-pyramId Gated MAmba for Temporally Consistent Video Lane Detection | AC: 4169
• SiGMA: Sign-Guided Merging and Adaptation framework for Multimodal Continual Instruction Tuning | AC: 5258
• SignBind-LLM: Multi-Stage Modality Fusion for Sign Language Translation | AC: 5003
• SIGNER: Temporally Grounded Sign Language Generation via Time-Resolved Conditioning
• SIGNET: Motion-Level Knowledge Transfer for Cross-Language Sign Language Translation
• SignNet-1M: Large-Scale Multilingual Sign Language Video Dataset with Downstream Benchmarks
• SignRefine: Adapting Foundational Video Models for Sign Language Generation | AC: 4976
• SignSparK: Efficient Multilingual Sign Language Production via Sparse Keyframe Learning | AC: 4491
• Silhouette-based Gait Foundation Model | AC: 3871
• Sim, Yet Same: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds | AC: 3334
• SimFlow: Simplified and End-to-End Training of Latent Normalizing Flows | AC: 4109
• SIMON: SImultaneous Multi-Object Navigation | AC: 4748
• Simple Filtering Improves Masked Autoencoders | AC: 5930
• SIMPLER: Efficient Foundation Model Adaptation via Similarity-Guided Layer Pruning for Earth Observation | AC: 4430
• SIMSplat: Language-Aligned 4D Gaussian Splatting for Driving Scenario Generation | AC: 4537
• Single-Query Person-Centric Bimanual Hand-Object Interaction Detection | AC: 4276
• Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs
• SiPhy: Single-Image Physical Property Reasoning | AC: 4863
• SK-Adapter: Skeleton-Based Structural Control for Native 3D Generation
• SKEL-CF: Coarse-to-Fine Biomechanical Skeleton and Surface Mesh Recovery
• SkelEM: Training-Signal Decoupling of Skeleton and Diffusion for Self-supervised Axial Super-Resolution in Volume Microscopy
• SkillSpotter: Pose-Aware Multi-View Skilled Action Detection and Grading in Ego-Exo Videos | AC: 5502
• Skin-R1: Clinical Knowledge-Guided Dermatological Diagnosis Using Vision-Language Models
• SkipGS: Post-Densification Backward Skipping for Efficient 3DGS Training | AC: 5008
• Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery | AC: 3179
• SkyLume: A Large-Scale Multi-Illumination Aerial Benchmark for Urban Scene Reconstruction and Beyond | AC: 3838
• SkySplat-OV: Generalizable Language Gaussian Splatting for Open-Vocabulary Scene Understanding from Sparse Satellite Views | AC: 3371
• SLAIR: Structured Latent Flow Matching for All-in-One Image Restoration | AC: 4411
• SLAM-Former: Putting SLAM into One Transformer | AC: 5556
• SLER-IR: Spherical Layer-wise Expert Routing for All-in-One Image Restoration | AC: 4286
• Slim-DETR: Real-Time Tiny Object Detection with Efficient Interaction and Gaussian Query | AC: 4625
• SlowBA: An efficiency backdoor attack towards VLM-based GUI agents
• Small Vision-Language Models are Smart Compressors for Long Video Understanding | AC: 5596
• SMART: When is it Actually Worth Expanding a Speculative Tree?
• SMG: Semantic Motion Graph for Monocular Dynamic Gaussian Splatting | AC: 3878
• SMP-UWGS: Coupled Physics-Geometry Optimization for Scalable Multi-Partition Underwater 3D Reconstruction | AC: 5565
• SNOW: Spatio-Temporal Scene Understanding with World Knowledge for Open-World Embodied Reasoning | AC: 4466
• Social-Mamba: Socially-Aware Trajectory Forecasting with State-Space Models | AC: 4424
• SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models | AC: 3202
• Solving Diffusion Inverse Problems with Restart Posterior Sampling | AC: 4553
• Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective
• SOMA: From Surface Observations to Muscle Anatomy | AC: 5182
• SON-GOKU：图着色实现多任务学习的无冲突调度
• SONIC: Spectral Optimization of Noise for Inpainting with Consistency
• Sound-based Multi-Person 3D Pose Estimation | AC: 3961
• Source-Agnostic Image Translation Based on Latent Aware Adaptive Masking | AC: 3364
• SOVTrack: Open-Vocabulary Multi-Object Tracking with Self-Supervised Pseudo Labeling and Feature Distillation | AC: 5099
• SP-TransientBench: A Real-Captured Single Photon Perception Benchmark | AC: 4446
• Spanning the Visual Analogy Space with a Weight Basis of LoRAs
• Spanning Tree Autoregressive Visual Generation | AC: 4249
• SPAR: A Sequential Primacy and Attribution Ranking Framework for Skill Determination | AC: 3908
• SPAR: Semantic-Pixel Self-Alignment and Adaptive Routing for Unified Multimodal Models | AC: 4353
• SpaR3D-MoE: Adaptive 3D Spatial Reasoning from Sparse Views Meets Geometry-Inductive Mixture-of-Experts | AC: 5271
• SPARC: Scalable Path-Specific Counterfactual Fairness via Causal Conditional Independence | AC: 4043
• SPARC: Single-Pass Scaling for Motion Forecasting with Conformal Bayesian Last Layers | AC: 5773
• SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation | AC: 5604
• Sparse auto-regressive modeling for scene generation from multi-view images | AC: 3421
• Sparse-View Surface Reconstruction using Gaussian Splatting through High-Confidence Depth Propagation with Normal Priors | AC: 4097
• SparseCtrl-HOI: Sparse Temporal Control for Human-Object Interaction Video Generation | AC: 5706
• SparseDriveV2: Scoring is All You Need for End-to-End Autonomous Driving | AC: 3597
• Sparsity-Inducing Divergence Losses for Biometric Verification
• Spatial Amsan: A Benchmark for Perception-Grounded Spatial Reasoning and Action Evaluation in Egocentric Manipulation | AC: 3328
• Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training | AC: 5426
• SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning | AC: 4502
• SpatiO: Adaptive Test-Time Orchestration of Vision-Language Agents for Spatial Reasoning | AC: 5289
• Spatiotemporal Flux Probing for Single-Photon Videography | AC: 3267
• SPDA: Efficient Online Test-Time Adaptation for Promptable Medical Segmentation | AC: 4824
• SPEAR: A Simulator for Photorealistic Embodied AI Research | AC: 3273
• SpecEyes: Accelerating Agentic Multimodal LLM via Speculative Planning and Perception | AC: 3726
• SPECSIA: Stylization Dataset for Novel-View Enhancement in Drawing-based 3D Animation
• Spectral and Trajectory Regularization for Diffusion Transformer Super-Resolution
• Spectral Consistent Flow for One-step 3D Medical Image Translation | AC: 4006
• Spectral Evolution-Guided Token Pruning in Multimodal Large Language Models
• Spectral Gating via Damped Oscillations for Adaptive Implicit Neural Representations
• Spectral Gradient Orthogonalization Improves Differentially Private Training at Scale | AC: 4651
• Spectral Prior for Reducing Exposure Bias in Diffusion Models | AC: 5192
• Spectral-Aware Analytic Class-Incremental Learning for Long-Tailed Distributions | AC: 4012
• SpectralSplats: Robust Differentiable Tracking via Spectral Moment Supervision
