CVPR 2026 Events with Videos

Posters

• PrivateEyes: Gaze-Preserving Anonymization for Data Sharing
• Beyond Matching to Tiles: Bridging Unaligned Aerial and Satellite Views for Vision-Only UAV Navigation
• X-WIN: Building Chest Radiograph World Model via Predictive Sensing
• Feed-Forward One-Shot Animatable Textured Mesh Avatar Reconstruction
• Generating Humanless Environment Walkthroughs from Egocentric Walking Tour Videos
• Heterogeneous Decentralized Diffusion Models
• Data-Centric Meta-Learning for Robust Few-Shot Generalization
• Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation
• Olbedo: An Albedo and Shading Aerial Dataset for Large-Scale Outdoor Environments
• AD-GBC: Anisotropic Granular-Ball Skip-Connection Refiner for UNet-Based Medical Image Segmentation
• TextOVSR: Text-Guided Real-World Opera Video Super-Resolution
• DextER: Language-driven Dexterous Grasp Generation with Embodied Reasoning
• Proof-of-Perception: Certified Tool-Using Multimodal Reasoning with Compositional Conformal Guarantees
• Content-Aware Frequency Encoding for Implicit Neural Representations with Fourier-Chebyshev Features
• Curriculum Group Policy Optimization: Adaptive Sampling for Unleashing the Potential of Text-to-Image Generation
• Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning
• GDPO-SR: Group Direct Preference Optimization for One-Step Generative Image Super-Resolution
• β-CLIP: Text-Conditioned Contrastive Learning for Multi-Granular Vision-Language Alignment
• Chain of World: World Model Thinking in Latent Motion
• Beyond Euclidean Gossip: KL-Barycentric Consensus on Heterogeneous and Imbalanced Images
• FAVE: A Structured Benchmark for Fine-Grained Audio-Visual Temporal Evaluation in Multimodal LLMs
• Measure The Feature Universe: Topology-based Pseudo Labeling and Gravity Consistency for Source-Free Domain Adaptation
• RnG: A Unified Transformer for Complete 3D Modeling from Partial Observations
• SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving
• Computation and Communication Efficient Federated Unlearning via On-server Gradient Conflict Mitigation and Expression
• BHCast: Unlocking Black Hole Plasma Dynamics from a Single Blurry Image with Long-Term Forecasting
• Vision-Speech Models: Teaching Speech Models to Converse about Images
• LaSM: Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI Agents
• MuCo: Multi-turn Contrastive Learning for Multimodal Embedding Model
• Unleashing the Intrinsic Visual Representation Capability of Multimodal Large Language Models
• FoV-Net: Rotation-Invariant CAD B-rep Learning via Field-of-View Ray Casting
• Neural Distribution Prior for LiDAR Out-of-Distribution Detection
• MonoSAOD: Monocular 3D Object Detection with Sparsely Annotated Label
• Affordance-First Decomposition for Continual Learning in Video–Language Understanding
• EgoControl: Controllable Egocentric Video Generation via 3D Full-Body Poses
• PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image
• RevINN: An End-to-End Invertible Neural Network for Reversible Adversarial Examples Generation
• S2C2Seg: Semantic-Spatial Consistency and Category Optimization for Open-Vocabulary Segmentation
• JRM: Joint Reconstruction Model for Multiple Objects without Alignment
• Video2Robo: 3DGS-based Synthetic Data from One Video Enables Scalable Robot Learning
• Variation-aware Vision Token Dropping for Faster Large Vision-Language Models
• A Debiased Reconstruction-based Framework for Training-Free Detection of AI-Generated Images
• Momentum Memory for Knowledge Distillation in Computational Pathology
• STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot Narrative
• HySeg: Learning Generative Priors for Structure-Aware Remote Sensing Segmentation
• LDP-Slicing: Local Differential Privacy for Images via Randomized Bit-Plane Slicing
• Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning
