The full list of 4,067 papers accepted at CVPR 2026 (IEEE/CVF Conference on Computer Vision and Pattern Recognition) . Click any title for details, similar papers, and links to the original source. You can also search these papers by meaning , not just keywords. $L^{2}DGS$: Low-Light Dynamic Gaussian Splatting accepted $\alpha$Matte4K & $\mu$Matting: Dataset and Model for Ultra-Micro Precision Alpha Video Matting accepted $\oslash$ Source Models Leak What They Shouldn't $\nrightarrow$: Unlearning Zero-Shot Transfer in Domain Adaptation Through Adversarial Optimization accepted $\phi$-DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Models accepted 2-Shots in the Dark: Low-Light Denoising with Minimal Data Acquisition accepted 240FPS Stereo Vision from Monocular Mixed Spikes accepted 2D-LFM: Lifting Foundation Model without 3D Supervision accepted 2ndMatch: Finetuning Pruned Diffusion Models via Second-Order Jacobian Matching accepted 3D Gaussian Splatting at Arbitrary Resolutions with Compact Proxy Anchors accepted 3D Gaussian Splatting from Unposed Spike Stream accepted 3D Gaussian Splatting with Self-Constrained Priors for High Fidelity Surface Reconstruction accepted 3D Space as a Scratchpad for Editable Text-to-Image Generation accepted 3D sans 3D Scans: Scalable Pre-training from Video-Generated Point Clouds accepted 3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation accepted 3D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understanding accepted 3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image accepted 3D-IDE: 3D Implicit Depth Emergent accepted 3D-LATTE: Latent Space 3D Editing from Textual Instructions accepted 3D-Object Perception Transformer (3PT) accepted 3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding accepted 3DReflecNet: A Large-Scale Dataset for 3D Reconstruction of Reflective, Transparent, and Low-Texture Objects accepted 3DrawAgent: Teaching LLM to Draw in 3D with Early Contrastive Experience accepted 3M-TI: High-Quality Mobile Thermal Imaging via Calibration-free Multi-Camera Cross-Modal Diffusion accepted 4C4D: 4 Camera 4D Gaussian Splatting accepted 4D Local Modeling Toward Dynamic Global Perception for Ambiguity-free Rotation-Invariant Point Cloud Analysis accepted 4D Primitive-Mache: Glueing Primitives for Persistent 4D Scene Reconstruction accepted 4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation accepted 4DEquine: Disentangling Motion and Appearance for 4D Equine Reconstruction from Monocular Video accepted 4DP-QA: Scalable QA for 4D Perception in Vision Language Models accepted 4DSurf: High-Fidelity Dynamic Scene Surface Reconstruction accepted 4DWorldBench: A Comprehensive Evaluation Framework for 3D/4D World Generation Models accepted A Bit is All You Need! Efficient Video Capture via Single Bit Imaging accepted A Causal Marriage between VLM and IRM from Understanding to Reasoning accepted A Closed-Form Solution for Debiasing Vision-Language Models with Utility Guarantees Across Modalities and Tasks accepted A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helps accepted A Combination of Noise and Bilateral Filters Achieve Supralinear and Scalable Adversarial Robustness in CNNs accepted A Cross-view Fusion Framework for Robust 6-DoF Grasp Pose Estimation accepted A Debiased Reconstruction-based Framework for Training-Free Detection of AI-Generated Images accepted A Difference-in-Difference Approach to Detecting AI-Generated Images accepted A Faster Path to Continual Learning accepted A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens accepted A Geometric Algebra-Informed 3DGS Framework for Wireless Channel Prediction accepted A Mixed Diet Makes DINO An Omnivorous Vision Encoder accepted A More Word-like Image Tokenization for MLLMs accepted A Multi-Agent Perception-Action Alliance for Efficient Long Video Reasoning accepted A Polynomial Chaos Framework for Causal Discovery in Nonlinear Uncertain Systems accepted A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large Vision-Language Models accepted A Sanity Check for Multi-In-Domain Face Forgery Detection in the Real World accepted A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generation accepted A Semantically Disentangled Unified Model for Multi-category 3D Anomaly Detection accepted A Stitch in Time: Learning Procedural Workflow via Self-Supervised Plackett-Luce Ranking accepted A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Space accepted A Supervised Multi-task Framework for Joint cryo-ET Restoration Enabled by Generative Physical Simulation accepted A Temporal and Content Co-Awareness Latent Diffusion for Controllable Hand Image Generation accepted A Training-Free Style-Personalization via SVD-Based Feature Decomposition accepted A Unified Framework for Knowledge Transfer in Bidirectional Model Scaling accepted A Unified Perspective on Adversarial Membership Manipulation in Vision Models accepted A2GC: Asymmetric Aggregation with Geometric Constraints for Locally Aggregated Descriptors accepted A3: Towards Advertising Aesthetic Assessment accepted ACE-Merging: Data-Free Model Merging with Adaptive Covariance Estimation accepted ACPV-Net: All-Class Polygonal Vectorization for Seamless Vector Map Generation from Aerial Imagery accepted ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models accepted AD-GBC: Anisotropic Granular-Ball Skip-Connection Refiner for UNet-Based Medical Image Segmentation accepted ADSeeker: A Knowledge-Grounded Reasoning Framework for Industry Anomaly Detection and Reasoning accepted AE2VID: Event-based Video Reconstruction via Aperture Modulation accepted AERGS-SLAM: Auto-Exposure-Robust Stereo 3D Gaussian Splatting SLAM accepted AG-VAS: Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models accepted AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions accepted AGFT: Alignment-Guided Fine-Tuning for Zero-Shot Adversarial Robustness of Vision-Language Models accepted AGiLe: Learning Robust Long-Horizon Manipulation via Affordance-Grounded Bidirectional Latent Planning accepted AHS: Adaptive Head Synthesis via Synthetic Data Augmentations accepted AIMDepth: Asymmetric Image-Event Mamba for Monocular Depth Estimation accepted AKCMamba-YOLO: Selective State Space Models For Real-Time Object Detection accepted ALLNet: Multi-task Dense Prediction for Degraded Images accepted AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend accepted AMap: Distilling Future Priors for Ahead-Aware Online HD Map Construction accepted AMusE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding accepted ANTS: Adaptive Negative Textual Space Shaping for OOD Detection via Test-Time MLLM Understanding and Reasoning accepted APEX: A Decoupled Memory-based Explorer for Asynchronous Aerial Object Goal Navigation accepted APPO: Attention-guided Perception Policy Optimization for Video Reasoning accepted AR2-4FV: Anchored Referring and Re-identification for Long-Term Grounding in Fixed-View Videos accepted ARC Is a Vision Problem! accepted AREA3D: Active Reconstruction Agent with Unified Feed-Forward 3D Perception and Vision-Language Guidance accepted ARES: Unifying Asymmetric RGB-Event Stereo for Probabilistic Scene Flow Estimation accepted ARGUS: Defending Against Multimodal Indirect Prompt Injection via Steering Instruction-Following Behavior accepted ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning accepted ARMFlow: AutoRegressive MeanFlow for Online 3D Human Reaction Generation accepted ART: Articulated Reconstruction Transformer accepted AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Models accepted AToken: A Unified Tokenizer for Vision accepted AURA: Multi-modal Shared Autonomy for Urban Navigation accepted AV-Reasoner: Improving and Benchmarking Clue-Grounded Audio-Visual Counting for MLLMs accepted AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models accepted AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention accepted AVATAR: Reinforcement Learning to See, Hear, and Reason Over Video accepted AVFakeBench: A Comprehensive Audio-Video Forgery Detection Benchmark for AV-LMMs accepted AVGGT: Rethinking Global Attention for Accelerating VGGT accepted AVION: Aerial Vision-Language Instruction from Offline Teacher to Prompt-Tuned Network accepted AXG-Reasoner: Error Detection and Explanation in Long Task Videos with Vision-Language Models accepted Abstract 3D Perception for Spatial Intelligence in Vision-Language Models accepted AcTTA: Rethinking Test-Time Adaptation via Dynamic Activation accepted Accelerating Autoregressive Video Diffusion via History-Guided Cache and Residual Correction accepted Accelerating Diffusion Model Training under Minimal Budgets: A Condensation-Based Perspective accepted Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance Scheduling accepted Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep accepted Accelerating Streaming Video Large Language Models via Hierarchical Token Compression accepted AceTone: Bridging Words and Colors for Conditional Image Grading accepted Act Like a Pathologist: Tissue-Aware Whole Slide Image Reasoning accepted Act2See: Emergent Active Visual Perception for Video Reasoning accepted ActAvatar: Temporally-Aware Precise Action Control for Talking Avatars accepted Action Motifs: Self-Supervised Hierarchical Representation of Human Body Movements accepted Action-Geometry Prediction with 3D Geometric Prior for Bimanual Manipulation accepted Action-Sketcher: From Reasoning to Action via Visual Sketches for Robotic Manipulation accepted ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion accepted Activation Matters: Test-time Activated Negative Labels for OOD Detection with Vision-Language Models accepted Active Inference for Micro-Gesture Recognition: EFE-Guided Temporal Sampling and Adaptive Learning accepted Active Intelligence in Video Avatars via Closed-loop World Modeling accepted Active Perceptual Inference: A Corticothalamic-Inspired Dynamic Nested Recurrent Network for Multimodal Sentiment Analysis with Incomplete Data accepted ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving accepted ActiveGrasp: Information-Guided Active Grasping with Calibrated Energy-based Model accepted ActivePolicy: Active Gaussian Reconstruction and Optimization Strategy Based on Global-Local Information Gain accepted ActiveVLA: Injecting Active Perception into Vision-Language-Action Models for Precise 3D Robotic Manipulation accepted ActivityForensics: A Comprehensive Benchmark for Localizing Manipulated Activity in Videos accepted AdaBet: Gradient-free Layer Selection for Efficient Training of Deep Neural Networks accepted AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation accepted AdaDexTrack: Dynamic Modulation for Adaptive and Generalizable Dexterous Manipulation Tracking accepted AdaIAT: Adaptively Increasing Attention to Generated Text to Alleviate Hallucinations in LVLM accepted AdaPrior: Bayesian-Inspired Adaptive Prior Correction for Long-Tailed Continual Learning accepted AdaRadar: Rate Adaptive Spectral Compression for Radar-based