• SpecV: Specification Verification for Robust Unified Multimodal Evaluation | AC: 4643
• SpEmoC: A Balanced Speaker-Segment Multimodal Emotion Benchmark | AC: 4511
• SPHERE: From MRI Sampling Mechanisms to Spatial Priors for Generalizable Brain Tumor Segmentation | AC: 5243
• SPICE: Simple Polysemantic feature Interpretation via Clustering-based Explanations | AC: 5239
• SplatCtrlA: Generalizable Single Image to Fully Controllable 3D Avatar | AC: 5172
• SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training | AC: 4992
• SplitHDR: Saturation-Aware HDR Recovery and Denoising for Real-Time Detection | AC: 4349
• SPOT-E: Test-Time Entropy Shaping with Visual Spotlights for Frozen VLMs | AC: 3388
• Spotlight: Identifying and Localizing Video Generation Errors Using VLMs | AC: 4969
• SR-Edit: Region-Aware Image Editing via Self-Refinement | AC: 5892
• SRRA: Stable-Rank-Based Residual Adaptation for Generalizable Deepfake Detection | AC: 5186
• SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models
• SSBP: Stage-Specialized Block Pruning for Video Diffusion Models | AC: 3369
• SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization | AC: 4495
• Stabilizing Deep Reconstruction Operators with Contractive Anchoring | AC: 3416
• Stabilizing Real-World Visual Active Tracking with Action-Smooth Test-Time Adaptation | AC: 4009
• Stabilizing Ultra-Low-Bit Quantization of Multimodal LLMs via Global Bit Allocation | AC: 5767
• Stable and Scalable Bundle Adjustment of Holistic 3D Structures | AC: 4860
• STAC: Selective Spatiotemporal Aggregation and Compression for Video Reasoning Segmentation | AC: 5742
• STANCE: Controllable Video Generation for Structured Dynamics via Sparse-To-dense ANChored Encoding | AC: 3671
• Stand Up and Move: Benchmarking Interactive Spatial Intelligence in WalkerBench | AC: 5523
• StarDojo: Benchmarking Open-Ended Behaviors of Agentic Multimodal LLMs in Production–Living Simulations with Stardew Valley
• STARLINC: Satellite Trail Artifact Removal using Inter-Frame Correlation | AC: 4093
• Starve to Perceive: Taming Lazy Perception in VLMs with Constrained Visual Bandwidth | AC: 4069
• STAT: Soft Tail-dropping for Adaptive Visual Tokenization | AC: 4551
• Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging | AC: 4368
• Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMs
• Stealthy Multi-task Adversarial Attacks | AC: 5515
• Steerable Visual Representations
• Steering 3D Generations: Preference Alignment via Direct Reward and Preference Optimization | AC: 5670
• Steering Diffusion Models via Class-Contrastive Influence for Few-Shot Classification | AC: 5919
• Step-by-Step Video-to-Audio Synthesis via Negative Audio Guidance
• STEP: Score-Based Temporal Energy for Human Pose Video Anomaly Detection | AC: 3512
• STEP: Spatial Thinking and Egocentric Pointing for Embodied Instruction Following | AC: 5165
• StereoEdit: A Diffusion-Based Framework for Stereo-Consistent Image Editing | AC: 5131
• StereoGS: Sparse-View 3D Gaussian Splatting via Stereo Priors
• Sticking Information in Plain Sight: Encoding and Detecting Hidden Stickers in the Real World | AC: 4984
• Stitched Embeddings: A Unified Latent Space for 3D Garments and 2D Patterns | AC: 5927
• StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning
• Stochastic Optimal Control Sampling for Diffusion Inverse Problems | AC: 5052
• Stokes-Informed Diffusion for Robust Linear Polarization Estimation | AC: 4397
• StoryBlender: Inter-Shot Consistent and Editable 3D Storyboard with Spatial-temporal Dynamics | AC: 5298
• StoryTeller: Training-Free Narrative Grounding for Long-Form Audio Description | AC: 4541
• Straight-Path Flow Matching for Incomplete Multi-View Clustering | AC: 4641
• StratoSplat: Taming Layered Regularities for Sparse Aerial 3D Gaussian Splatting | AC: 5641
• Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion | AC: 3212
• Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors | AC: 3538
• StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generation
• StreamOcc: Streaming Dense Voxel Representations for 3D Occupancy Prediction
• StreamSpatial: A Benchmark and Framework for Streaming 3D Visual-Spatial Reasoning | AC: 4131
• StreamTalk: Streaming Co-Speech Gesture Generation with Key-Pose Anchoring | AC: 3204
• StreetForward: Perceiving Dynamic Street with Feedforward Causal Dynamics | AC: 5566
• STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding | AC: 3272
• StrucTab: A Structured Optimization Framework for Table Parsing | AC: 4626
• StructPolicy: Structure-Guided Imitation Learning Robust to Visual Domain Shifts | AC: 4187
• StructSplat: Generalizable 3D Gaussian Splatting from Uncalibrated Sparse Views | AC: 3486
• Structural Assessment for Understanding and Guiding Dataset Distillation in Discrete Token Space
• Structure Gaussian Splatting SLAM | AC: 5019
• Structured Hyperedge Adaptation for Parameter-Efficient Fine-Tuning of Vision Transformers
• Structured Redundancy Modeling for Efficient Visual Token Pruning in High-Resolution MLLMs | AC: 5909
• Structured SIR: Efficient and Expressive Importance-Weighted Inference for High-Dimensional Image Registration | AC: 5798
• Structured-Noise Masked Modeling for Video, Audio and Beyond | AC: 3560
• StructureGS: Structure-aware Gaussian Splatting for Articulated Object Reconstruction | AC: 4158
• STVFocus: Query-guided Spatio-Temporal Visual Focusing for Video LLMs | AC: 5016
• StyleFusion360: View-Consistent Head Stylization via Adaptive Style Modulation | AC: 4520
• Stylized Video Generation via Decoupled Data Synthesis and Gated Style Token Injection | AC: 3198
• SubSplat: High-Resolution Pixel-aligned 3DGS via Sub-pixel Gaussian Reparameterization | AC: 4274
• SUM: Unified Geometric Surgery on Spatio-Temporal Adaptation Vectors for Federated Class Incremental Learning | AC: 4372
• SuperFlex: Deformable Superquadrics for Point Cloud Decomposition | AC: 3728
• SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation | AC: 4300
• SupIR-GS: Thermal Infrared Super-Resolution Novel View Synthesis with Imaging-Calibrated 3D Gaussian Splatting | AC: 5680
• Surprise Forcing: What to Remember, When to Skip in Long Video Generation | AC: 3534
• SurvMILKD: A Weakly Supervised Survival Analysis Framework for Multi-Teacher Knowledge Distillation using Pathology Foundation Models | AC: 5511
• SV-TAD: Native Sparse Convolutions for Efficient Temporal Action Detection | AC: 3635
• SVCBench: A Streaming Video Counting Benchmark for Spatial-Temporal State Maintenance
• SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing | AC: 3530
• SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence | AC: 3718
• SVI360: Spherical Video Interpolation | AC: 5362