• ConceptPrism: Concept Disentanglement in Personalized Diffusion Models via Residual Token Optimization
• MD2E: Modeling Depth-to-Edge Cues for Monocular Metric Depth Estimation
• Fast SceneScript: Fast and Accurate Language‑Based 3D Scene Understanding via Multi‑Token Prediction
• X-AVDT: Audio-Visual Cross-Attention for Robust Deepfake Detection
• The Missing GAP: From Solving Square Jigsaw Puzzles to Handling Real World Archaeological Fragments
• Don’t Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs
• RealBirdID: Benchmarking Bird Species Identification in the Era of MLLMs
• Material Magic Wand: Material-Aware Grouping of 3D Parts in Untextured Meshes
• PRISM: Learning a Shared Primitive Space for Transferable Skeleton Action Representation
• UnReflectAnything: RGB-Only Highlight Removal by Rendering Synthetic Specular Supervision
• WikiCLIP: An Efficient Contrastive Baseline for Open-domain Visual Entity Recognition
• MedGRPO: Multi-Task Reinforcement Learning for Heterogeneous Medical Video Understanding
• Curvature-Aware Zeroth-Order Optimization for Memory-Efficient Test-Time Adaptation
• Scalable Trajectory Generation for Whole-Body Mobile Manipulation
• Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI
• World in a Frame: Understanding Culture Mixing as a New Challenge for Vision-Language Models
• Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views
• Neural Dynamic GI: Random-Access Neural Compression for Temporal Lightmaps in Dynamic Lighting Environments
• Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration
• Real-Time Multimodal Fingertip Contact Detection via Depth and Motion Fusion for Vision-Based Human–Computer Interaction
• ARGUS: Defending Against Multimodal Indirect Prompt Injection via Steering Instruction-Following Behavior
• Concept Regions Matter: Benchmarking CLIP with a New Cluster-Importance Approach
• Differences That Matter: Auditing Models for Capability Gap Discovery and Rectification
• MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second
• SAIL: Similarity-Aware Guidance and Inter-Caption Augmentation-based Learning for Weakly-Supervised Dense Video Captioning
• EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing
• View-Aware Semantic Alignment for Aerial-Ground Person Re-Identification
• Neural Gabor Splatting: Enhanced Gaussian Splatting with Neural Gabor for High-frequency Surface Reconstruction
• PatchAlign3D: Local Feature Alignment for Dense 3D Shape Understanding
• SSM-Aware Token-Efficient VMamba via Adaptive Patch Pruning and Merging for Person Re-Identification
• GenErase: Generalizable and Semantically-Aware Concept Erasure in Diffusion Models
• FontCrafter: High-Fidelity Element-Driven Artistic Font Creation with Visual In-Context Generation
• MotionEnhancer: Leveraging Video Diffusion for Motion-Enhanced Vision-Language Models
• Recovering Physically Plausible Human-Object Interactions from Monocular Videos
• Not All Birds Look The Same: Identity-Preserving Generation For Birds
• One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework
• CraftMesh: High-Fidelity Generative Mesh Manipulation via Poisson Seamless Fusion
• Are Image-to-Video Models Good Zero-Shot Image Editors?
• CapNav: Benchmarking Vision Language Models on Capability-conditioned Indoor Navigation
• Nonparametric Deep Fine-grained Clustering with Low-Rank Guided Vision-Language Model
• SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation
• Pano3DComposer: Feed-Forward Compositional 3D Scene Generation from Single Panoramic Image
• DICArt: Advancing Category-level Articulated Object Pose Estimation in Discrete State-Spaces
• Harnessing the Power of Foundation Models for Accurate Material Classification
• Preference-Aligned LoRA Merging: Preserving Subspace Coverage and Addressing Directional Anisotropy
• PiLoT: Neural Pixel-to-3D Registration for UAV-based Ego and Target Geo-localization