Perception accepted AdaSFormer: Adaptive Serialized Transformers for Monocular Semantic Scene Completion from Indoor Environments accepted AdaSVD: Singular Value Decomposition with Adaptive Mechanisms for Large Multimodal Models accepted AdaSpark: Adaptive Sparsity for Efficient Long-Video Understanding accepted AdaSpot: Spend Resolution Where It Matters for Precise Event Spotting accepted AdapAction: Adaptive Target Action Backdoor Attack against GUI Agents accepted AdapTok: Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Space accepted AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition accepted Adapter Shield: A Unified Framework with Built-in Authentication for Preventing Unauthorized Zero-Shot Image-to-Image Generation accepted Adapting In-context Generation for Enhanced Composed Image Retrieval accepted Adapting Lightweight Image-based Counting Models for Video Crowd Counting accepted Adapting Point Cloud Analysis via Multimodal Bayesian Distribution Learning accepted Adapting a Pre-trained Single-Cell Foundation Model to Spatial Gene Expression Generation from Histology Images accepted Adaptive 3D Perception for Small Aerial Targets Under Sparse Sampling via Reinforcement Learning accepted Adaptive Action Chunking at Inference-time for Vision-Language-Action Models accepted Adaptive Anisotropic Gaussian Splatting for Multi-contrast MRI Arbitrary-Scale Super-Resolution with Anatomy Guidance accepted Adaptive Auxiliary Prompt Blending for Target-Faithful Diffusion Generation accepted Adaptive Bayesian Early-Exit Networks for Efficient Non-Transferable Learning accepted Adaptive Capacity Autoregressive Visual Tracking accepted Adaptive Confidence Regularization for Multimodal Failure Detection accepted Adaptive Data Augmentation with Multi-armed Bandit: Sample-Efficient Embedding Calibration for Implicit Pattern Recognition accepted Adaptive Depth Lightweight RGB-T Tracking with Holistic Token Routing accepted Adaptive Learned Image Compression with Graph Neural Networks accepted Adaptive Spatial-Temporal Window: Unlocking the Potential of Event Cameras in Heterogeneous Velocity Scenarios accepted Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration accepted Adaptive Video Distillation: Mitigating Oversaturation and Temporal Collapse in Few-Step Generation accepted Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learning accepted AdvFM: Lookahead Flow-Matching Velocity-Field Attacks for Imperceptible and Transferable Adversarial Examples accepted Advancing Cancer Prognosis with Hierarchical Fusion of Genomic, Proteomic and Pathology Imaging Data from a Systems Biology Perspective accepted Advancing Image Classification with Discrete Diffusion Classification Modeling accepted Adversarial Style Optimization: Enhancing VLM Jailbreaks by GRPO-based Stylistic Triggers Optimization accepted AeroAgent: A Vision-Physics-Decision Framework for Aerodynamic Vehicle Design accepted AeroDGS: Physically Consistent Dynamic Gaussian Splatting for Single-Sequence Aerial 4D Reconstruction accepted AeroGS: Scale-Aware Gaussian Splatting for Pose-Free Dynamic UAV Scene Reconstruction accepted Aesthetic Camera Viewpoint Suggestion with 3D Aesthetic Field accepted Affine Perspective-Three-Point Problem accepted AffordGen: Generating Diverse Demonstrations for Generalizable Object Manipulation with Affordance Correspondence accepted AffordGrasp: Cross-Modal Diffusion for Affordance-Aware Grasp Synthesis accepted AffordMatcher: Affordance Learning in 3D Scenes from Visual Signifiers accepted Affordance Field Intervention: Enabling VLAs to Escape Memory Traps in Robotic Manipulation accepted Affordance-First Decomposition for Continual Learning in Video-Language Understanding accepted Affostruction: 3D Affordance Grounding with Generative Reconstruction accepted Agent4FaceForgery: Multi-Agent LLM Framework for Realistic Face Forgery Detection accepted AgentDet: A Shared-Blackboard Multi-Agent Framework for Zero-/Few-Shot Object Detection accepted Agentic Retoucher for Text-To-Image Generation accepted Agentic Video Summarization via Self-Reflecting Multimodal Understanding accepted Agile Deliberation: Concept Deliberation for Subjective Visual Classification accepted Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval accepted AirSim360: A Panoramic Simulation Platform within Drone View accepted AlcheMinT: Fine-grained Temporal Control for Multi-Reference Consistent Video Generation accepted Alert-CLIP: Abnormality-aware Latent-Enhanced Representation Tuning of CLIP for Video Anomaly Detection accepted Align Images Before You Generate accepted Align Once to Explain: Feature Alignment for Scalable B-cosification of Foundational Vision Transformers accepted Align While Search: Belief-Guided Exploratory Inference for World-Grounded Embodied Agents accepted AlignPose: Generalizable 6D Pose Estimation via Multi-view Feature-metric Alignment accepted Aligning Multi-Character Narrative Image Generation with Multi-Aspect Human Preferences accepted Aligning Text, Images and 3D Structure Token-by-Token accepted Aligning What Vision-Language Models See and Perceive with Adaptive Information Flow accepted All Roads Lead to Rome: Incentivizing Divergent Thinking in Vision-Language Models accepted All Vehicles Can Lie: Efficient Adversarial Defense in Fully Untrusted-Vehicle Collaborative Perception via Pseudo-Random Bayesian Inference accepted All in One: Unifying Deepfake Detection, Tampering Localization, and Source Tracing with a Robust Landmark-Identity Watermark accepted All-in-One Slider for Attribute Manipulation in Diffusion Models accepted An Efficient Token Compression Framework for Visual Object Tracking accepted An Empirical Study on How Video-LLMs Answer Video Questions accepted An Instance-Centric Panoptic Occupancy Prediction Benchmark for Autonomous Driving accepted An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning accepted Anatomica: Localized Control over Geometric and Topological Properties for Anatomical Diffusion Models accepted Anatomical Domain Shifts: Test-time Heterogeneous Adaptation for 3D Human Pose Prediction accepted Anchor-Guided Gradient Alignment for Incomplete Multimodal Learning accepted AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned Flows accepted AnchorSplat: Feed-Forward 3D Gaussian Splatting With 3D Geometric Priors accepted Anchoring and Rescaling Attention for Semantically Coherent Inbetweening accepted Anchoring the Mind of Multimodal Reasoners: Cognitive Bias as a Vector for Jailbreak Attacks accepted Ani3DHuman: Photorealistic 3D Human Animation with Self-guided Stochastic Sampling accepted AniMimic: Imitating 3D Animation from Video Priors accepted Animator-Centric Skeleton Generation on Objects with Fine-Grained Details accepted Annotation-Efficient Coreset Selection for Context-dependent Segmentation accepted Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization accepted Anomaly-Related Residual Fields for Cross-domain Anomaly Detection accepted AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors accepted AnthroTAP: Learning Point Tracking with Real-World Motion accepted Anti-Degradation Lifelong Multi-View Clustering accepted Anti-I2V: Safeguarding your Photos from Malicious Image-to-video Generation accepted AntiStyler: Defending Object Detection Models Against Adversarial Patch Attacks Using Style Removal accepted Any Resolution Any Geometry: From Multi-View To Multi-Patch accepted Any2Any 3D Diffusion Models with Knowledge Transfer: A Radiotherapy Planning Study accepted Any4D: Unified Feed-Forward Metric 4D Reconstruction accepted AnyDoc: Enhancing Document Generation via Large-Scale HTML/CSS Data Synthesis and Height-Aware Reinforcement Optimization accepted AnyID: Ultra-Fidelity Universal Identity-Preserving Video Generation from Any Visual References accepted AnyLift: Scaling Motion Reconstruction from Internet Videos via 2D Diffusion accepted AnyPcc: Compressing Any Point Cloud with a Single Universal Model accepted ApET: Approximation-Error Guided Token Compression for Efficient VLMs accepted Ar2Can: An Architect and an Artist Leveraging a Canvas for Multi-Human Generation accepted Arcadia: Toward a Full-Lifecycle Framework for Embodied Lifelong Learning accepted ArchSym: Detecting 3D-Grounded Architectural Symmetries in the Wild accepted Archon: A Unified Multimodal Model for Holistic Digital Human Generation accepted Are Image-to-Video Models Good Zero-Shot Image Editors? accepted Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation accepted ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactions accepted ArtLLM: Generating Articulated Assets via 3D LLM accepted ArtPro: Self-Supervised Articulated Object Reconstruction with Adaptive Integration of Mobility Proposals accepted ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding accepted Artiverse: A Diverse and Physically Grounded Dataset for Articulated Objects accepted Asking like Socrates: Socrates helps VLMs understand remote sensing images accepted AssemblyBench: Physics-Aware Assembly of Complex Industrial Objects accepted Assignment-Driven Hash Learning in a Hyper-Semantic Space for On-the-Fly Category Discovery accepted AstraNav-Memory: Contexts Compression for Long Memory accepted AsymLoc: Towards Asymmetric Feature Matching for Efficient Visual Localization accepted Asynchronous Temporal Modeling with Two-Agent Framework for Streaming Dense Video Captioning accepted AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robots accepted Attack for Defense: Adversarial Agents for Point Prompt Optimization Empowering Segment Anything Model accepted Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing accepted Attention Surgery: An Efficient Recipe to Linearize Your Video Diffusion Transformer accepted Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models accepted Attention-aware Inference Optimizations for Large Vision-Language Models with Memory-efficient Decoding accepted Attribute-Preserving Pseudo-Labeling for Diffusion-Based Face Swapping accepted Attribution as Retrieval: Model-Agnostic AI-Generated Image Attribution accepted Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors accepted Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner accepted AudioAvatar: Personalized Audio-driven Whole-body Talking Avatars accepted AudioStory: Generating Long-Form Narrative Audio with Large Language Models accepted Authorize-on-Demand: Dynamic Authorization with Legality-Aware Intellectual Property Protection for VLMs accepted AutoCut: End-to-end advertisement video editing based on multimodal discretization and controllable generation accepted AutoDebias: An Automated Framework for Detecting and Mitigating Backdoor Biases in Text-to-Image Models accepted AutoRegressive Generation with B-rep Holistic Token Sequence Representation accepted AutoTraces: Autoregressive Trajectory Forecasting via Multimodal Large Language Models accepted Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation accepted AvatarPointillist: AutoRegressive 4D Gaussian Avatarization