• SWAN: World-Aware Adaptive Multimodal Networks for Runtime Variations | AC: 4587
• Swap the Right Identity: Spatio-Temporal Preference Optimization for Identity Swapping | AC: 5784
• SWIFT: Spatial-Window Integrated Frequency-aware Token Pruning for Efficient MLLMs on Edge Devices | AC: 3307
• SwiftWA: An Efficient Action-Centered World-Action Model | AC: 4887
• SWSL: Semantic-aware Weakly Supervised Learning for 3D Motion Generation using 2D Motion Data | AC: 4931
• Symbiotic-MoE: Unlocking the Synergy between Generation and Understanding
• Syn-GRPO: Self-Evolving Data Synthesis for MLLM Perception Reasoning | AC: 5711
• Syn4D: A Multiview Synthetic 4D Dataset | AC: 3248
• SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation
• SyncFix: Multi-View Consistent Diffusion Refinement of 3D Reconstructions | AC: 5509
• SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion | AC: 4017
• SyncLoop: A Multimodal Dual-Loop Framework for Self-Improving Mathematical Reasoning | AC: 3237
• SyncVL: Synchronizing Vision ⟷ Language Using Unsupervised Adaptation | AC: 5126
• Synesthesia via Direct Latent Augmentation: Bypassing the Decode-Encode Loop for Cross-Modal Distillation | AC: 3566
• SynFlow: Scaling Up LiDAR Scene Flow Estimation with Synthetic Data | AC: 5318
• SynHMR: Synergistic Joint-Mesh Modeling for LiDAR-based Human Mesh Reconstruction | AC: 4675
• SynLF: Zero-Shot Metric Depth from Light Field Cameras via Physics-Grounded Synthesis | AC: 4459
• Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos | AC: 3891
• SyntheticDoc: A Large Synthetic Dataset for Document Unwarping and Illumination Correction | AC: 5293
• SynVAR: Synergizing Spatial and Semantic Alignment in Visual Autoregressive Model | AC: 5822
• T-REN: Learning Text-Aligned Region Tokens Improves Dense Vision-Language Alignment and Scalability | AC: 3505
• Table-MCR2TR: Merged-Cell-Aware Table Recognition via Reinforced Multimodal Language Models | AC: 4733
• TabletopGen: Tabletop Scene Generation and Interactive Simulation for Robotic Manipulation | AC: 4437
• Tac2Real: Reliable and GPU Visuotactile Simulation for Online Reinforcement Learning and Zero-shot Real-World Deployment | AC: 5180
• Tackling Misattribution in 3D Intrinsic Decomposition via Proximity Attention Point Rendering | AC: 4265
• TACO-Net: Topological Signatures Triumph in 3D Object Classification | AC: 3582
• Tactile Modality Fusion for Vision-Language-Action Models | AC: 5973
• TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction | AC: 4734
• Taming Camera-Controlled Video Generation with Verifiable Geometry Reward | AC: 3872
• Taming Dynamic Clutter: Variance-Driven Adaptive Gain Control for Bio-inspired Small Target Detection | AC: 5061
• Taming LLMs for Codematic Indoor Scene Generation | AC: 3532
• Taming Text-to-Sounding Video Generation via Advanced Modality Condition and Interaction
• TAQ: Static-Deployable Temporal-Aware Quantization for Real-World Video Super-Resolution | AC: 5539
• TAR: Temporal Anchor-Constrained Reasoning for Video Temporal Grounding | AC: 4107
• Target-aware Image Editing via Cycle-consistent Constraints | AC: 4615
• Target-Bench: Can Video World Models Achieve Mapless Path Planning with Semantic Targets? | AC: 5197
• Targeted Structure Completion for Sparse-View 3D Reconstruction in Autonomous Driving | AC: 5127
• TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs | AC: 4204
• TASE: Truncation-Aware Semantic Embeddings for 3D Scene Understanding and Editing | AC: 4900
• Task Alignment: A simple and effective proxy for model merging in computer vision | AC: 3489
• Task-Agnostic Incremental Vision-Language Object Detection via Prompt Augmentation and Distribution-Aware Fusion | AC: 4192
• Task-driven Processing with Coarse-to-Fine Glimpse-based Active Perception | AC: 5374
• TaskTok: Delving into Task Tokens for Task-driven Image Restoration
• TaxoGrasp: Taxonomy-Guided Human Grasp Synthesis with Sparse Contact Constraint | AC: 4890
• TaxoMIL: Taxonomy-Constrained Learning for Hierarchical Whole Slide Image Analysis
• TDSR-VLA: Transition-aware Denoising Sequence Representations for Vision-Language-Action | AC: 5826
• Teaching an Agent to Sketch One Part at a Time | AC: 4305
• Teaching Vision-Language-Action Models What to See and Where to Look | AC: 5835
• TecoPrompt: Temporal-Conservative Prompt Learning for Vision-Language Models | AC: 5588
• Tempo-SAM3D: Monocular Video to 4D via Temporal Memory-Guided Generation | AC: 5725
• Temporal and Cross-modal Alignment for Enhanced Audiovisual Video Captioning | AC: 4311
• Temporally Aware Densification for Dynamic 3D Gaussian Splatting | AC: 4688
• Temporally Stable Generative Illumination with a One-Step Diffusion Model | AC: 4617
• TerrainGraphNet: Terrain-Constrained Graph Reasoning for Landslide Segmentation | AC: 5731
• Tessellating The Earth
• Test-time Counterfactual Calibration for Hallucination-Resistant Temporal Grounding | AC: 3576
• Test-Time Noise Guided Adaptation for Realistic Autoregressive Video Generation | AC: 5734
• Test-Time Registers as Global Priors for Tokenized Image Generation | AC: 5167
• TETO: Tracking Events with Teacher Observation for Motion Estimation and Frame Interpolation | AC: 3139
• TetraSDF: Analytic Isosurface Extraction with Multi-resolution Tetrahedral Grid | AC: 4724
• TEX-Drive: Temporal Perception Meets Experience-Guided Mixture-of-Experts for End-to-End Autonomous Driving | AC: 3743
• Text Dictates, Music Decorates: Energy-based Attention for Editable Dance Motion Generation
• Text-based Tactile Graphics Generation for the Visually Impaired | AC: 5071
• Text-Conditioned Background Generation for Editable Multi-Layer Documents
• Text-Guided 6D Object Pose Rearrangement via Closed-Loop VLM Agents | AC: 3785
• TexTailor: Inference-Time Textual Guidance Tailoring for Multimodal Diffusion Transformers | AC: 5253
• TextDS: Parameter-Efficient Representation Alignment for Scene Text Detection under Distribution Shifts
• TextFace: Compositional Text-Guided Identity Preserving Face Synthesis for Face Recognition | AC: 5851
• The 3D Mirage: Probing and Taming 3D Hallucinations | AC: 5997
• The Cost of Reasoning: Chain-of-Thought Induces Overconfidence in Vision-Language Models | AC: 4513
• The Devil Is in the Dark Pixels: Toward Brightness Bias-Robust Denoising | AC: 5112
• The Dynamic Prior: Understanding 3D Structures for Casual Dynamic Videos | AC: 4606
• The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models
• The Label Imitation Game: Turing Test Network for Zero-Shot Pseudo-Label Pruning
• The Language of Visual Attention: Modeling Scanpaths via Autoregressive Token Prediction | AC: 5404
• The Map Is Not the Territory: Embedding-Coverage Blacklists for Safe Diffusion Steering | AC: 5983