• ReSAM: Refine, Requery, and Reinforce: Self-Prompting Point-Supervised Segmentation for Remote Sensing Images
• Teacher-Guided Routing for Sparse Vision Mixture-of-Experts
• RMIR: A Benchmark Dataset for Reasoning-Intensive Multimodal Image Retrieval
• PhysHead: Simulation-Ready Gaussian Head Avatars
• Act2See: Emergent Active Visual Perception for Video Reasoning
• Hugging Visual Prompt and Segmentation Tokens: Consistency Learning for Fine-Grained Visual Understanding in MLLMs
• Bidirectional Normalizing Flow: From Data to Noise and Back
• AXG-Reasoner: Error Detection and Explanation in Long Task Videos with Vision–Language Models
• DualSplat: Robust 3D Gaussian Splatting via Pseudo-Mask Bootstrapping from Reconstruction Failures
• Beyond Patches: Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation
• Lifting Unlabeled Internet-level Data for 3D Scene Understanding
• MOSAIC-GS: Monocular Scene Reconstruction via Advanced Initialization for Complex Dynamic Environments
• Render-to-Adapt: Unsupervised Personal Adaptation for Gaze Estimation
• The Surprising Effectiveness of Noise Pretraining for Implicit Neural Representations
• Unblur-SLAM: Dense Neural SLAM for Blurry Inputs
• LIFT and PLACE: A Simple, Stable, and Effective Knowledge Distillation Framework for Lightweight Diffusion Models
• Bootstrapping Multi-view Learning for Test-time Noisy Correspondence
• C-GenReg: Training-Free 3D Point Cloud Registration by Multi-View-Consistent Geometry-to-Image Generation with Probabilistic Modalities Fusion
• Probing and Bridging Geometry–Interaction Cues for Affordance Reasoning in Vision Foundation Models
• ManifoldNeuS: Manifold-aware View Optimizability for Pose-Free Neural Surface Reconstruction
• TeHOR: Text-Guided 3D Human and Object Reconstruction with Textures
• Language-Free Generative Editing from One Visual Example
• VIRST: Video-Instructed Reasoning Assistant for SpatioTemporal Segmentation
• Breaking Spurious Correlations: Uncertainty-Driven Causal Transformers for AU Detection
• DABO: Difficulty-Aware Bayesian Optimization with Diffusion-Learned Priors
• IR-HGP: Physically-Aware Gaussian Inverse Rendering for High-Illumination Scenes via Generative Priors
• Bias In, Bias Out? Finding Unbiased Subnetworks in Vanilla Models
• Unified Spherical Frontend: Learning Rotation-Equivariant Representations of Spherical Images from Any Camera
• Query2Uncertainty: Robust Uncertainty Quantification and Calibration for 3D Object Detection under Distribution Shift
• CG-Reasoner: Centroid-Guided Positional Reasoning Segmentation for Medical Imaging with a Robust Visual-Text Consistency Metric
• Understanding Counting Mechanisms in Large Language and Vision-Language Models
• VGA: Empowering Aerial-Ground Localization by Visual Geometry Alignment
• Adaptive Spatial-Temporal Window: Unlocking the Potential of Event Cameras in Heterogeneous Velocity Scenarios
• Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion
• iSHIFT: Lightweight Slow-Fast GUI Agent with Adaptive Perception
• S^2-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance
• Towards Knowledge-augmented Bayesian Deep Learning For Computer Vision
• Does YOLO Really Need to See Every Training Image in Every Epoch?
• MOFA-VTON: More Fashion Possibilities with Fine-Grained Adaptations in Virtual Try-On
• Video Generation with Stable Transparency via Shiftable RGB-A Distribution Learner
• HandVQA: Diagnosing and Improving Fine-Grained Spatial Reasoning about Hands in Vision-Language Models
• Diffusion-Based Makeup Transfer with Facial Region-Aware Makeup Features
• Interpretable and Steerable Concept Bottleneck Sparse Autoencoders
• DirectFisheye-GS: Enabling Native Fisheye Input in Gaussian Splatting with Cross-View Joint Optimization
• Long-Tail Internet Photo Reconstruction