accepted AviaSafe: A Physics-Informed Data-Driven Model for Aviation Safety-Critical Cloud Forecasts accepted AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation accepted B$^3$-Seg: Camera-Free, Training-Free 3DGS Segmentation via Analytic EIG and Beta-Bernoulli Bayesian Updates accepted BA-GS: Bayesian Adaptive Gaussian Splatting for SFM-Free 3D Reconstruction accepted BALM: A Model-Agnostic Framework for Balanced Multimodal Learning under Imbalanced Missing Rates accepted BAMI: Training-Free Bias Mitigation in GUI Grounding accepted BAgger: Backwards Aggregation for Mitigating Drift in Autoregressive Video Diffusion Models accepted BD-Merging: Bias-Aware Dynamic Model Merging with Evidence-Guided Contrastive Learning accepted BDNet:Bio-Inspired Dual-Backbone Small Object Detection Network accepted BEA-GS: BEyond RAdiance Supervision in 3DGS for Precise Object Extraction accepted BEV-CAR: Enhancing Monocular Bird's Eye View Segmentation with Context-Aware Rasterization accepted BEV-SLD: Self-Supervised Scene Landmark Detection for Global Localization with LiDAR Bird's-Eye View Images accepted BHCast: Unlocking Black Hole Plasma Dynamics from a Single Blurry Image with Long-Term Forecasting accepted BIT: Matching-based Bi-directional Interaction Transformation Network for Visible-Infrared Person Re-Identification accepted BOP-ASK: Object-Interaction Reasoning for Vision-Language Models accepted BUSSARD: Normalizing Flows for Bijective Universal Scene-Specific Anomalous Relationship Detection accepted BabyVLM-V2: Toward Developmentally Grounded Pretraining and Benchmarking of Vision Foundation Models accepted Back to Basics: Let Denoising Generative Models Denoise accepted Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection accepted Back to Source: Open-Set Continual Test-Time Adaptation via Domain Compensation accepted Back to the Feature: Explaining Video Classifiers with Video Counterfactual Explanations accepted BackSplit: The Importance of Sub-dividing the Background in Biomedical Lesion Segmentation accepted Balanced Dataset Distillation via Modeling Multiple Visual Pattern Distribution accepted Balanced Hierarchical Contrastive Learning with Decoupled Queries for Fine-grained Object Detection in Remote Sensing Images accepted BarbieGait: An Identity-Consistent Synthetic Human Dataset with Versatile Cloth-Changing for Gait Recognition accepted Basis-Oriented Low-rank Transfer for Few-Shot and Test-Time Adaptation accepted Batch Loss Score for Dynamic Data Pruning accepted Batman: Benign Knowledge Alignment Through Malicious Null Space in Federated Backdoor Attack accepted Bayesian Decomposition and Semantic Completion for Few-shot Semantic Segmentation accepted BeautyGRPO: Aesthetic Alignment for Face Retouching via Dynamic Path Guidance and Fine-Grained Preference Modeling accepted Benchmarking Endoscopic Surgical Image Restoration and Beyond accepted Benchmarking PhD-Level Coding in 3D Geometric Computer Vision accepted Benchmarking Single-Factor Physical Video-to-Audio Generation accepted Best Segmentation Buddies for Image-Shape Correspondence accepted Better than Average: Spatially-Aware Aggregation of Segmentation Uncertainty Improves Downstream Performance accepted Better, Stronger, Faster: Tackling the Trilemma in MLLM-based Segmentation with Simultaneous Textual Mask Prediction accepted Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning accepted Beyond Appearance: Camouflaged Object Detection via Geometric Structure accepted Beyond Binary Contrast: Modeling Continuous Skeleton Action Spaces with Transitional Anchors accepted Beyond Caption-Based Queries in Video Moment Retrieval accepted Beyond Duality: A Hybrid Framework of Leveraging Shared and Private Features for RGB-Event Object Detection accepted Beyond Endpoints: Path-Centric Reasoning for Vectorized Off-Road Network Extraction accepted Beyond Euclidean Gossip: KL-Barycentric Consensus on Heterogeneous and Imbalanced Images accepted Beyond Explicit Language: Plug-and-Play Visual-to-Linguistic Modeling Toward General Object Tracking accepted Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models accepted Beyond Geometry: Artistic Disparity Synthesis for Immersive 2D-to-3D accepted Beyond Global Similarity: Multi-Conditional Retrieval for Fine-Grained Cross-Modal Understanding accepted Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter accepted Beyond Ground-Truth: Leveraging Image Quality Priors for Real-World Image Restoration accepted Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognition accepted Beyond Layer-Wise Merging: Chain-of-Merging for Vision-Language Models accepted Beyond Matching to Tiles: Bridging Unaligned Aerial and Satellite Views for Vision-Only UAV Navigation accepted Beyond Mimicry: Learning Whole-Body Human-Humanoid Interaction from Human-Human Demonstrations accepted Beyond Missing Modalities: Hypergraph Conditioned Diffusion for Uncertainty-Aware Multimodal Emotion Recognition accepted Beyond Multiple Choice: Verifiable OpenQA for Robust Vision-Language RFT accepted Beyond Myopic Alignment: Lookahead Optimization for Online Class-Incremental Learning accepted Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification accepted Beyond Patches: Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation accepted Beyond Perceptual Shortcuts: Causal-Inspired Debiasing Optimization for Generalizable Video Reasoning in Lightweight MLLMs accepted Beyond Pixel Simulation: Pathology Image Generation via Diagnostic Semantic Tokens and Prototype Control accepted Beyond Prompt Degradation: Prototype-guided Dual-pool Prompting for Incremental Object Detection accepted Beyond Reassembly: Fractured Object Recovery with Missing Parts accepted Beyond Rule-Based Agents: Active Markov Games for Realistic Multi-Agent Interaction in Autonomous Driving accepted Beyond Scanpaths: Graph-Based Gaze Simulation in Dynamic Scenes accepted Beyond Semantic Search: Towards Referential Anchoring in Composed Image Retrieval accepted Beyond Sequential Tools: A Unified VLM Agent System for Photographic Post-Processing via Dynamic Multi-Expert Fusion accepted Beyond Single Images: A Comprehensive Benchmark for Album-Level Vision-Language Understanding accepted Beyond Single Solution: Multi-Hypothesis Deep Unfolding Network for Image Compressive Sensing accepted Beyond Single-View Sufficiency: CVBench for Cross-View Human Understanding accepted Beyond Soft Label: Dataset Distillation via Orthogonal Gradient Matching accepted Beyond Static Frames: Temporal Aggregate-and-Restore Vision Transformer for Human Pose Estimation accepted Beyond Strict Pairing: Arbitrarily Paired Training for High-Performance Infrared and Visible Image Fusion accepted Beyond Success: Refining Elegant Robot Manipulation from Mixed-Quality Data via Just-in-Time Intervention accepted Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration accepted Beyond Text: Visual Description Assembly by Probabilistic Model for CLIP-based Weakly Supervised Semantic Segmentation accepted Beyond Tie Points: Satellite Image Block Adjustment based on Dense Feature Consistency accepted Beyond Top Activations: Efficient and Reliable Crowdsourced Evaluation of Automated Interpretability accepted Beyond Weak Supervision: MLLMs-Guided Graded Knowledge Distillation for Unsupervised Camouflaged Object Detection accepted Beyond What's Shared: Recovering Lost Unique Information from Intermediate Layers to Boost Multimodal Geo-Foundation Models accepted Beyond [CLS] Token: Query-Driven Token-Level Forgery Purification for Generalizable Deepfake Detection accepted Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations accepted Beyond the Golden Data: Resolving the Motion-Vision Quality Dilemma via Timestep Selective Training accepted Beyond the Ground Truth: Enhanced Supervision for Image Restoration accepted Beyond the Static World: Continual Category Discovery under Visual Drift accepted Beyond the Static-World: Lifelong Learning for All-in-One Medical Image Restoration accepted Bezier Degradation Modeling for LiDAR-based Human Motion Capture accepted Bi-Bridge: Bidirectional Diffusion Bridges for Low-Light Image Enhancement accepted Bi-directional Autoregressive Diffusion for Large Complex Motion Interpolation accepted BiEvLight: Bi-level Learning of Task-Aware Event Refinement for Low-Light Image Enhancement accepted BiFM: Bidirectional Flow Matching for Few-Step Image Editing and Generation accepted BiGMINT: Biologically-guided Hierarchical Multimodal Integration for Modeling Multiple Compound Activities in Drug Discovery accepted BiGain: Unified Token Compression for Joint Generation and Classification accepted BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generation accepted BiOTPrompt: Bidirectional Optimal Transport Guided Prompting for Disease Evolution-aware Radiology Report Generation accepted BiPA: Bilevel Prompt Adaptation for Underwater Instance Segmentation accepted BiPreManip: Learning Affordance-Based Bimanual Preparatory Manipulation through Anticipatory Collaboration accepted BiProLoRA: Bilevel Prompt LoRA for Real Scene Recovery accepted Bias In, Bias Out? Finding Unbiased Subnetworks in Vanilla Models accepted Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models accepted Bias at the End of the Score accepted Bidirectional Cross-Modal Prompting for Event-Frame Asymmetric Stereo accepted Bidirectional Multimodal Prompt Learning with Scale-Aware Training for Few-Shot Multi-Class Anomaly Detection accepted Bidirectional Normalizing Flow: From Data to Noise and Back accepted Bidirectional Query-Driven Generation of Parametric CAD Sketch accepted Bilevel Layer-Positioning LoRA for Real Image Dehazing accepted BinaryAttention: One-Bit QK-Attention for Vision and Diffusion Transformers accepted BioVITA: Biological Dataset, Model, and Benchmark for Visual-Textual-Acoustic Alignment accepted BiomedCCPL: Causal Conditional Prompt Learning for Biomedical Vision-Language Models accepted Black-Box Domain Adaptation for Object Detection with Retention-Driven Knowledge Compression accepted Black-box Membership Inference Attacks on the Pre-training Data of Image-generation Models accepted BlackMirror: Black-Box Backdoor Detection for Text-to-Image Models via Instruction-Response Deviation accepted Blink: Dynamic Visual Token Resolution for Enhanced Multimodal Understanding accepted Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers accepted Block-based Learned Image Compression without Blocking Artifacts accepted BluRef: Unsupervised Image Deblurring with Dense-Matching References accepted BoostSLT: Boosting Sign Language Translation via a Plug-and-Play Diffusion-Based Semantic Enhancer accepted Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing accepted Boosting Quantitive and Spatial Awareness for Zero-Shot Object Counting accepted Boosting Reasoning in Large Multimodal Models via Activation Replay accepted Boosting Self-Supervised Tracking with Contextual Prompts and Noise Learning accepted Boosting Vision-Language Models Towards Cross-Domain