• The Path to Reconciling Quality and Safety Alignment in Text-to-Image Generation | AC: 5345
• The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding | AC: 3637
• The Sterkfontein Caves Dataset: A Novel View Rendering Challenge from the Cradle of Humankind | AC: 5206
• The Telephone Game: Evaluating Semantic Drift in Unified Models | AC: 5689
• Thermo-JEPA: Learning a Geometry-Grounded Thermal World Model via Cross-Modal Privileged Masking | AC: 3162
• ThermoGS: Decoupling Physical Surface Attributes for Spatio-Temporal Thermal Field Emulation via 4D Gaussian Splatting | AC: 3922
• Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning | AC: 5006
• Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models | AC: 3721
• Think While You Map: Asynchronous Vision-Language Agents for Incremental 3D Scene Graphs
• Thinking Ahead: Foresight Intelligence in MLLMs and World Model | AC: 4277
• Thinking from the Robot’s View: The CoT-HRC Benchmark for Human Intent Reasoning in Embodied Collaboration | AC: 5794
• Thinking in Streaming Video | AC: 4857
• This Looks Distinctly Like That: Grounding Interpretable Recognition in Stiefel Geometry against Neural Collapse | AC: 3477
• Through Van Gogh’s Eyes: Global Style Transfer with Diffusion Model | AC: 5399
• TiCRL: Textual Image Classification with Reinforcement Learning-Based Curriculum Learning | AC: 4608
• TIDES: Time-Derivative Event Simulation via Deformable Reconstruction | AC: 5299
• TIIF-Bench: How Does Your T2I Model Follow Your Instructions? | AC: 3177
• Tiled Prompts: Overcoming Prompt Misguidance in Image and Video Super-Resolution | AC: 4355
• TiltDiff: Tilted Weight-Space Diffusion for Neural Network Generation | AC: 5942
• TimeWalker: Personalized Neural Space for Lifelong Head Avatars | AC: 5143
• TinyHistory: Lightweight Video History Embeddings via Two-Stage Context Learning | AC: 4003
• TIR-Agent: Training an Explorative and Efficient Agent for Image Restoration | AC: 5122
• TIR-Bench: A Comprehensive Benchmark for Agentic Thinking-with-Images Reasoning | AC: 4263
• TMI: Text-to-Image Meets Image-to-Image for Complementary Data Synthesis to Boost Long-Tailed Instance Segmentation | AC: 4146
• To Adapt or Not to Adapt? Selective Adaptation for Vision-Language Models | AC: 3715
• To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion | AC: 5971
• ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance | AC: 4815
• Together, Then Apart: Balancing Alignment and Distinctiveness for Multimodal Survival Analysis | AC: 4717
• Token-Based Affordance Grounding with Large Vision-Language Models | AC: 3304
• Token-level Response-visual Attention Guidance for Multimodal LLMs Knowledge Distillation | AC: 5853
• TooBad: Backdoor Diffusion Models with Ultra-Low Poison Rate and Imperceptible Trigger | AC: 4050
• TOPA: Mitigating Concept Dominance in Diffusion Personalization via Target-Oriented Perturbation Augmentation | AC: 4256
• TopoAgent: An Agentic Framework for Automated Topology Learning in Medical Imaging | AC: 5080
• TopoFuse: Topology-Aware Tri-Planar Fusion for 3D Cryo-Electron Tomography Segmentation | AC: 4153
• TopoGAT: Plug-and-Play Topological Graph Attention for Fine-Grained 3D Segmentation | AC: 4162
• TopoGS: Planar Reconstruction via Topology-Aware 3D Gaussian Splatting | AC: 5769
• Topology-Weighted Effective Rank: A Zero-Cost Proxy for Training Dynamics Stability in Neural Architecture Search | AC: 3390
• TORA: Topological Representation Alignment for 3D Shape Assembly
• TouchAnything: Diffusion-Guided 3D Reconstruction from Sparse Robot Touches | AC: 4442
• Toward Interpretable Analysis of Whole-slide Pathology Images via Large Language Model-based Agentic Reasoning | AC: 3840
• Toward Robust In-Context Segmentation via Concept Guidance
• Towards Alias-Free 4D Gaussian Representations with Motion-Aware Filtering | AC: 5460
• Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning
• Towards Consistent and Efficient Dataset Distillation via Diffusion-Driven Selection | AC: 5321
• Towards Effective Long Video Understanding: Dynamic MAS Construction via Meta-Agent | AC: 5579
• Towards Flexible, Natural, Efficient Interaction for Conversational Talking Face Generation | AC: 4948
• Towards Generalizable Robotic Manipulation in Dynamic Environments
• Towards Geometry-Grounded Dense Semantic Matching with VGGT Priors | AC: 4094
• Towards High-Resolution Visual Perception via Hierarchical Entity Exploration | AC: 5737
• Towards In-Context Tone Style Transfer with A Large-Scale Triplet Dataset | AC: 4607
• Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation
• Towards Interactive Global Geolocation Assistant | AC: 3263
• Towards Long-Form Spatio-Temporal Video Grounding
• Towards Memory-Efficient Autoregressive Video Generation via Instance-Specific Parametric Absorption | AC: 4508
• Towards Memory-Efficient Autoregressive Video Generation via Instance-Specific Parametric Absorption | AC: 4508
• Towards Metric-Agnostic Trajectory Forecasting
• Towards More Efficient Decoding for Autoregressive Vision-language-action Models | AC: 4634
• Towards Practical Lossless Neural Compression for LiDAR Point Clouds | AC: 5307
• Towards Purified Multi-Label Test-Time Adaptation of Vision-Language Models | AC: 3924
• Towards Real-World Wearable Motion Reconstruction | AC: 4965
• Towards Reconfigurable Visual Feature Compression | AC: 4103
• Towards Reliable Medical Large Vision-Language Models via Counterfactual Preference Optimization | AC: 4374
• Towards Reliable Multi-Label Classification via Conditional Dependency Modeling | AC: 5768
• Towards Robust Driving Perception: A Flexible Scale-Driven Family for Self-Supervised Monocular Depth Estimation | AC: 5634
• Towards Scalable Pre-training of Visual Tokenizers for Generation | AC: 3997
• Towards Sparsely Annotated Open World Object Detection | AC: 4378
• Towards Spatial Supersensing in the Wild | AC: 3819
• Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics
• Towards Temporal Compositional Reasoning in Long-Form Sports Videos | AC: 4666
• Towards Trustworthy Dermatology MLLMs: A Benchmark and Multimodal Evaluator for Diagnostic Narratives | AC: 4514
• Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresight | AC: 4793
• Towards Unsupervised Multi-modal Semantic Segmentation | AC: 3704
• Towards Video Anomaly Detection from Event Streams: A Baseline and Benchmark Datasets | AC: 5214
• TPCNet: A Low-Light Image Enhancement Network Inspired by Triple Physical Constraints | AC: 4351
• TR-MoE: Temporal Reliability-Aware Mixture-of-Experts for Robust Tracking | AC: 4745
• Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels | AC: 4002
• Training-free Controllable Motion Generation under Heterogeneous Constraints | AC: 3731