• Learning Compact 3D Representations from Feed-Forward Novel View Synthesis
• Asynchronous Temporal Modeling with Two-Agent Framework for Streaming Dense Video Captioning
• fMRI-LM: Towards a Universal Foundation Model for Language-Aligned fMRI Understanding
• From Weights to Concepts: Data-Free Interpretability of CLIP via Singular Vector Decomposition
• Efficient Real-Time Raw-to-Raw Denoising for Extreme Low-Light Ultra HD Video on Mobile Devices
• REArtGS++: Generalizable Articulation Reconstruction with Temporal Geometry Constraint via Planar Gaussian Splatting
• DENALI: A Dataset Enabling Non-Line-of-Sight Spatial Reasoning with Low-Cost LiDARs
• Cluster-Aware Neural Collapse Prompt Tuning for Long-Tailed Generalization of Vision-Language Models
• A Combination of Noise and Bilateral Filters Achieve Supralinear and Scalable Adversarial Robustness in CNNs
• When to Think and When to Look: Uncertainty-Guided Lookback
• HandX: Scaling Bimanual Motion and Interaction Generation
• rPPG-VQA: A Video Quality Assessment Framework for Unsupervised rPPG Training
• Dynamic-eDiTor: Training-Free Text-Driven 4D Scene Editing with Multimodal Diffusion Transformer
• Synergistic Bleeding Region and Point Detection in Laparoscopic Surgical Videos
• MedCLIPSeg: Probabilistic Vision-Language Adaptation for Data-Efficient and Generalizable Medical Image Segmentation
• UNI-OOD: Unified Object- and Image-level Out-of-Distribution Detection via Cross-Context Attentive Vision-Language Modeling
• HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives
• Spatial-Frequency Collaborative Learning for Occluded Visible-Infrared Person Re-Identification
• CausalLens: Sensitivity-Guided Multi-Head Causal Intervention for Hallucination Mitigation in Large Vision-Language Models
• Do You Have Freestyle? Expressive Humanoid Locomotion via Audio Control
• Incentivizing Generative Zero-Shot Learning via Outcome-Reward Reinforcement Learning with Visual Cues
• GuideFlow: Constraint-Guided Flow Matching for Planning in End-to-End Autonomous Driving
• Beyond Top Activations: Efficient and Reliable Crowdsourced Evaluation of Automated Interpretability
• HERBench: A Benchmark for Multi-Evidence Integration in Video Question Answering
• Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learning
• OMG-Bench: A New Challenging Benchmark for Skeleton-based Online Micro Hand Gesture Recognition
• DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching
• Blink: Dynamic Visual Token Resolution for Enhanced Multimodal Understanding
• 3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation
• VesMamba: 3D Pulmonary Vessel Segmentation from CT images via Mamba with Structural Perception and Scale-aware Filtering
• Graph2Eval: Automatic Multimodal Task Generation for Agents via Knowledge Graphs
• MovieRecapsQA: A Multimodal Open-Ended Video Question-Answering Benchmark
• Learning Personalized Photographic Style from Pairwise User Preferences
• ImageRAGTurbo: Towards One-step Text-to-Image Generation with Retrieval-Augmented Diffusion Models
• Hierarchical Action Learning for Weakly-Supervised Action Segmentation
• Geometric Neural Distance Fields for Learning Human Motion Priors
• OmniSonic: Towards Universal and Holistic Audio Generation from Video and Text
• RawMetaDiff: Unlocking Extreme Darkness from Dual-Exposure RAW with Meta-Guided Diffusion
• Rethinking Dataset Distillation: Hard Truths about Soft Labels
• From Detection to Association: Learning Discriminative Object Embeddings for Multi-Object Tracking
• VideoMaMa: Mask-Guided Video Matting via Generative Prior
• Reinforcing Video Reasoning Segmentation to Think Before It Segments
• Ultra Diffusion Poser: Diffusion-Based Human Motion Tracking from Sparse Inertial Sensors and Ranging-based Between-sensor Distances
• SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signals
• How Much 3D Do Video Foundation Models Encode?