Incremental Object Detection accepted Boosting Vision-Language-Action Finetuning with Feasible Action Neighborhood Prior accepted Boosting Visual Reprogramming for CLIP with Dual Granularity Alignment accepted Bootstrap Dynamic-Aware 3D Visual Representation for Scalable Robot Learning accepted Bootstrap Your Own AV-Proxies: Adaptive Contrastive and Prototype Learning for Audio-Visual Segmentation accepted Bootstrapping Multi-view Learning for Test-time Noisy Correspondence accepted Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptation accepted Boundary-Responsive Differentiable Gating for Superpixel-Based Segmentation accepted Breaking Multimodal LLM Safety via Video-Driven Prompting accepted Breaking Semantic Boundaries: Distribution-Guided Semantic Exploration for Creative Generation accepted Breaking Smooth-Motion Assumptions: A UAV Benchmark for Multi-Object Tracking in Complex and Adverse Conditions accepted Breaking Spurious Correlations: Uncertainty-Driven Causal Transformers for AU Detection accepted Breaking the 3D Dataset Bottleneck: Fast Scalable Generation of Aligned 3D Assets from Scratch for Category 6D Pose Estimation and Robotic Grasping accepted Breaking the Continuum: Discrete Distribution Learning for Structural MRI Reconstruction accepted Breaking the Illusion: When Positive Meets Negative in Multimodal Decoding accepted Breaking the Regional Perception Bottleneck of Multimodal Large Language Models via External Reasoning Framework accepted Breaking the Scalability Limit of Multi-Projector Calibration with Embedded Cameras accepted BrepGaussian: CAD reconstruction from Multi-View Images with Gaussian Splatting accepted BrepVGAE: Variational Graph Autoencoder with Unified Latent Representation for B-rep accepted Brewing Stronger Features: Dual-Teacher Distillation for Multispectral Earth Observation accepted BriMA: Bridged Modality Adaptation for Multi-Modal Continual Action Quality Assessment accepted BrickNet: Graph-Backed Generative Brick Assembly accepted Bridge: Basis-Driven Causal Inference Marries VFMs for Domain Generalization accepted BridgeEQA: Virtual Embodied Agents for Real Bridge Inspections accepted Bridging Brain and Semantics: A Hierarchical Framework for Semantically Enhanced fMRI-to-Video Reconstruction accepted Bridging Domain Expertise and Generalization for Performance Estimation accepted Bridging Domains through Subspace-Aware Model Merging accepted Bridging Facial Understanding and Animation via Language Models accepted Bridging Fidelity-Reality with Controllable One-Step Diffusion for Image Super-Resolution accepted Bridging Human Evaluation to Infrared and Visible Image Fusion accepted Bridging Pixels and Words: Mask-Aware Local Semantic Fusion for Multimodal Media Verification accepted Bridging Privacy and Provenance: Traceable Virtual Identity Generation accepted Bridging RGB and Hematoxylin Components: An Interleaved Guidance and Fusion Framework for Point Supervised Nuclei Segmentation accepted Bridging the 2D-3D Gap: A Hierarchical Semantic-Geometric Map for Vision Language Navigation accepted Bridging the Modality Gap in Compositional Zero-Shot Learning via Sparse Alignment and Unimodal Memory Bank accepted Bridging the Perception Gap in Image Super-Resolution Evaluation accepted Bringing Your Portrait to 3D Presence accepted BuildAnyPoint: 3D Building Structured Abstraction from Diverse Point Clouds accepted Building Robust Vision Encoders for Cross-Dataset Evaluation in Immunofluorescent Microscopy accepted Building a Precise Video Language with Human-AI Oversight accepted BuildingGPT: Auto-Regressive Building Wireframe Reconstruction Model with Reinforcement Learning accepted Bulk RNA-seq Guided Multi-modal Detection of Anomalous Regions in Human Cancer via Spatial Transcriptomics accepted BulletTime: Decoupled Control of Time and Camera Pose for Video Generation accepted Bypassing the Transport Plan: Dynamic Reweighting for Out-of-Distribution Detection with Optimal Transport accepted C-GenReg: Training-Free 3D Point Cloud Registration by Multi-View-Consistent Geometry-to-Image Generation with Probabilistic Modalities Fusion accepted C-LaV: Conditional Latent Velocity Field Denoising for Weather-Robust LiDAR Place Recognition accepted CAD-Refiner: A Unified Framework for CAD Generation and Iterative Editing accepted CADC: Content Adaptive Diffusion-Based Generative Image Compression accepted CADFS: A Big CAD Program Dataset and Framework for Computer-Aided Design with Large Language Models accepted CAPT: Confusion-Aware Prompt Tuning for Reducing Vision-Language Misalignment accepted CAR-SAM: Cross-Attention Reconstruction for Post-Training Quantization of the Segment Anything Model accepted CARD: A Multi-Modal Automotive Dataset for Dense 3D Reconstruction in Challenging Road Topography accepted CARD: Correlation Aware Restoration with Diffusion accepted CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoning accepted CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing accepted CARE: A Molecular-Guided Foundation Model with Adaptive Region Modeling for Whole Slide Image Analysis accepted CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction accepted CARLoS: Retrieval via Concise Assessment Representation of LoRAs at Scale accepted CASPA: Graph-Structured Concept Anchors for Modality-Agnostic Adaptation in Vision-Language Models accepted CASR: A Robust Cyclic Framework for Arbitrary Large-Scale Super-Resolution with Distribution Alignment and Self-Similarity Awareness accepted CAST: Context-Aware Dynamic Latent Space Transformation for Interactive Text-to-Image Retrieval accepted CATNet: Collaborative Alignment and Transformation Network for Cooperative Perception accepted CC-VQA: Conflict- and Correlation-Aware Method for Mitigating Knowledge Conflict in Knowledge-Based Visual Question Answering accepted CCCaption: Dual-Reward Reinforcement Learning for Complete and Correct Image Captioning accepted CCF: Complementary Collaborative Fusion for Domain Generalized Multi-Modal 3D Object Detection accepted CD-Buffer: Complementary Dual-Buffer Framework for Test-Time Adaptation in Adverse Weather Object Detection accepted CDICS: Delving Into Fine-Grained Attribute for In-Context Segmentation via Compositional Prompts and Phased Decoupling accepted CF-IPT: Cross-Modal Fusion Interactive Prompt Tuning of Vision-Language Pre-Trained Model for Multisource Remote Sensing Data Classification accepted CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance accepted CG-Floor: Centroid-Guided Diffusion for Large-Scale Floorplan Generation accepted CG-Reasoner: Centroid-Guided Positional Reasoning Segmentation for Medical Imaging with a Robust Visual-Text Consistency Metric accepted CGHair: Compact Gaussian Hair Reconstruction with Card Clustering accepted CGL: Advancing Continual GUI Learning via Reinforcement Fine-Tuning accepted CGU-Bayes: Causal Graph Uncertainty-Guided Bayesian Inference for Domain Generalization accepted CHAL: Causal-guided Hierarchical Anomaly-aware Learning for Moving Infrared Small Target Detection accepted CHEEM: Continual Learning by Reuse, New, Adapt and Skip - A Hierarchical Exploration-Exploitation Approach accepted CHIPS: Efficient CLIP Adaptation via Curvature-aware Hybrid Influence-based Data Selection accepted CHIRP dataset: towards long-term, individual-level, behavioral monitoring of bird populations in the wild accepted CI-VID: A Coherent Interleaved Text-Video Dataset accepted CICA: Coupling Confidence-Aware Pretraining with Confidence-Informed Attention for Robust Multimodal Sentiment Analysis accepted CIGMA: Causal Information-Gain Mechanistic Attribution of Attention Heads in Vision Transformers accepted CIGPose: Causal Intervention Graph Neural Network for Whole-Body Pose Estimation accepted CLAY: Conditional Visual Similarity Modulation in Vision-Language Embedding Space accepted CLCR: Cross-Level Semantic Collaborative Representation for Multimodal Learning accepted CLEP: Contrastive Language-Pose Pretraining accepted CLEX: Complementary Label Exchange Learning for Noisy Facial Expression Recognition accepted CLIP Is Shortsighted: Paying Attention Beyond the First Sentence accepted CLIP-like Model as a Foundational Density Ratio Estimator accepted CLIPoint3D: Language-Grounded Few-Shot Unsupervised 3D Point Cloud Domain Adaptation accepted CLP: A Real-World Dataset of Contaminated Lens Protectors for Robust Semantic Segmentation accepted CLaD: Planning with Grounded Foresight via Cross-Modal Latent Dynamics accepted CLiViS: Unleashing Cognitive Map through Linguistic-Visual Synergy for Embodied Visual Reasoning accepted CME-CAD: Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generation accepted CMR-RD: Long-Tailed Adaptive VLM for Explainable CMR Diagnosis accepted COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimation accepted COPE: Consistent Occlusion and Prompt Enhancement Network for Occluded Person Re-identification accepted COPO: Causal-Oriented Policy Optimization for Hallucinations of MLLMs accepted COPYLENS: Towards Copyrighted Characters Infringement Detection via Copyright-Aware Prompt Learning accepted CORE: Compact Object-centric REpresentations as a New Paradigm for Token Merging in LVLMs accepted COT-FM: Cluster-wise Optimal Transport Flow Matching accepted CRAFT-LoRA: Content-Style Personalization via Rank-Constrained Adaptation and Training-Free Fusion accepted CRAFT: Aligning Diffusion Models with Fine-Tuning Is Easier Than You Think accepted CREval: An Automated Interpretable Evaluation for Creative Image Manipulation under Complex Instructions accepted CREward: A Type-Specific Creativity Reward Model accepted CRFT: Consistent-Recurrent Feature Flow Transformer for Cross-Modal Image Registration accepted CRIT: Graph-Based Automatic Data Synthesis to Enhance Cross-Modal Multi-Hop Reasoning accepted CROWn: A Unified Framework for Anti-Aliased Downsampling and Phase-Calibrated Fusion in 3D Medical Segmentation accepted CSF: Black-box Fingerprinting via Compositional Semantics for Text-to-Image Models accepted CTCal: Rethinking Text-to-Image Diffusion Models via Cross-Timestep Self-Calibration accepted CUBic: Coordinated Unified Bimanual Perception and Control Framework accepted CUE: Concept-Aware Multi-Label Expansion to Mitigate Concept Confusion in Long-Tailed Learning accepted CUPID: Generative 3D Reconstruction via Joint Object and Pose Modeling accepted CURE: Curriculum-guided Multi-task Training for Reliable Anatomy Grounded Report Generation accepted CURVE: A Benchmark for Cultural and Multilingual Long Video Reasoning accepted CVA: Context-aware Video-text Alignment for Video Temporal Grounding accepted C^2FG: Control Classifier-Free Guidance via Score Discrepancy Analysis accepted CaReFlow: Cyclic Adaptive Rectified Flow for Multimodal Fusion accepted CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering accepted CaT-GS: Efficient 3DGS Rendering for Large-Scale Scenes with Inter-frame Caching and Tile Scheduling accepted CaTok: Taming Mean Flows for One-Dimensional Causal Image Tokenization accepted CaliTex: Geometry-Calibrated Attention for View-Coherent 3D Texture Generation accepted CamDirector: Towards Long-Term Coherent Video Trajectory Editing accepted CamPI: Physical Adversarial Examples through Camera Power Signal Injection accepted Camera Control for Text-to-Image Generation via Learning Viewpoint Tokens accepted Camouflage-aware Image-Text Retrieval via Expert Collaboration accepted