• Training-free Cross-domain Few-shot Segmentation via Robust Semantic Representation and Matching | AC: 5609
• Training-free Discriminative Patch Mining for Robust Few-Shot Recognition with CLIP | AC: 5508
• Training-Free Multi-Concept Image Editing | AC: 3799
• Training-Free Refinement of Flow Matching with Divergence-based Sampling | AC: 3225
• Training-Free Task Classification for Multi-Task Model Merging | AC: 4341
• Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs | AC: 3809
• Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectories | AC: 5786
• Trajectory-aware Cross-view Geo-Localization with Sequential Observations | AC: 5554
• Trajectory-Level Continuous Action Representation for Robotic Manipulation | AC: 4280
• TRaM-VSR: Importance-Aware Token Routing and Merging for One-Step Diffusion Video Super-Resolution | AC: 3546
• TRAM: Finetuning-Free Test-Time Adaptation for Generalized Face Anti-Spoofing with Only a Few Bonafide Samples | AC: 3306
• Transferability Between Understanding and Generation in Unified Multimodal Models | AC: 3137
• Transport Discrepancy as a Reliability Signal for Vision-Language-Action Models | AC: 5621
• TransVLM: A Vision-Language Framework and Benchmark for Detecting Any Shot Transitions | AC: 3199
• TraversRL: Traversable Pedestrian Pathway Generation With Reinforcement Learning | AC: 4528
• TreeSRNF: Square-Root Normal Fields for Generative Modelling of the Geometric and Structural Variability in Tree-like 3D Objects | AC: 4614
• Tri-Efficient Transfer Learning for Point Cloud Videos | AC: 3624
• Triangle Splatting SLAM | AC: 5458
• Triangular Consistency as a Universal Constraint for Learning Optical Flow
• Tricam-rPPG: A Multimodal Multispectral Dataset for remote Photoplethysmography | AC: 5976
• TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields | AC: 5309
• TRiGS: Temporal Rigid-Body Motion for Scalable 4D Gaussian Splatting | AC: 5074
• TriMotion: Modality-Agnostic Camera Control for Video Generation | AC: 3398
• TRINITY: A Multi-Perspective Benchmark for Personal-Style Video Highlight Detection | AC: 5563
• TriO: Tri-Modal Unsupervised Occupancy World Model for Anything Perception | AC: 4951
• TripVVT: A Large-Scale Triplet Dataset and a Coarse-Mask Baseline for In-the-Wild Video Virtual Try-On | AC: 3935
• Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models | AC: 3299
• Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models | AC: 4970
• TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction | AC: 4310
• Trustworthy Image Authentication using Forensic Knowledge Graphs
• TruthLens: Object Hallucination Detection via Self-Evaluating Truthfulness Scores in LVLMs | AC: 3651
• TryOnCrafter: Unleashing Camera Trajectories for Realistic Video Virtual Try-on via a Renderable 4D Try-on Proxy | AC: 3423
• TSEmbed: Unlocking Task Scaling in Universal Multimodal Embeddings | AC: 5034
• Tuning-free Visual Effect Transfer across Videos | AC: 4356
• TurboMPLE: Joint Infrared Turbulence Mitigation and Physical Fields Estimation via Mutual Progressive Layered Extraction | AC: 5610
• Twin-DAgger: Synergizing Digital Twins and Human Corrections for Efficient Robot Manipulation | AC: 5664
• Two Birds, One Projection: Harmonizing Safety and Utility in LVLMs via Inference-time Feature Projection | AC: 4820
• Two-Parameter Flow Map Learning for Continuous-Time Diffeomorphic Image Registration | AC: 5533
• Two-Way Street: Efficient VSLAM using Collaborative In-Sensor and Off-Sensor processing | AC: 4943
• UBone3D: Physics-Rectified Conditional Flow Matching for Anatomical 3D Shape Completion from Ultrasound | AC: 3358
• UC-VLM: Consistency-Driven Learning for AI-Generated Image Detection with Vision-Language Large Models | AC: 5204
• UECP: Uncertainty-Enhanced Collaborative Perception | AC: 5602
• UEval: A Benchmark for Unified Multimodal Generation | AC: 3346
• UF0-6D: Unified Flow-based Zero-Shot 6D Object Pose Estimation without Refinement | AC: 5730
• UHD-MFF: Shattering Barriers in Multi-Focus Ultra-High-Definition Image Fusion via Learnable Lookup Tables
• Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention | AC: 4126
• UltraGen: Efficient Ultra-High-Resolution Image Generation with Hierarchical Local Attention | AC: 3514
• UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models | AC: 4831
• UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priors | AC: 3418
• Unbalanced Optimal Transport for Efficient Visual Document Retrieval | AC: 4715
• Uncertainty-aware tree height change regression | AC: 3782
• Uncertainty-Driven Gaussian Sphere Propagation for 3D Semantic Segmentation | AC: 5330
• Under One Sun: Multi-Object Generative Perception of Materials and Illumination | AC: 4343
• Understanding Cross-Rig Generalization in Automotive Perception: a Multi-Rig Benchmark and Rig Variation Metrics
• Understanding Geometric Representations in Self-Supervised Vision Transformers via Subspace Intervention | AC: 4702
• Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models | AC: 5064
• UNet-Twice: A Simple Structured Reference-based Inpainting Framework | AC: 3442
• Unfold The World: Factorize 4D Properties in Reinforcing Spatial Understanding | AC: 3149
• UniBYD: A Unified Framework for Learning Robotic Manipulation Across Embodiments Beyond Imitation of Human Demonstrations | AC: 4832
• UniCSG: Unified High-Fidelity content-constrained style-driven generation via Staged Semantic and Frequency Disentanglement | AC: 4742
• UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer | AC: 5824
• UniDrive-WM: Unified Understanding, Planning and Generation World Model for Autonomous Driving
• UniDriveDreamer: A Single-Stage Multimodal World Model for Autonomous Driving | AC: 4301
• UniDynamics: Event-RGB Fusion for Unified Future 4D Dynamic Scene Generation | AC: 5685
• Unified and Efficient Point-Line Local Features | AC: 5738
• Unified Backbone Refinement for Diffusion Models via Internal-Latent Analysis | AC: 5816
• Unified Multi-Layer Subspace Modeling for Cross-Domain OOD Detection | AC: 3729
• Unified Multi-plane Autoregressive Diffusion for 3D Multi-Contrast MRI Synthesis | AC: 5224
• Unified Panoramic–Gaussian Representation for Monocular 4D Scene Synthesis | AC: 4215
• Unified Prediction and Planning via Conflict-Aware Disjoint Parameter Training | AC: 4845
• Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipeline | AC: 3348
• Unified Video Dense Prediction from Disjoint Data | AC: 5642
• UniFlow: Zero-Shot LiDAR Scene Flow for Autonomous Driving | AC: 3875
• UniFusion: Sparse-View 4D Reconstruction via Unified Spatio-temporal Depth Alignment | AC: 4596
• Unifying CNNs and ViTs for Learning-Efficient and Scalable Variational AutoEncoder | AC: 5840