• Efficient Weighted Sampling via Score-based Generative Models
• Region-Adaptive Sampling for Diffusion Transformers
• Transition Matching Distillation for Fast Video Generation
• Correspondence-Attention Alignment for Multi-View Diffusion Models
• Beyond Duality: A Hybrid Framework of Leveraging Shared and Private Features for RGB-Event Object Detection
• StaR-KVQA: Structured Reasoning Traces for Implicit-Knowledge Visual Question Answering
• FoleyDesigner: Immersive Stereo Foley Generation with Precise Spatio-Temporal Alignment for Film Clips
• Rel-Zero: Harnessing Patch-Pair Invariance for Robust Zero-Watermarking Against AI Editing
• Mind the Gap: Transferring Labels to Align Object Detection Datasets
• Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision
• NOWA: Null-space Optical Watermark for Invisible Capture Fingerprinting and Tamper Localization
• 3D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understanding
• MMFace-DiT: A Dual-Stream Diffusion Transformer for High-Fidelity Multimodal Face Generation
• Models as Lego Builders: Assembling Malice from Benign Blocks via Semantic Blueprints
• VideoSeek: Long-Horizon Video Agent with Tool-Guided Seeking
• FALCON: False-Negative Aware Learning of Contrastive Negatives in Vision-Language Alignment
• AffordMatcher: Affordance Learning in 3D Scenes from Visual Signifiers
• Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation
• LiDeRe: A Lightweight Readout for Fast and Data-Efficient Dense Prediction
• EmoStyle: Emotion-Driven Image Stylization
• A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Space
• Breaking the Illusion: When Positive Meets Negative in Multimodal Decoding
• EG-3DVG: Expression and Geometry Aware Grounding Decoder for 3D Visual Grounding
• NexusFlow: Unifying Disparate Tasks under Partial Supervision via Invertible Flow Networks
• Dual Band Thermal Videography: Separating Time-Varying Reflection and Emission Near Ambient Conditions
• LLM-Guided Probabilistic Fusion for Label-Efficient Document Layout Analysis
• DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images
• From Observation to Action: Latent Action-based Primitive Segmentation for VLA Pre-training in Industrial Settings
• LNEM: Lunar Neural Elevation Model
• GenMatter: Perceiving Physical Objects with Generative Matter Models
• Physical Simulator In-the-Loop Video Generation
• Learning Multi-View Spatial Reasoning from Cross-View Relations
• FlashDecoder: Real-Time Latent-to-Pixel Streaming Decoder with Transformers
• Unsafe2Safe: Controllable Image Anonymization for Downstream Utility
• EmoThinker: Advancing Visual-Acoustic Emotion Analysis via Structural Token Selection and Chain-of-Thought Reasoning
• ReflexSplit: Single Image Reflection Separation via Layer Fusion-Separation
• Scalable Feature Matching via State Space Modeling and Sparse Correlation
• InstAP: Instance-Aware Vision-Language Pre-Train for Spatial-Temporal Understanding
• NESTOR: A Nested MOE-based Neural Operator for Large-Scale PDE Pre-Training
• DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning
• Functional Mean Flow in Hilbert Space
• MaskAdapt: Learning Flexible Motion Adaptation via Mask-Invariant Prior for Physics-Based Characters
• MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videos
• Fighting Hallucinations with Counterfactuals: Diffusion-Guided Perturbations for LVLM Hallucination Suppression
• FlowPortal: Residual-Corrected Flow for Training-Free Video Relighting and Background Replacement
• MRD: Multi-resolution Retrieval-Detection Fusion for High-Resolution Image Understanding
• E2EGS: Event-to-Edge Gaussian Splatting for Pose-Free 3D Reconstruction
• Stay in your Lane: Role Specific Queries with Overlap Suppression Loss for Dense Video Captioning
• Exploring Spatial Intelligence from a Generative Perspective
• Ultrasound-CLIP: Semantic-Aware Contrastive Pre-training for Ultrasound Image-Text Understanding
• Revisiting Geometric Obfuscation with Dual Convergent Lines for Privacy-Preserving Image Queries in Visual Localization
• SketchDeco: Training-Free Latent Composition for Precise Sketch Colourisation
• Quantized Residuals to Continuous Prompts for Few-Shot Class Incremental Learning in Vision-Language Models