Can Natural Image Autoencoders Compactly Tokenize fMRI Volumes for Long-Range Dynamics Modeling? accepted Can We Build Scene Graphs, Not Classify Them? FlowSG: Progressive Image-Conditioned Scene Graph Generation with Flow Matching accepted Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers accepted Can a Second-View Image Be a Language? Geometric and Semantic Cross-Modal Reasoning for X-ray Prohibited Item Detection accepted CanonCGT: Reference-Based Color Grading via Canonical Pivot Representation accepted CapNav: Benchmarking Vision Language Models on Capability-conditioned Indoor Navigation accepted Captain Safari: A World Engine with Pose-Aligned 3D Memory accepted CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects accepted CaptionQA: Is Your Caption as Useful as the Image Itself? accepted CaricHarmony: Contrastive Diffusion Paths for Identity-Preserving Caricature Synthesis accepted Catalyst4D: High-Fidelity 3D-to-4D Scene Editing via Dynamic Propagation accepted Causal Motion Diffusion Models for Autoregressive Motion Generation accepted CausalLens: Sensitivity-Guided Multi-Head Causal Intervention for Hallucination Mitigation in Large Vision-Language Models accepted CausalVAD: De-confounding End-to-End Autonomous Driving via Causal Intervention accepted Causality in Video Diffusers is Separable from Denoising accepted Cell-Type Prototype-Informed Neural Network for Gene Expression Estimation from Pathology Images accepted ChArtist: Generating Pictorial Charts with Unified Spatial and Subject Control accepted Chain of Event-Centric Causal Thought for Physically Plausible Video Generation accepted Chain of World: World Model Thinking in Latent Motion accepted Chain-of-Frames: Advancing Video Understanding in Multimodal LLMs via Frame-Aware Reasoning accepted Chain-of-Models Pre-Training: Rethinking Training Acceleration of Vision Foundation Models accepted Chain-of-Thought Guided Multi-Modal Object Re-Identification accepted ChangeBridge: Spatiotemporal Image Generation with Multimodal Controls for Remote Senisng accepted Changes in Real Time: Online Scene Change Detection with Multi-View Fusion accepted Charge: A Comprehensive Novel View Synthesis Benchmark and Dataset to Bind Them All accepted Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts accepted ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding accepted ChartR: Evaluating Reasoning Accuracy and Robustness in Chart Question Answering accepted ChimeraLoRA: Multi-Head LoRA-Guided Synthetic Datasets accepted ChordEdit: One-Step Low-Energy Transport for Image Editing accepted Choreographing a World of Dynamic Objects accepted Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding accepted ChronoGS: Disentangling Invariants and Changes in Multi-Period Scenes accepted CineBrain: A Large-Scale Multi-Modal Audiovisual Brain Dataset for Brain-Conditioned Video Generation accepted CineSRD: Leveraging Visual, Acoustic, and Linguistic Cues for Open-World Visual Media Speaker Diarization accepted CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generation accepted Cinematic Audio Source Separation Using Visual Cues accepted Circuit Mechanisms for Spatial Relation Generation in Diffusion Transformers accepted Circular-DPO: Aligning Multi-Stage 3D Generative Models via Preference Feedback Loop accepted Clair Obscur: an Illumination-Aware Method for Real-World Image Vectorization accepted Clay-to-Stone: Phase-wise 3D Gaussian Splatting for Monocular Articulated Hand-Object Manipulation Modeling accepted Cleaning the Pool: Progressive Filtering of Unlabeled Pools in Deep Active Learning accepted ClimaOoD: Improving Anomaly Segmentation via Physically Realistic Synthetic Data accepted Clinically-Grounded Counterfactual Reasoning for Medical Video Diagnosis accepted ClipGStream: Clip-Stream Gaussian Splatting for Any Length and Any Motion Multi-View Dynamic Scene Reconstruction accepted Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models accepted Closed-Form Concept Erasure via Double Projections accepted Clothe and Pose accepted Cluster-Aware Neural Collapse Prompt Tuning for Long-Tailed Generalization of Vision-Language Models accepted Cluster-Wise Spatio-Temporal Masking for Efficient Video-Language Pretraining accepted Cluster-aware Anchor Learning for Multi-View Clustering accepted ClusterMark: Towards Robust Watermarking for Autoregressive Image Generators with Visual Token Clustering accepted Co-Me: Confidence Guided Token Merging for Visual Geometric Transformers accepted CoCoVideo: The High-Quality Commercial-Model-Based Contrastive Benchmark for AI-Generated Video Detection accepted CoD: A Diffusion Foundation Model for Image Compression accepted CoFiDA-M: Concept-Aware Feature Modulation for Cross-Domain Adaptation with Image-Only Inference accepted CoIn3D: Revisiting Configuration-Invariant Multi-Camera 3D Object Detection accepted CoIn: Coverage and Informativeness-Guided Token Reduction for Efficient Large Multimodal Models accepted CoLC: Communication-Efficient Collaborative Perception with LiDAR Completion accepted CoLoGen: Progressive Learning of Concept-Localization Duality for Unified Image Generation accepted CoLoR: The Devil is in Scene Coordinate Regression for Large-Scale Visual Localization accepted CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning accepted CoRiM: Conflict-driven Risk Minimization for Dynamic Multimodal Fusion accepted CoRoGS: Contextual Gaussian Splatting for Robust Large-Deviation View Synthesis accepted CoSMo3D: Open-World Promptable 3D Semantic Segmentation through LLM-Guided Canonical Spatial Modeling accepted CoT-Edit: Let CoT Guide Instruction Video Editing accepted CoV-Align: Efficient Fine-grained Cross-Modal Alignment with Cohesive Visual Semantics Priority accepted CoVFT: Context-aware Visual Fine-tuning for Multimodal Large Language Models accepted CoWTracker: Tracking by Warping instead of Correlation accepted CodeDance: A Dynamic Tool-integrated MLLM for Executable Visual Reasoning accepted CodeMMR: Bridging Natural Language, Code, and Image for Unified Retrieval accepted CodePercept: Code-Grounded Visual STEM Perception for MLLMs accepted CodeV: Code with Images for Faithful Visual Reasoning via Tool-Aware Policy Optimization accepted Coded-E2LF: Coded Aperture Light Field Imaging from Events accepted CogDriver: Integrating Cognitive Inertia for Temporally Coherent Planning in Autonomous Driving accepted CogniEdit: Dense Gradient Flow Optimization for Fine-Grained Image Editing accepted CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric Reasoning accepted ColaVLA: Leveraging Cognitive Latent Reasoning for Hierarchical Parallel Trajectory Planning in Autonomous Driving accepted Collaborative Multi-Mode Pruning for Vision-Language Models accepted Color When It Counts: Grayscale-Guided Online Triggering for Always-On Streaming Video Sensing accepted Color-Encoded Illumination for High-Speed Volumetric Scene Reconstruction accepted ColorFLUX: A Structure-Color Decoupling Framework for Old Photo Colorization accepted ComPose: A Unified Completion-Pose Framework for Robust Category-Level Object Pose Estimation accepted Common Inpainted Objects In-N-Out of Context accepted CompBench: Benchmarking Complex Instruction-guided Image Editing accepted CompetitorFormer: Mitigating Query Conflicts for 3D Instance Segmentation via Competitive Strategy accepted Complementary Prototype Mapping for Efficient Multimodal Anomaly Detection accepted Complet4R: Geometric Complete 4D Reconstruction accepted Composing Concepts from Images and Videos via Concept-prompt Binding accepted Composite-Attribute Person Re-Identification via Pose-Guided Disentanglement accepted Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization accepted Compositional Transformation Reasoning for Composed Video Retrieval accepted Compressed-Domain-Aware Online Video Super-Resolution accepted Computation and Communication Efficient Federated Unlearning via On-server Gradient Conflict Mitigation and Expression accepted Computational Speckle Pattern Interferometry accepted Computer Vision with a Superpixelation Camera accepted Conan: Progressive Learning to Reason Like a Detective over Multi-Scale Visual Evidence accepted Concept Regions Matter: Benchmarking CLIP with a New Cluster-Importance Approach accepted Concept-Aware Batch Sampling Improves Language-Image Pretraining accepted Concept-Aware LoRA for Domain-Aligned Segmentation Dataset Generation accepted Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness accepted ConceptPose: Training-Free Zero-Shot Object Pose Estimation using Concept Vectors accepted ConceptPrism: Concept Disentanglement in Personalized Diffusion Models via Residual Token Optimization accepted Condensed Test-Time Adaptation of VLMs for Action Recognition accepted Conditional Factuality Controlled LLMs with Generalization Certificates via Conformal Sampling accepted ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval accepted Confidence-Guided Multi-Scale Aggregation for Sparse-View High-Resolution 3D Gaussian Splatting accepted Conflict-Aware Adaptive Cross-Reconstruction for Multimodal Sentiment Analysis accepted Confusion-Aware Spectral Regularizer for Long-Tailed Recognition accepted ConsID-Gen: View-Consistent and Identity-Preserving Image-to-Video Generation accepted Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR accepted Consensus vs. Controversy: Mapping the Decision Space Where Architectures Diverge accepted ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation accepted ConsistCompose: Unified Multimodal Layout Control for Image Composition accepted Consistency Beyond Contrast: Enhancing Open-Vocabulary Object Detection Robustness via Contextual Consistency Learning accepted Consistent Instance Field for Dynamic Scene Understanding accepted Contact-Aware Neural Dynamics accepted Content-Adaptive Hierarchical Hyperprior for Neural Video Coding accepted Content-Aware Dynamic Patchification for Efficient Video Diffusion accepted Content-Aware Frequency Encoding for Implicit Neural Representations with Fourier-Chebyshev Features accepted Context-Nav: Context-Driven Exploration and Viewpoint-Aware 3D Spatial Reasoning for Instance Navigation accepted Continual Distillation of Teachers from Different Domains accepted Continual Learning for fMRI-Based Brain Disorder Diagnosis via Functional Connectivity Matrices Generative Replay accepted Continuous Exposure-Time Modeling for Realistic Atmospheric Turbulence Synthesis accepted Contrastive Cross-Bag Augmentation for Multiple Instance Learning-based Whole Slide Image Classification