• UniGeo: Unifying Geometric Constraints for Camera-Controllable Image Editing via Video Priors | AC: 3886
• UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception | AC: 5645
• UniH3: Unifying Hierarchical Homogeneity and Heterogeneity for All-in-One Medical Image Restoration | AC: 4375
• UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation
• UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction | AC: 4472
• UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer
• UniQueR: Unified Query-based Feedforward 3D Reconstruction | AC: 4973
• UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameters | AC: 5352
• UniREditBench: A Unified Reasoning-based Image Editing Benchmark | AC: 4175
• UniReflect: Self-Reflection Tuning for Unified Multimodal Understanding and Generation | AC: 5043
• UniScale: Arbitrary-Scale Anomaly Generation | AC: 4322
• UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization | AC: 4932
• Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation | AC: 4601
• UniStitch: Unifying Semantic and Geometric Features for Image Stitching | AC: 3646
• UniTac: A Unified Multimodal Model for Cross-Sensor Tactile Understanding and Generation
• UniTeD: Unified Temporal Diffusion for Joint Perception and Planning in Autonomous Driving
• UniTemp: Unlocking Video Generation in Any Temporal Order via Autoregressive Distillation | AC: 5467
• UniTranslator: A Unified Multi-modal Framework for End-to-end In-Image Machine Translation
• UniTriSplat: A Unified 3D Gaussian Splatting Framework with Uniform Spherical Rasterization for Universal Cameras
• Universal Image Immunization against Diffusion-based Image Editing via Semantic Injection
• Unleashing Multimodal Large Language Models for Training-free HOI Detection in the Wild | AC: 5582
• Unleashing the Power of Large-Scale ViT in Zero-Shot SBIR: A Strong Baseline with Multi-Layer Feature Aggregation | AC: 5193
• Unlocking Complex Image Editing via Natively Interleaved Visual Textual CoT with Deep Confidence Reasoning | AC: 5162
• Unlocking Few-Shot Capabilities in LVLMs via Prompt Conditioning and Head Selection | AC: 5510
• Unmasking-Time Visual Calibration for Hallucination Mitigation in Multimodal Discrete Diffusion Language Models | AC: 4427
• Unordered Landmark Visual Navigation | AC: 5727
• Unpaired Geometry-Guided Sim2Real Translation for Autonomous Driving | AC: 5751
• Unsupervised Pixel-Level Semantic Left-Right Understanding of In-the-Wild Images | AC: 4585
• Unsupervised Point Cloud Registration via Training-Time Semantic Guidance | AC: 3865
• Unsupervised Semantic Segmentation Facilitates Model Understanding | AC: 3397
• Unsupervised Source-Free Ranking of Biomedical Segmentation Models Under Distribution Shift | AC: 4464
• Unveiling Transferability in Trajectory Prediction via Latent Scene Embeddings
• Unwarping the Lens: A Physics-Grounded Approach to Video Glasses Removal | AC: 3821
• Urban Boundaries, Social Barriers: A Benchmark and Vision-Centric Framework for Mapping Gated Communities and Equity Implications | AC: 5544
• UrbanAlign: Post-hoc Semantic Calibration for VLM-Human Preference Alignment | AC: 4316
• URHead: A Unified UV-Space Representation for Joint Mesh–3DGS Optimization in Head Avatars | AC: 4747
• URoPE: Universal Relative Position Embedding across Geometric Spaces
• V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising | AC: 3424
• V-HOLD: Stabilizing Flow Trajectories to Rethink the Edit–Preservation Trade-off | AC: 5540
• V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning | AC: 4392
• V-REX: Benchmarking Exploratory Visual Reasoning via Chain-of-Questions | AC: 5985
• Variational Patch Gating for Training-Free Few-Shot Classification | AC: 5331
• VarProtoAD: Variational Prototype-Conditioned Prompting for Zero-Shot Anomaly Detection | AC: 3553
• VC-VAE: Leveraging Video Codecs for Training-Efficient and High-Fidelity Video VAE | AC: 4714
• VCP-DCN: Beyond Visual Concealed Property via Depth Collaborative Network for Camouflaged Object Detection | AC: 4014
• VD-LoRA: Adaptive Reuse of Low-Rank Directions for Continual Learning | AC: 5333
• VDC-Agent: When Video Detailed Captioners Evolve Themselves via Agentic Self-Reflection | AC: 3258
• Vector Scaffolding: Inter-Scale Orchestration for Differentiable Image Vectorization
• VectorReLoc: Reliable Vectorized SD Map Visual Re-localization with Contrastive Feature Alignment | AC: 3610
• VERDICT: Training-Free Step-Wise Verification of Multimodal Reasoning via Disagreement-Aware Consensus | AC: 4674
• Verifying Cancer Segmentation in Vision Transformers via Internal Concepts | AC: 3897
• Vero: Open Reinforcement Learning Recipes for Visual Reasoning | AC: 3269
• Versatile Editing of Video Content, Actions, and Dynamics without Training | AC: 5505
• VersatileMotion: A Unified Framework for Motion Synthesis and Comprehension | AC: 3374
• VersaViT: Enhancing MLLM Vision Backbones via Task-Guided Optimization | AC: 3750
• VERTIGO: Visual Preference Optimization for Cinematic Camera Generation | AC: 4222
• VesselTok: Tokenizing Vessel-like 3D Biomedical Graph Representations for Reconstruction and Generation | AC: 5483
• VGEdit: Unlocking Video Generation Priors for Reasoning-Informed Image Editing | AC: 3271
• VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward | AC: 3500
• VGGT-World: Transforming VGGT into an Autoregressive Geometry World Model | AC: 3788
• ViBe: Ultra-High-Resolution Video Synthesis Born from Pure Images | AC: 3574
• VICAL: Vicinal Consistency Alignment for Long-Tailed Visual Recognition | AC: 5153
• Video Can Teach PAN-Sharpening: PSF-Aware Cross-Domain Supervision | AC: 5524
• Video Generation Models are General-Purpose Vision Learners | AC: 5984
• Video Generation Models Are Inherent Lighting Estimators | AC: 4021
• Video Generative Models as Geometry Learner | AC: 4384
• Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously | AC: 3229
• Video-Holmes: Can MLLM Think like Holmes for Complex Video Reasoning? | AC: 4209
• Video-HolmesV2: Can MLLMs Reason with Spatio-Temporal Audio-Visual Evidence in Long Videos? | AC: 4938
• Video-Oasis: Rethinking Evaluation of Video Understanding | AC: 5179
• Video-Text Alignment Model for Sign Language Translation | AC: 3633
• Video2Reaction: Mapping Video to Audience Reaction Distribution in the Wild | AC: 3525
• VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement
• VideoSfM: Exploiting Temporal Structure for Video-Based Structure-from-Motion | AC: 4576
• VideoTIR: Accurate Understanding for Long Videos with Efficient Tool-Integrated Reasoning | AC: 4726
• VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations | AC: 3595