• Perception Characteristics Distance: Measuring Stability and Robustness of Perception System in Dynamic Conditions under a Certain Decision Rule
• X-band Radar Non-Line-of-Sight Imaging
• TWEO: Transformers Without Extreme Outliers Enables FP8 Training And Quantization For Dummies
• Conditional Factuality Controlled LLMs with Generalization Certificates via Conformal Sampling
• ShotDirector: Directorially Controllable Multi-Shot Video Generation with Cinematographic Transitions
• CompBench: Benchmarking Complex Instruction-guided Image Editing
• Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark
• Sparsity-Aware Voxel Attention and Foreground Modulation for 3D Semantic Scene Completion
• Shedding Light on VLN Robustness: A Black-box Framework for Indoor Lighting-based Adversarial Attack
• LLMind: Bio-inspired Training-free Adaptive Visual Representations for Vision-Language Models
• AutoTraces: Autoregressive Trajectory Forecasting via Multimodal Large Language Models
• Shoe Style-Invariant and Ground-Aware Learning for Dense Foot Contact Estimation
• Active Perceptual Inference: A Corticothalamic-Inspired Dynamic Nested Recurrent Network for Multimodal Sentiment Analysis with Incomplete Data
• TeFlow: Enabling Multi-frame Supervision for Self-Supervised Feed-forward Scene Flow Estimation
• Advancing Image Classification with Discrete Diffusion Classification Modeling
• Speeding Up the Learning of 3D Gaussians with Much Shorter Gaussian Lists
• Beyond Depth: Evaluating the Width-centric Reasoning Capability of MLLMs
• VibeToken: Scaling 1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generations
• FlexTraj: Image-to-Video Generation with Flexible Point Trajectory Control
• Inferring Compositional 4D Scenes without Ever Seeing One
• Consistent Instance Field for Dynamic Scene Understanding
• Refaçade: Editing Object with Given Reference Texture
• PromptMoE: A Segmentation Refinement Framework Leveraging Mixture of Experts for Improved Prompting
• SV-GS: Sparse View 4D Reconstruction with Skeleton-Driven Gaussian Splatting
• DeepProtect: Proactive Face-Swapping Defense using Identity Blending and Attribute Distortion
• Stabilizing Feature Geometry in Noisy Pretrained Models for Robust Downstream Tasks
• Bidirectional Query-Driven Generation of Parametric CAD Sketch
• VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detection
• ConsID-Gen: View-Consistent and Identity-Preserving Image-to-Video Generation
• Bidirectional Cross-Modal Prompting for Event-Frame Asymmetric Stereo
• DemoFunGrasp: Universal Dexterous Functional Grasping via Demonstration-Editing Reinforcement Learning
• SAIDO: Generalizable Detection of AI-Generated Images via Scene-Aware and Importance-Guided Dynamic Optimization in Continual Learning
• ORBIT: Benchmarking SfM in the Wild with 360° Video
• NimbusGS: Unified 3D Scene Reconstruction under Hybrid Weather
• FedDAP: Domain-Aware Prototype Learning for Federated Learning under Domain Shift
• MedMO: Grounding and Understanding Multimodal Large Language Model for Medical Images
• Ar2Can: An Architect and an Artist Leveraging a Canvas for Multi-Human Generation
• Emergent Outlier View Rejection in Visual Geometry Grounded Transformers
• Neighbor GRPO: Contrastive ODE Policy Optimization Aligns Flow Models
• Time Without Time: Pseudo-Temporal Representation for Space-Time Super-Resolution
• No Labels, No Look-Ahead: Unsupervised Online Video Stabilization with Classical Priors
• HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics
• Training-free, Perceptually Consistent Low-Resolution Previews with High-Resolution Image for Efficient Workflows of Diffusion Models
• Source Models Leak What They Shouldn’t: Unlearning Zero-Shot Transfer in Domain Adaptation Through Adversarial Optimization
• LuxRemix: Lighting Decomposition and Remixing for Indoor Scenes
• Meta-Learning In-Context Enables Training-Free Cross Subject Brain Decoding
• GFRRN: Explore the Gaps in Single Image Reflection Removal
• DynamicTree: Interactive Real Tree Animation via Sparse Voxel Spectrum
• VoDaSuRe: A Large-Scale Dataset Revealing Domain Shift in Volumetric Super-Resolution
• Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Field
• PercHead: Perceptual Head Model for Single-Image 3D Head Reconstruction & Editing
• Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognition
• Learning to Act Robustly with View-Invariant Latent Actions
• Decoupled Generative Modeling for Human-Object Interaction Synthesis
• Multi-Scale Local Speculative Decoding for Image Generation
• Hierarchical Concept Embedding & Pursuit for Interpretable Image Classification
• Thinking Diffusion: Penalize and Guide Visual-Grounded Reasoning in Diffusion Multimodal Language Models
• HyperST: Hierarchical Hyperbolic Learning for Spatial Transcriptomics Prediction
• Intra-class Distribution-guided Generative Hashing with Neighbor Refinement for Cross-modal Retrieval
• Instruction-Guided Lesion Segmentation for Chest X-rays with Automatically Generated Large-Scale Dataset
• Seeing through boxes: Non-Line-of-Sight 3D Reconstruction from Radar Signals
• The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation
• Gastric-X: A Multimodal Multi-Phase Benchmark Dataset for Advancing Vision-Language Models in Gastric Cancer Analysis
• EgoFlow: Gradient-Guided Flow Matching for Egocentric 6DoF Object Motion Generation
• AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation
• Twin-T & TwintVQA: A Reliable Structure–Detail Separating VLM and a Comprehensive Benchmark for Chart and Table Tasks
• VISTA: A Test-Time Self-Improving Video Generation Agent
• Refracting Reality: Generating Images with Realistic Transparent Objects
• Efficient All-Pairs Correlation Volume Sampling for Optical Flow Estimation
• GeniNav: Generative Model Driven Image-Goal Navigation via Imagination-Guided Consistency Flow Matching
• Agile Deliberation: Concept Deliberation for Subjective Visual Classification
• PixARMesh: Autoregressive Mesh-Native Single-View Scene Reconstruction
• IF-Prune: Information-Flow Guided Token Pruning for Efficient Vision-Language Models
• AnyPcc: Compressing Any Point Cloud with a Single Universal Model
• ViT^3: Unlocking Test-Time Training in Vision
• Lifelong Imitation Learning with Multimodal Latent Replay and Incremental Adjustment
• OddGridBench: Exposing the Lack of Fine-Grained Visual Discrepancy Sensitivity in Multimodal Large Language Models
• Act Like a Pathologist: Tissue-Aware Whole Slide Image Reasoning
• OSA: Echocardiography Video Segmentation via Orthogonalized State Update and Anatomical Prior-aware Feature Enhancement
• The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery
• MMVIP: A Visible-infrared Paired Dataset for Multi-weather Marine Vision
• Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal Models
• Global Underwater Geolocation from Time-Lapse Polarization Imagery
• Data Leakage Detection and De-duplication in Large Scale Geospatial Image Datasets
• VES-RFT: Rewarding Visual Evidence Sensitivity to Mitigate Hallucinations in Large Vision–Language Models
• UniSpector: Towards Universal Open-set Defect Recognition via Spectral-Contrastive Visual Prompting
• ProjFlow: Projection Sampling with Flow Matching for Zero‑Shot Exact Spatial Motion Control
• Plant Taxonomy Meets Plant Counting: A Fine-Grained, Taxonomic Dataset for Counting Hundreds of Plant Species
• Prime Once, then Reprogram Locally: An Efficient Alternative to Black-Box Service Model Adaptation
• Cross-Modal Emotion Transfer for Emotion Editing in Talking Face Video
• InternData-A1: Pioneering High-Fidelity Synthetic Data for Pre-training Generalist Policy
• Efficient Training for Human Video Generation with Entropy-Guided Prioritized Progressive Learning
• Exact-GS: Mathematically Rigorous and Accurate 3D Gaussian Splatting for 3D X-ray Reconstruction
• PAUL: Uncertainty-Guided Partition and Augmentation for Robust Cross-View Geo-Localization under Noisy Correspondence
• Generalized-CVO: Fast and Correspondence-Free Local Point Cloud Registration with Second Order Riemannian Optimization
• Concept-Aware Batch Sampling Improves Language-Image Pretraining
• FaithFusion: Harmonizing Reconstruction and Generation via Pixel-wise Information Gain
• Event-based Motion Deblurring with Unpaired Data
• Envisioning the Future, One Step at a Time
• GeoFlow: Real-Time Fine-Grained Cross-View Geolocalization via Iterative Flow Prediction
• Globscope: Toward a Global View of the Loss Landscape
• Global Information Thresholding for Sufficient and Necessary Circuits
• QuietPrune: Query-Guided Early Token Pruning for Vision-Language Models