accepted Controllable Federated Prompt Learning at Test Time accepted Conversational Image Segmentation: Grounding Abstract Concepts with Scalable Supervision accepted Convexity-Aware Noise Calibration: A Self-Supervised Framework for Noise-Level-Unknown Image Denoising accepted Convolutional Neural Networks Driven by Content Similarity accepted CoopDiff: A Diffusion-Guided Approach for Cooperation under Corruptions accepted CoordSpeaker: Exploiting Gesture Captioning for Coordinated Caption-Empowered Co-Speech Gesture Generation accepted Coordinate Denoising for Non-Equilibrium Molecular Representation Learning accepted Copy-Transform-Paste: Zero-Shot Object-Object Alignment Guided by Vision-Language and Geometric Constraints accepted Correspondence-Attention Alignment for Multi-View Diffusion Models accepted CountGD++: Generalized Prompting for Open-World Counting accepted Counterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoning accepted Coupled Diffusion Sampling for Training-Free Multi-View Image Editing accepted Coupling Liquid Time-Constant Encoders with Modern Hopfield Memory accepted Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimation accepted Coverage Optimization for Camera View Selection accepted CrackSSM: Reviving SSMs for Crack Segmentation via Dynamic Scanning accepted CraftMesh: High-Fidelity Generative Mesh Manipulation via Poisson Seamless Fusion accepted Critical Patch-Aware Sparse Prompting with Decoupled Training for Continual Learning on the Edge accepted Cross from Left to Right Brain: Adaptive Text Dreamer for Vision-and-Language Navigation accepted Cross-Architecture Adaptation: Cloud-Edge Continual Test-Time Adaptation with Dynamic Sampling and Heterogeneous Distillation accepted Cross-Axis Feature Fusion with Joint-Wise Motion Difference Prediction for Text-Based 3D Human Motion Editing accepted Cross-Domain Demo-to-Code via Neurosymbolic Counterfactual Reasoning accepted Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptation accepted Cross-Hand Latent Representation for Vision-Language-Action Models accepted Cross-Instance Gaussian Splatting Registration via Geometry-Aware Feature-Guided Alignment accepted Cross-Modal Attention Calibration for LVLM Hallucination Mitigation accepted Cross-Modal Emotion Transfer for Emotion Editing in Talking Face Video accepted Cross-Modal Guided Visual Synthesis for Data-Efficient Multimodal Depression Recognition accepted Cross-Scale Pansharpening via ScaleFormer and the PanScale Benchmark accepted Cross-Slice Knowledge Transfer via Masked Multi-Modal Heterogeneous Graph Contrastive Learning for Spatial Gene Expression Inference accepted Cross-Subject EEG-to-Video Reconstruction and Beyond accepted Cross-View Distillation and Adaptive Masking for Incomplete Multi-View Multi-Label Classification accepted Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced Images accepted Cross-domain Dual-stream Feature Disentanglement for Brain Disorder Prediction with Sparsely Labeled PET accepted Cross-modal Fuzzy Alignment Network for Text-Aerial Person Retrieval and A Large-scale Benchmark accepted Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learning accepted Cross-modal Representation Learning for Diffusion-generated Image Detection accepted CrossEarth-Gate: Fisher-Guided Adaptive Tuning Engine for Efficient Adaptation of Cross-Domain Remote Sensing Semantic Segmentation accepted CrossHOI-Bench: A Unified Benchmark for HOI Evaluation across Vision-Language Models and HOI-Specific Methods accepted CrossHOI: Learning Cross-View Representations for Monocular 3D Human-Object Interaction Reconstruction accepted CrossVL: Complexity-Aware Feature Routing and Paired Curriculum for Cross-View Vision-Language Detection accepted CrowdGaussian: Reconstructing High-Fidelity 3D Gaussians for Human Crowd from a Single Image accepted CryoHype: Reconstructing a thousand cryo-EM structures with transformer-based hypernetworks accepted CryoKRAQEN: Kernel-Regularized Annealing for Quantized Embedding Networks in Cryo-EM Heterogeneous Reconstruction accepted CubeComposer: Spatio-Temporal Autoregressive 4K 360deg Video Generation from Perspective Video accepted Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens accepted Curriculum Group Policy Optimization: Adaptive Sampling for Unleashing the Potential of Text-to-Image Generation accepted Curvature-Aware Captioning: Leveraging Geodesic Attention for 3D Scene Understanding accepted Curvature-Aware Zeroth-Order Optimization for Memory-Efficient Test-Time Adaptation accepted CustomTex: High-fidelity Indoor Scene Texturing via Multi-Reference Customization accepted Customized Fusion: A Closed-Loop Dynamic Network for Adaptive Multi-Task-Aware Infrared-Visible Image Fusion accepted Cut to the Chase: Training-free Multimodal Summarization via Chain-of-Events accepted Cycle-Consistent Tuning for Layered Image Decomposition accepted CycleBEV: Regularizing View Transformation Networks via View Cycle Consistency for Bird's-Eye-View Semantic Segmentation accepted CycleManip: Enabling Cycle-based Manipulation via Effective History Perception and Understanding accepted D$^2$-FOSA: Dual-Diffusion Guided EEG-to-Image Reconstruction with Frequency-Oriented Semantic Alignment accepted D-Convexity: A Unified Differentiable Convex Shape Prior via Quasi-Concavity for Data-driven Image Segmentation accepted D-Prism: Differentiable Primitives for Structured Dynamic Modeling accepted D2Cache: Second-Order Delta Caching for Higher Video Diffusion Acceleration accepted D2Dewarp: Dual Dimensions Geometric Representation Learning Based Document Image Dewarping accepted D2FANet: Enhancing Video Object Detection with Dual-Domain Feature Aggregation Network accepted D2T2 - Multimodal Automated Planning for Brachytherapy accepted D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigation accepted DA-Mamba: Learning Domain-Aware State Space Model for Global-Local Alignment in Domain Adaptive Object Detection accepted DA-VAE: Plug-in Latent Compression for Diffusion via Detail Alignment accepted DABO: Difficulty-Aware Bayesian Optimization with Diffusion-Learned Priors accepted DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation accepted DARC: Dual Adjustment Reasoning with Counterfactuals for Trustworthy Chest X-ray Classification accepted DASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examples accepted DBMSolver: A Training-free Diffusion Bridge Sampler for High-Quality Image-to-Image Translation accepted DC-Merge: Improving Model Merging with Directional Consistency accepted DCoAR: Deep Concept Injection into Unified Autoregressive Models for Personalized Text-to-Image Generation accepted DDSF: Robust Few-Shot Learning via Disentangled Subspaces with Determinantal Point Process accepted DDT: Decoupled Diffusion Transformer accepted DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers accepted DENALI: A Dataset Enabling Non-Line-of-Sight Spatial Reasoning with Low-Cost LiDARs accepted DETACH : Decomposed Spatio-Temporal Alignment for Exocentric Video and Ambient Sensors with Staged Learning accepted DEVA: Fine-tuning Multimodal Large Language Models for Visual Perception Tasks accepted DFD-HR: Generalizable Deepfake Detection via Hierarchical Routing Learning accepted DF^2-VB: Dual-level Fuzzy Fusion with View-specific Boosting for Multi-view Multi-label Classification accepted DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images accepted DGS: Dual Gradient and Semantic-Shift Guided Low-Rank Adaptation for Class Incremental Learning accepted DICArt: Advancing Category-level Articulated Object Pose Estimation in Discrete State-Spaces accepted DIMOS: Disentangling Instance-level Moving Object Segmentation accepted DINO Eats CLIP: Adapting Beyond Knowns for Open-set 3D Object Retrieval accepted DK-DDIL: Adaptive Knowledge Retention for Dynamic Domain-Incremental Learning in Medical Imaging accepted DLVP-CLIP: Enhancing Fine-Grained Zero-Shot Anomaly Detection via Dynamic Local Visual Prompting accepted DLWM: Dual Latent World Models enable Holistic Gaussian-centric Pre-training in Autonomous Driving accepted DMAligner: Enhancing Image Alignment via Diffusion Model Based View Synthesis accepted DMGD: Train-Free Dataset Distillation with Semantic-Distribution Matching in Diffusion Models accepted DNF-SR: Dual-Input and Negative-Aware Feature Fine-Tuning for Real-World Image Super-Resolution accepted DP-FedAdamW: An Efficient Optimizer for Differentially Private Federated Large Models accepted DPAR: Dynamic Patchification for Efficient Autoregressive Visual Generation accepted DPGF-Net: Dual-Prior Guided Fusion Network for Joint Assessment of Perceptual Quality and Semantic Consistency in AI-Generated Images accepted DPL: Decoupled Prototype Learning for Enhancing Robustness of Vision-Language Transformers to Missing Modalities accepted DRAMA: Next-Gen Dynamic Orchestration for Resilient Multi-Agent Ecosystems in Flux accepted DREAM: Document Recognition with Explicit Adaptive Memory accepted DRM: Diffusion-based Reward Model With Step-wise Guidance accepted DROID-SLAM in the Wild accepted DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding accepted DRiffusion: Draft-and-Refine Process Parallelizes Diffusion Models with Ease accepted DSCA: Dynamic Subspace Concept Alignment for Lifelong VLM Editing accepted DSERT-RoLL: Robust Multi-Modal Perception for Diverse Driving Conditions with Stereo Event-RGB-Thermal Cameras, 4D Radar, and Dual-LiDAR accepted DSFlash: Comprehensive Panoptic Scene Graph Generation in Realtime accepted DSO: Direct Steering Optimization for Bias Mitigation accepted DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution accepted DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference accepted DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolution accepted DVAR: Dynamic Visual Autoregressive Modeling for Image Super-Resolution accepted DVGT: Driving Visual Geometry Transformer accepted D^3FER: Dual Channel and Dual Branch Network for Robust Facial Expression Recognition under Dual Challenges accepted Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridging accepted Dark3R: Learning Structure from Motion in the Dark accepted DarkAct: A RGB-Thermal Dataset and Fusion Framework for Multimodal Low-Light Action Recognition accepted DarkShake-DVS: Event-based Human Action Recognition under Low-light and Shaking Camera Conditions accepted Data Leakage Detection and De-duplication in Large Scale Geospatial Image Datasets accepted Data-Centric Meta-Learning for Robust Few-Shot Generalization accepted Dataset Distillation by Influence Matching accepted DeAR: Fine-Grained VLM Adaptation by Decomposing Attention Head Roles accepted DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation accepted DeDelayed: Deleting Remote Inference Delay via On-Device Correction accepted DeRVOS: Decoupling Consistent Trajectory Generation and Multimodal Understanding for Referring Video Object Segmentation accepted DeX-Portrait: Disentangled and Expressive Portrait Animation