• ViewFusion: Structured Spatial Thinking Chains for Multi-View Reasoning | AC: 4875
• ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models | AC: 3165
• ViewSplat: View-Adaptive 3D Gaussian Splatting for Feed-Forward Synthesis
• VIGA: View-Conditioned and Identity-Guided Adaptation for Aerial-Ground Person Re-Identification | AC: 5925
• VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignment | AC: 3197
• VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM | AC: 3982
• VIPS: Vehicle-Infrastructure Cooperative Planning Benchmark via Pseudo-Simulation | AC: 3793
• ViQ: Text-Aligned Visual Quantized Representations at Any Resolution
• Virtual Category-Guided Continual Generalized Category Discovery | AC: 5208
• VisCoP: Visual Probing for Video Domain Adaptation of Vision Language Models | AC: 3824
• VisCritic: Visual State Comparison as Process Reward for GUI Agents
• Visible Yet Unrecognizable: Frequency-Selective Facial Privacy via Attention | AC: 5918
• Vision Bridge Transformer at Scale | AC: 3232
• Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning | AC: 3599
• VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting | AC: 4761
• VisNec: Measuring and Leveraging Visual Necessity for Multimodal Instruction Tuning
• VISOR++ : VISUAL INPUT BASED STEERING FOR LARGE VISION LANGUAGE MODELS | AC: 5990
• VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning | AC: 4827
• VisReflect: Latent Visual Reflection for Fine-Grained Perception in Long Visual Context
• VisTa3D: A Dataset and Benchmark for Vision, Tactile, and 3D Point Clouds-based Thin Object Reconstruction | AC: 4285
• Visual Prompt Discovery via Semantic Exploration | AC: 4728
• VisWordBench: Bridging the Gap in Cross-modal Reasoning for Multimodal Large Language Models | AC: 4506
• ViTAL‑X: Video-Text Alignment with Cross‑Modal Temporal Edits | AC: 5949
• Vitality-Aware Compression for Efficient Image-to-Shape Diffusion Transformers
• ViTexQA: A Multi-Frame Temporal Perception Dataset for Video Text Question Answering | AC: 3846
• VIVAS: Vitalizing Visual Perception in VLM Pre-training via Vision-language Unified Autoregressive Supervision | AC: 4767
• VKSR: Scalable Kernel Surface Reconstruction Using Vecchia's Approximation | AC: 4985
• VLA Knows Its Limits: Adaptive Execution Horizons for Robot Policies
• VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking | AC: 4145
• VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model | AC: 3580
• VLA-R1: Enhancing Reasoning in Vision-Language-Action Models | AC: 4862
• VLMSysTrojan: Stealthy System-Aware Backdoor Attacks Against Vision-Language Models | AC: 3928
• VLOD-TTA: Test-Time Adaptation of Vision-Language Object Detectors
• VLTR: Vision-Language Tool Reasoning for Instruction-Guided Image Editing | AC: 5950
• VLZip: Unified Visual and Textual Compression for Interleaved Long-Context Modeling | AC: 5308
• VNC: A Scale-Space Foundation for Learnable 3D Surface Evolution | AC: 5451
• VoCa: Unified Autoregressive Modeling for Talking Audio-Video Generation | AC: 4195
• VOCA: Visual Odometry with Codec Awareness
• VOID: Video Object and Interaction Deletion | AC: 3342
• VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction
• Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding | AC: 5832
• VoxAnchor: Explicit Voxel-Semantic Grounding for Spatial Understanding in Videos | AC: 4848
• VPA-WM: Vision-Priors-Aligned World Models for Robust Visual Reinforcement Learning | AC: 5069
• VQT: Vector Quantization Tuning for Efficient Fine-tuning and Compression of Pre-trained Vision Transformers | AC: 3318
• VSDiffusion: Taming Ill-Posed Shadow Generation via Visibility-Constrained Diffusion | AC: 3690
• VTEdit-Bench: A Comprehensive Benchmark for Multi-Reference Image Editing Models in Virtual Try-On
• Vulnerability of Privacy-Preserving Visual Localization against Diffusion-based Attacks | AC: 4261
• VVSim: A Large-Scale Aerial-Ground Dataset and Benchmark for Cooperative Perception | AC: 4802
• WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching | AC: 3393
• Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs
• Walk through Paintings : Ego-centric World models from Internet Priors | AC: 3734
• Walking in the Implicit: Interactive World Exploration via Neural Scene Representation
• WALL-EVE: World Alignment with Rule Learning in Visual Environments | AC: 4314
• Wan-R1: Verifiable-Reinforcement Learning for Generalizable Video Reasoning | AC: 5896
• WAPR: A Foundation Model for Wide-Angle Refinement in Unseen Object Pose Estimation | AC: 5279
• Warp-free Cross-view Geo-localization via Feature-space Consensus Mining | AC: 4705
• WARP: Wide Attention with Rich Projections for Image Super-Resolution | AC: 4822
• WarpI2I: Image Warping for Image-to-Image Translation
• Wat3R: Underwater 3D Geometry Learning without Underwater Annotations | AC: 5154
• WaterGen: Decoupling Scene and Medium in Underwater Image Generation | AC: 4981
• Wavelet-based Intra-video Counterfactual Reasoning for Video Question Grounding | AC: 5697
• Wavelet-Driven Cross-Domain Consistency for Mixed-Supervised 3D Tumor Segmentation | AC: 3143
• Wavelet-Guided Semantic Signal Compensation for Inversion-Free Image Editing | AC: 5053
• WearWow: Native 2K Multi-Garment Virtual Try-On via Adaptive Token Packing and Preference Alignment | AC: 4590
• Weather-Conditioned Depth Anything | AC: 5620
• WeatherReasonSeg: A Benchmark for Weather-Aware Reasoning Segmentation in Visual Language Models | AC: 4908
• WebEyeTrack: Scalable Eye-Tracking for the Browser via On-Device Few-Shot Personalization | AC: 4136
• WebRetriever: A Large-Scale Comprehensive Benchmark for Efficient Web Agent Evaluation | AC: 5413
• WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing | AC: 4337
• Weight Feedback Computes the Exact Jacobian Transpose in Modern Deep Networks | AC: 4545
• Weight-Space Mixture-of-Experts for Implicit Neural Representation Classification | AC: 4420
• What if? Emulative Simulation with World Models for Situated Reasoning
• What Images Cannot Say: Language-Guided Olfactory Representation Learning | AC: 3554
• What Matters in RL-Based Methods for Object-Goal Navigation? An Empirical Study and A Unified Framework | AC: 5774
• What Moves? Localized Motion Representations for Compositional Scene Control | AC: 3492
• What VGGT Knows About Overlap: Probing Geometric Foundation Models for Co-Visibility | AC: 5911
• What You Ask is What You Ground: Bridging Question Intent to Temporal Evidence for Grounded VideoQA | AC: 3157
• When 3D Gaussian Splatting Recovers Real Surfaces | AC: 5350
• When Cars Have Stereotypes: Auditing Demographic Bias in Objects from Text-to-Image Models | AC: 5904