via Explicit and Latent Motion Representations accepted Debiased Sample Selection for Learning with Noisy Labels accepted Deciphering Genotype-Phenotype Mechanisms from High-Content Profiling via Knowledge-Guided Multi-modal Graph Learning accepted Decision Boundary-aware Generation for Long-tailed Learning accepted DecoVLN: Decoupling Observation, Reasoning, and Correction for Vision-and-Language Navigation accepted Decoding 3D Perception via BrainSSD: Synergistic Fusion of EEG Representations from Static and Dynamic Visual Streams accepted Decompose and Transfer: CoT-Prompting Enhanced Alignment for Open-Vocabulary Temporal Action Detection accepted Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression accepted Deconstructing the Failure of Ideal Noise Correction: A Three-Pillar Diagnosis accepted Decouple Your Discovery and Memory in Continual Generalized Category Discovery accepted Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoning accepted Decoupled Generative Modeling for Human-Object Interaction Synthesis accepted Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translation accepted Decoupled and Reusable Adaptation for Efficient Cross-Modal Transfer accepted Decoupling Bias, Aligning Distributions: Synergistic Fairness Optimization for Deepfake Detection accepted Decoupling Defense Strategies for Robust Image Watermarking accepted Decoupling Stability and Plasticity for Multi-Modal Test-Time Adaptation accepted Decoupling Vision and Language: Codebook Anchored Visual Adaptation accepted Deep Feature Deformation Weights accepted DeepAlign: Mitigating Modality Conflict through Modality-Specific Alignment accepted DeepProtect: Proactive Face-Swapping Defense using Identity Blending and Attribute Distortion accepted DeepScan: A Training-Free Framework for Visually Grounded Reasoning in Large Vision-Language Models accepted Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models accepted DeepfakeImpact: A Two-Stage Benchmark with Real-World Impact in Deepfake Detection accepted Defect Cue-Preserved Structural Feature Refinement for Few-Shot Anomaly Detection accepted Defending Unauthorized Model Merging via Dual-Stage Weight Protection accepted Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillation accepted Deformation-based In-Context Learning for Point Cloud Understanding accepted Degradation-Consistent Test-Time Adaptation for All-in-One Image Restoration accepted Degradation-Robust Fusion: An Efficient Degradation-Aware Diffusion Framework for Multimodal Image Fusion in Arbitrary Degradation Scenarios accepted Dehallu3D: Hallucination-Mitigated 3D Generation from a Single Image via Cyclic View Consistency Refinement accepted Dejavu: Towards Experience Feedback Learning for Embodied Intelligence accepted Delta Rectified Flow Sampling for Text-to-Image Editing accepted DeltaQuant: 4-bit Video Diffusion Models with Spatiotemporal Delta Smoothing accepted Delving Aleatoric Uncertainty in Medical Image Segmentation via Vision Foundation Models accepted Demo2Tutorial: From Human Experience to Multimodal Software Tutorials accepted DemoFunGrasp: Universal Dexterous Functional Grasping via Demonstration-Editing Reinforcement Learning accepted Den-TP: A Density-Balanced Data Curation and Evaluation Framework for Trajectory Prediction accepted Denoise and Align: Towards Source-Free UDA for Robust Panoramic Semantic Segmentation accepted Denoising as Path Planning: Training-Free Acceleration of Diffusion Models with DPCache accepted Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation accepted Dense Metric Depth Completion from Sparse Direct Time-of-Flight Sensors accepted Depth Any Endoscopy: Towards Self-Supervised Generalizable Depth Estimation in Monocular Endoscopy accepted Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation accepted Depth Hypothesis Guided Iterative Refinement for Event-Image Monocular Depth Estimation accepted Depth Peeling for High-Fidelity Gaussian-Enhanced Surfel Rendering accepted DepthFocus: Controllable Depth Estimation for See-Through Scenes accepted Describe Anything Anywhere At Any Moment accepted Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models accepted Designing Instance-Level Sampling Schedules via REINFORCE with James-Stein Shrinkage accepted Designing to Forget: Deep Semi-parametric Models for Unlearning accepted DetAny4D: Detect Anything 4D Temporally in a Streaming RGB Video accepted Detect Any AI-Counterfeited Text Image accepted Detect Anything via Next Point Prediction accepted DetectSCI: Toward Object-Guided ROI Reconstruction for High-Resolution Video Snapshot Compressive Imaging accepted Detecting AI-Generated Forgeries via Iterative Manifold Deviation Amplification accepted Detecting Compressed AI-Generated Images via Phase Spectrum Robustness accepted Detecting Unknown Objects via Energy-based Separation for Open World Object Detection accepted DextER: Language-driven Dexterous Grasp Generation with Embodied Reasoning accepted Dexterous World Models accepted DiG: Differential Grounding for Enhancing Fine-Grained Perception in Multimodal Large Language Models accepted DiGraphHal-Bench: Evaluating Multimodal Large Language Models on Complex Directed Graphs accepted DiP: Taming Diffusion Models in Pixel Space accepted DiT-Distill: Open-Set Fine-Grained Retrieval via Generative Curriculum Knowledge accepted DiT-IC: Aligned Diffusion Transformer for Efficient Image Compression accepted DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training accepted Diagnose, Correct, and Learn from Manipulation Failures via Visual Symbols accepted Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection accepted Diagram2Structure: Unlocking LLMs' Diagram Comprehension through DiagramDiff, a Framework for Structuring Offline Diagrams accepted DialogueVPR: Towards Conversational Visual Place Recognition accepted Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs accepted Diff-SemiER: Transparency-Aware Adaptive Fusion Diffusion Model with Generative Prior for Semi-Transparent Eyeglasses Removal accepted Diff4Splat: Repurposing Video Diffusion Models for Dynamic Scene Generation accepted DiffBMP: Differentiable Rendering with Bitmap Primitives accepted DiffDecompose: Layer-Wise Decomposition of Alpha-Composited Images via Diffusion Transformers accepted DiffGraph: An Automated Agent-driven Model Merging Framework for In-the-Wild Text-to-Image Generation accepted DiffSoup: Direct Differentiable Rasterization of Triangle Soup for Extreme Radiance Field Simplification accepted Differences That Matter: Auditing Models for Capability Gap Discovery and Rectification accepted Differentiable Adaptive 4D Structured Illumination for Joint Capture of Shape and Reflectance accepted Differentiable Laplacian Matrix Guided Superpixel Segmentation accepted Differentiable Stroke Planning with Dual Parameterization for Efficient and High-Fidelity Painting Creation accepted Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression accepted Differentially Private 2D Human Pose Estimation accepted DiffuView: Multi-View Diffusion Pretraining for 3D Aware Robotic Manipulation accepted Diffusion Forcing Planner: History-Annealed Planning with Time-Dependent Guidance for Autonomous Driving accepted Diffusion Guided Chain-of-Vision for Large Autoregressive Vision Models accepted Diffusion MRI Transformer with a Diffusion Space Rotary Positional Embedding (D-RoPE) accepted Diffusion Mental Averages accepted Diffusion Probe: Generated Image Result Prediction Using CNN Probes accepted Diffusion Sampling Path Tells More: An Efficient Plug-and-Play Strategy for Sample Filtering accepted Diffusion with a Linguistic Compass: Steering the Generation of Clinically Plausible Future sMRI Representations for Early MCI Conversion Prediction accepted Diffusion-Based Makeup Transfer with Facial Region-Aware Makeup Features accepted Diffusion-Based Native Adversarial Synthesis for Enhanced Medical Segmentation Generalization accepted Diffusion-Based sRGB Real Noise Generation via Prompt-Driven Noise Representation Learning accepted DiffusionFF: A Diffusion-based Framework for Joint Face Forgery Detection and Fine-Grained Artifact Localization accepted DiffusionHarmonizer: Bridging Neural Reconstruction and Photorealistic Simulation with Online Diffusion Enhancer accepted Direct Segmentation without Logits Optimization for Training-Free Open-Vocabulary Semantic Segmentation accepted DirectFisheye-GS: Enabling Native Fisheye Input in Gaussian Splatting with Cross-View Joint Optimization accepted Direction-aware 3D Large Multimodal Models accepted DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching accepted Disco-GS: Gaussian Splatting in Dynamic Color Lighting accepted Discover, Segment, and Select: A Progressive Mechanism for Zero-shot Camouflaged Object Segmentation accepted Discovering Adaptive Task Dependencies for Efficient Multi-Task Representation Compression accepted Discriminative Perception via Anchored Description for Reasoning Segmentation accepted Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement accepted Disentangled Textual Priors for Diffusion-based Image Super-Resolution accepted Disentanglement-wise Image Dehazing through Cross-Domain Manifold Consensus accepted Disentangling to Re-couple: Resolving the Similarity-Controllability Paradox in Subject-Driven Text-to-Image Generation accepted Distilling Balanced Knowledge from a Biased Teacher accepted Distilling Quasi-Conformal Mapping: A Generalizable and Efficient Solution for Wide-Angle Correction accepted Distilling Unsigned Distance Function for Surface Reconstruction from 3D Gaussian Splatting accepted Distributed Image Compression with Multimodal Side Information at Extremely Low Bitrates accepted Distribution-Aligned Multimodal Fusion for Robust Object Detection accepted Diverse Video Generation with Determinantal Point Process-Guided Policy Optimization accepted DiverseDiT: Towards Diverse Representation Learning in Diffusion Transformers accepted DiverseGRPO: Mitigating Mode Collapse in Image Generation via Diversity-Aware GRPO accepted Diversity over Uniformity: Rethinking Representation in Generated Image Detection accepted Divide, Conquer, and Aggregate: Asymmetric Experts for Class-Imbalanced Semi-Supervised Medical Image Segmentation accepted Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding accepted Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models? accepted Do VLMs Perceive or Recall? Probing Visual Perception vs. Memory with Classic Visual Illusions accepted Do Vision-Language Models Leak What They Learn? Adaptive Token-Weighted Model Inversion Attacks accepted Do Vision-Language Models Measure Up? Benchmarking Visual Measurement Reading with MeasureBench accepted Do You Have Freestyle? Expressive Humanoid Locomotion via Audio Control accepted Do You See What I Am Pointing At? Gesture-Based Egocentric Video Question Answering accepted DocPrune: Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning accepted DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding accepted Does YOLO Really Need to See Every Training Image in Every Epoch? accepted Domain Sensitive Federated Learning with Fisher-Informed Pruning accepted Domain-Skewed Federated Learning with Feature Decoupling and Calibration accepted Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs accepted Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal Models accepted Dr. Seg: Revisiting GRPO Training for Visual Large Language Models through Perception-Oriented Design accepted Dr.Occ: Depth- and Region-Guided 3D Occupancy from Surround-View Cameras for Autonomous Driving accepted Draft and Refine with Visual Experts accepted Drainage: A Unifying Framework for Addressing Class Uncertainty accepted DreamOmni2: Multimodal Instruction-based Generation and Editing accepted DreamSAC: Learning Hamiltonian World Models via Symmetry Exploration accepted DreamSR: Towards Ultra-High-Resolution Image Super-Resolution via a Receptive-Field Enhanced Diffusion Transformer accepted DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prior accepted DreamStereo: Towards Real-Time Stereo Inpainting for HD Videos accepted DreamStyle: A Unified Framework for Video Stylization accepted DreamingComics: A Story Visualization Pipeline via Subject and Layout Customized Generation using Video Models accepted Drift-Resilient Temporal Priors for Visual Tracking accepted Drive My Way: Preference Alignment of Vision-Language-Action Model for Personalized Driving accepted DriveCombo: Benchmarking Compositional Traffic Rule Reasoning in Autonomous Driving accepted DriveLaW: Unifying Planning and Video Generation in a Latent Driving World accepted DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving accepted DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning accepted DrivePTS: A Progressive Learning Framework with Textual and Structural Enhancement for Driving Scene Generation accepted DriveVLN: Towards Mapless Vision-and-Language Navigation in Autonomous Driving accepted DriverGaze360: OmniDirectional Driver Attention with Object-Level Guidance accepted Driving on Registers accepted Dropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splatting accepted Dual Ascent Diffusion for Inverse Problems accepted Dual Band Thermal Videography: Separating Time-Varying Reflection and Emission Near Ambient Conditions accepted Dual Graph Regularized Deep Unfolding Network for Guided Depth Map Super-resolution accepted Dual-Agent Reinforcement Learning for Adaptive and Cost-Aware Visual-Inertial Odometry accepted Dual-Estimator: Decoupling Global and Local Semantic Shift for Drift Compensation in Class-Incremental Learning accepted Dual-Granularity Memory for Efficient Video Generation accepted Dual-Level Confidence based Implicit Self-Refinement for Medical Visual Question Answering accepted Dual-Level Hypergraph Generation for Addressing Feature Scarcity in Whole-Slide Image Classification accepted Dual-Prototype-Guided Multi-task Learning for Unsupervised Anomaly Detection and Classification accepted Dual-branch Distilled Transformer for Efficient Asymmetric UAV Tracking accepted Dual-level Adaptation for Multi-Object Tracking: Building Test-Time Calibration from Experience and Intuition accepted Dual-level Adapter Boosting Prompt-free Curvilinear Structure Segmentation accepted DualMirage: Hunting Stealthy Multimodal LLM Agents via CAPTCHAs with Contour and Adversarial Illusions accepted DualPrim: Compact 3D Reconstruction with Positive and Negative Primitives accepted DualReg: Dual-Space Filtering and Reinforcement for Rigid Registration accepted DualSplat: Robust 3D Gaussian Splatting via Pseudo-Mask Bootstrapping from Reconstruction Failures accepted Duala: Dual-Level Alignment of Subjects and Stimuli for Cross-Subject fMRI Decoding accepted DuetMerging: Synergizing Dynamic and Static Strategies for Mitigating Task Interference in Model Merging accepted DuetSVG: Unified Multimodal SVG Generation with Internal Visual Guidance accepted DuoGen: Towards Autonomous Interleaved Multimodal Generation accepted DuoMo: Dual Motion Diffusion for World-Space Human Reconstruction accepted DyFCLT: Dynamic Frequency-Decoupled Cross-Modal Learning Transformer for Multimodal Tiny Object Detection accepted DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation accepted DynBridge: Bridging Imagination and Control through Interaction Dynamics for Robot Manipulation accepted DynFusion: Rethinking Condition Fusion for Adaptive Multi-Conditional Text-to-Image Generation accepted Dynamic Black-hole Emission Tomography with Physics-informed Neural Fields accepted Dynamic Exposure Burst Image Restoration accepted Dynamic Important Example Mining for Reinforcement Finetuning accepted Dynamic Label Noise Suppression with Optimal Teacher Pool for Facial Expression Recognition accepted Dynamic Logits Adjustment and Exploration for Test-Time Adaptation in Vision Language Models accepted Dynamic Magic: Unleashing Restricted Knowledge for Lifelong Person Re-Identification accepted Dynamic Momentum Recalibration in Online Gradient Learning accepted Dynamic Stream Network for Combinatorial Explosion Problem in Deformable Medical Image Registration accepted Dynamic Token Reweighting for Robust Vision-Language Models accepted Dynamic Visual SLAM using a General 3D Prior accepted Dynamic-Static Decomposition for Novel View Synthesis of Dynamic Scenes with Spiking Neurons accepted Dynamic-eDiTor: Training-Free Text-Driven 4D Scene Editing with Multimodal Diffusion Transformer accepted DynamicGTR: Leveraging Graph Topology Representation Preferences to Boost VLM Capabilities on Graph QAs accepted DynamicTree: Interactive Real Tree Animation via Sparse Voxel Spectrum accepted DynamicVGGT: Learning Dynamic Point Maps for 4D Scene Reconstruction in Autonomous Driving accepted Dynamics-Aware Preference Optimization for Vision-Language Models accepted Dynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From Videos accepted DynamicsBoost: Dynamic Plausible Video Generation via Annotation-Free Continuation Preference Optimization accepted E$^2$-SCI: Elastic Edge-Cloud Speculative Decoding via Credit Inertia accepted E-3DPSM: A State Machine for Event-based Egocentric 3D Human Pose Estimation accepted E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training accepted E-comIQ-ZH: A Human-Aligned Dataset and Benchmark for Fine-Grained Evaluation of E-commerce Posters with Chain-of-Thought accepted E2EGS: Event-to-Edge Gaussian Splatting for Pose-Free 3D Reconstruction accepted E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Driving accepted EDGS: Eliminating Densification for Efficient Convergence of 3DGS accepted EE-RL: Vision Language Guided Reinforcement Learning with Explorer and Expert model for End-to-End Autonomous Driving accepted EEGiT: Teaching Vision Transformers to Understand the EEG signal accepted EG-3DVG: Expression and Geometry Aware Grounding Decoder for 3D Visual Grounding accepted EI-Part:Explode for Completion and Implode for Refinement accepted ELITE: Efficient Gaussian Head Avatar from a Monocular Video via Learned Initialization and Test-time Generative Adaptation accepted ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Video Understanding accepted ELVIS: Enhance Low-Light for Video Instance Segmentation in the Dark accepted ELiC: Efficient LiDAR Geometry Compression via Cross-Bit-depth Feature Propagation and Bag-of-Encoders accepted EMAD: Evidence-Centric Grounded Multimodal Diagnosis for Alzheimer's Disease accepted EMGauss: Continuous Slice-to-3D Reconstruction via Dynamic Gaussian Modeling in Volume Electron Microscopy accepted EMMA: Concept Erasure Benchmark with Comprehensive Semantic Metrics and Diverse Categories accepted EMMA: Extracting Multiple physical parameters from Multimodal Data accepted EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models accepted EMR-Diff: Edge-aware Multimodal Residual Diffusion Model for Hyperspectral Image Super-resolution accepted ENC-Bench: A Benchmark for Evaluating Multimodal Large Language Models in Electronic Navigational Chart Understanding accepted ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization accepted EReCu: Pseudo-label Evolution Fusion and Refinement with Multi-Cue Learning for Unsupervised Camouflage Detection accepted ESAM++: Efficient Online 3D Perception on the Edge accepted EV-CGNet: Co-visible Focused 3D-guided 2D Event Keypoint Detection Network accepted EVA: Efficient Reinforcement Learning for End-to-End Video Agent accepted EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation accepted EVLF: Early Vision-Language Fusion for Generative Dataset Distillation accepted EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformer accepted EXOTIC: External Vision-driven Incomplete Multi-view Classification accepted EagleNet: Energy-Aware Fine-Grained Relationship Learning Network for Text-Video Retrieval accepted EagleVision: A Dual-Stage Framework with BEV-grounding-based Chain-of-Thought for Spatial Intelligence accepted EarlyTom: Early Token Compression Completes Fast Video Understanding accepted Easy2Hard: From Partially to Fully Unmatched Modalities as Negative Samples in Contrastive Learning accepted Easy3E: Feed-Forward 3D Asset Editing via Rectified Voxel Flow accepted EasyOmnimatte: Taming Pretrained Inpainting Diffusion Models for End-to-End Video Layered Decompositio accepted EasyV2V: A High-quality Instruction-based Video Editing Framework accepted EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generation accepted EchoPOSE: 6D Pose Estimation of Sparse Echocardiograms for Left-Ventricular 3D Shape Reconstruction accepted EchoVDiff: Cardiac-Cycle Echocardiography Video Generation from Arbitrary Single Frame accepted Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models accepted Echoes of Ownership: Adversarial-Guided Dual Injection for Copyright Protection in MLLMs accepted EcoAlign: An Economically Rational Framework for Efficient LVLM Alignment accepted EcoSplat: Efficiency-controllable Feed-forward 3D Gaussian Splatting from Multi-view Images accepted Edge-Focused Super-Resolution for Omnidirectional Images with Spherical Geometric Augmentation accepted Edge-RecViT: Efficient Vision Transformer via Semantic-Refined Dynamic Recursion accepted Edges Compete for Trust: Group Relative Edge Optimization for Building Reconstruction from Point Clouds accepted Edit-As-Act: Goal-Regressive Planning for Open-Vocabulary 3D Indoor Scene Editing accepted Edit-aware RAW reconstruction accepted Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers accepted EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editing accepted EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editing accepted Editprint: General Digital Image Forensics via Editing Fingerprint with Self-Augmentation Training accepted EduDiag: A Benchmark for Educational Diagnostic Reasoning with Error Tracing and Correction on Large Multimodal Models accepted CVPR accepted papers in other years Looking for submission deadlines instead? See the conference deadline calendar .