• When Distillation Breaks Motion Control: Restoring Generative Trajectories for Fast Video Generators | AC: 3640
• When Higher Order Hurts: Pre-Asymptotic Order Collapse in Generative ODE Sampling — A Theory of Discretization–Learning Interaction | AC: 5631
• When Rubrics Fail: Error Enumeration as Reward for Reference-Free RL Post-Training | AC: 5549
• When Sinks Help or Hurt: Unified Framework for Attention Sink in Large Vision-Language Models
• When Specialists Meet Generalists: Segmenter-Coordinated Asymmetric Learning for Label-Deficient Concealed Object Segmentation | AC: 3843
• When the City Teaches the Car: Label-Free 3D Perception from Infrastructure | AC: 4075
• When the Teacher Has More Bits: Self-Teacher Latent Distillation for Learned Image Compression | AC: 4556
• When Thinking Hurts: Mitigating Visual Forgetting in Video Reasoning via Frame Repetition | AC: 4218
• When Token Compression Breaks: Structural Pruning vs. Token Reduction for Robust ViT Segmentation under High Compression | AC: 5746
• When W4A4 Breaks Camouflaged Object Detection: Token-Group Dual-Constraint Activation Quantization | AC: 3996
• Whence the Voice? Self-supervised Dual-source Audio-Visual Localisation via Selective Convergence | AC: 4648
• Where and What: Long-Term Object Tracking in Egocentric Videos | AC: 3987
• Where to Look Matters: Learning Influential Views for VLM-based 3D Visual Grounding | AC: 5244
• Which Layer Causes Distribution Deviation? Entropy-Guided Adaptive Pruning for Diffusion and Flow Models | AC: 5529
• White Aggregation and Restoration for Few-shot 3D Point Cloud Semantic Segmentation | AC: 4810
• Who Does What and Where to Go: Orthogonal Alignment and Hierarchical Planning for Multi-Entity Trajectories | AC: 4760
• Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decoding | AC: 5552
• Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition | AC: 3461
• Why Do Vision Language Models Struggle To Recognize Human Emotions? | AC: 5341
• Why Far Looks Up: Probing Spatial Representation in Vision-Language Models | AC: 5463
• Why Feature Magnitude Deceives OOD Detectors: An Angular Separation Perspective | AC: 4401
• Why Linear Probing Works: Non-Vacuous Generalization Bounds via Effective Dimension | AC: 5959
• Wid3R: Wide Field-of-View 3D Reconstruction via Camera Model Conditioning | AC: 5473
• WiFi-JEPA: Self-supervised Learning for WiFi-CSI 3D Human Pose Estimation | AC: 5874
• WiFlow: Estimating Optical Flow using WiFi Channel State Information | AC: 3389
• WildCity: A Real-World Dataset for City-Scale Rendering and Beyond | AC: 5054
• WildDepth: A Multimodal Dataset for 3D Wildlife Perception and Depth Estimation | AC: 5827
• WildProp: Visual Estimation of Wildlife Body Proportions at Scale | AC: 3587
• WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images | AC: 4603
• WildWorld: A Large-Scale Dataset for Action-Conditioned World Modeling with Explicit State Annotations | AC: 5427
• WilLaGS: Latent-Conditional 3D Appearance Fields for Robust Gaussian Splatting In-the-Wild | AC: 5306
• WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens | AC: 4781
• World Knowledge in the Weights: Reading Concept Circuits of Vision Transformers | AC: 4949
• World Models for Learning Dexterous Hand-Object Interactions from Human Videos | AC: 5625
• World Reconstruction From Inconsistent Views | AC: 3497
• World-in-Loop: Online Correction via Event-Triggered World Models for Robust VLA Policies | AC: 4231
• WorldAgents: Can Foundation Image Models be Agents for 3D World Models? | AC: 5821
• WorldCache: Content-Aware Caching for Accelerated Video World Models | AC: 5908
• WorldFlow3D: Flowing Through 3D Distributions for Unbounded World Generation | AC: 4564
• WorldMesh: Generating Navigable Multi-Room 3D Scenes via Mesh-Conditioned Image Diffusion | AC: 4808
• WorldWander: Bridging Egocentric and Exocentric Worlds in Video Generation | AC: 4650
• WristMimic: Full-Body Humanoid Control with Wrist-Guided Manipulation | AC: 5090
• X-SG2S: Safe and Generalizable Gaussian Splatting with X-dimensional Watermarks | AC: 5800
• X-Stream: Benchmarking MLLMs as Multiplexers for Multi-Stream Understanding | AC: 3686
• X2SAM: Any Segmentation in Images and Videos | AC: 3911
• XDen-1K: A Density Field Dataset of Real-World Objects | AC: 3952
• XPos3R: Cross-Modal Transformer for Intraoperative 2D/3D Registration | AC: 4332
• XSemanticFlow: Cross Object Semantic Alignment for Zero-shot Manipulation | AC: 3733
• XSurfer: Reconstructing surface meshes of cerebral and cerebellar cortex from diverse MRI data using untrained neural networks | AC: 4957
• XYZ-IBD: Benchmarking Robust 6D Object Pose Estimation under Real-World Industrial Complexity | AC: 3426
• Y-diff: Structure-Texture Decoupled Diffusion Distillation for H&E-to-pCLE Translation | AC: 5229
• YesTrack: Referring Multi-Object Tracking via MLLM-based Yes/No Reasoning | AC: 3914
• YeTI: You Only Need Two Noisy Images for Real-World sRGB Noise Generation | AC: 5744
• Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation
• YouTube-Occ: Learning Indoor 3D Semantic Occupancy Prediction from YouTube Videos | AC: 4091
• ZAP: Zero-Shot Assembly Planning with Large Language Models | AC: 5872
• Zero-Shot Depth from Defocus: 从对焦堆栈零样本估计度量深度
• Zero-Shot Image Personalization from Personas | AC: 5327
• Zero-Shot Inference-Time Rectification for Real-World Arbitrary-Scale Super-Resolution | AC: 4685
• Zero-Shot Novel Depth Synthesis Using Foundation Models Scene Representations | AC: 5491
• ZeroSplat: Generalized Referring Segmentation in 3D Gaussian Splatting | AC: 3373
• ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device | AC: 5935
• ZMIS-SAM: Segment Anything Model Enhanced With Wavelet Transform For Zooplankton Microscopy Image Instance Segmentation | AC: 4597
• Zoom-IQA: Image Quality Assessment with Reliable Region-Aware Reasoning | AC: 4206
• ZTRS: Zero-Human Demonstration End-to-end Autonomous Driving with Trajectory Scorer | AC: 4135
• λSplit: Self-Supervised Content-Aware Spectral Unmixing for Fluorescence Microscopy | AC: 4844
• μFlow: Leveraging Average Images for Improving Generalisation of Deepfake Faces Detectors | AC: 5525
• Φeat: Physically-Grounded Material Feature Representation | AC: 4415
• 基于扰动高斯集合的层析成像主动视角选择
• 无滤波快照高光谱成像：基于引导Patch扩散模型
• 混合事件-帧传感器：统一噪声建模、标定与仿真
• MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE | AC: 5603
• Visual Spatial Tuning | AC: 4687
• RL from Physical Feedback: Aligning Large Motion Models with Humanoid Control | AC: 5820
• PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference | AC: 5763
• GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding | AC: 5780
• One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policies | AC: 5978