• RHCNet: Residual-Guided Hierarchical Calibration Network for Robust Underwater Object Detection
• MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation
• Towards Foundation Models for 3D Scene Understanding: Instance-Aware Self-Supervised Learning for Point Clouds
• Physical Object Understanding with a Physically Controllable World Model
• Authorize-on-Demand: Dynamic Authorization with Legality-Aware Intellectual Property Protection for VLMs
• A Geometric Algebra-Informed 3DGS Framework for Wireless Channel Prediction
• RaGS: Unleashing 3D Gaussian Splatting from 4D Radar and Monocular Cue for 3D Object Detection
• Event Structural Valley: A Unified Theoretical and Practical Framework for Event Camera Autofocus
• A Training-Free Style-Personalization via SVD-Based Feature Decomposition
• Spectrally Distilled Representations Aligned with Instruction-Augmented LLMs for Satellite Imagery
• Extend3D: Town-Scale 3D Generation
• Label-Free Cross-Task LoRA Merging with Null-Space Compression
• VAD-GS: Visibility-Aware Densification for 3D Gaussian Splatting in Dynamic Urban Scenes
• Heuristic Self-Paced Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions
• Glove2Hand: Synthesizing Natural Hand-Object Interaction from Multi-Modal Sensing Gloves
• Reflection Separation from a Single Image via Joint Latent Diffusion
• BiGMINT: Biologically-guided Hierarchical Multimodal Integration for Modeling Multiple Compound Activities in Drug Discovery
• UniPR: Unified Object-level Real-to-Sim Perception and Reconstruction from a Single Stereo Pair
• QueryMe: Query-Driven Open-Vocabulary 3D Object Affordances Grounding from Multimodal Evidence
• WaDi: Weight Direction-aware Distillation for One-step Image Synthesis
• UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation
• Cross-Instance Gaussian Splatting Registration via Geometry-Aware Feature-Guided Alignment
• The Midas Touch for Metric Depth
• SoC: Semantic Orthogonal Calibration for Test-Time Prompt Tuning
• TEAR: Temporal-aware Automated Red-teaming for Text-to-Video Models
• Divide, Conquer, and Aggregate: Asymmetric Experts for Class-Imbalanced Semi-Supervised Medical Image Segmentation
• HumanBA: Human-Aware Bundle Adjustment via Global Human-Camera Decoupling
• Out of Sight, Out of Track: Adversarial Attacks on Propagation-based Multi-Object Trackers via Query State Manipulation
• Spatio-Temporal Conditional Denoising Transformer for Modality-Missing RGBT Tracking
• HandDreamer: Zero-Shot Text to 3D Hand Model Generation using Corrective Hand Shape Guidance
• GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering
• VL-RouterBench: A Benchmark for Vision–Language Model Routing
• STARFlow-V: End-to-End Video Generative Modeling with Autoregressive Normalizing Flows
• GT-SVJ: Generative-Transformer-Based Self-Supervised Video Judge For Efficient Video Reward Modeling
• Gyro-based Deep Video Deblurring
• DeepAlign: Mitigating Modality Conflict through Modality-Specific Alignment
• Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model
• MSPT: Efficient Large-Scale Physical Modeling via Parallelized Multi-Scale Attention
• COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimation
• Differentiable Adaptive 4D Structured Illumination for Joint Capture of Shape and Reflectance
• PinPoint: Evaluation of Composed Image Retrieval with Explicit Negatives, Multi-Image Queries, and Paraphrase Testing
• Splatent: Splatting Diffusion Latents for Novel View Synthesis
• AvatarPointillist: AutoRegressive 4D Gaussian Avatarization
• Universal 3D Shape Matching via Coarse-to-Fine Language Guidance
• SeeU: Seeing the Unseen World via 4D Dynamics-aware Generation
• Tackling Alignment Ambiguity in Person Retrieval through Conversational Attribute Mining
• SyncMos: Scalable Motion Synchronisation for Multi-Agent Scene Interaction
• CLAY: Conditional Visual Similarity Modulation in Vision-Language Embedding Space
• Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding
• Make it SING: Analyzing Semantic Invariants in Classifiers
• TGSFormer: Scalable Temporal Gaussian Splatting for Embodied Semantic Scene Completion
• VLIC: Vision-Language Models As Perceptual Judges for Human-Aligned Image Compression
• Continual Distillation of Teachers from Different Domains
• Spectral Scalpel: Amplifying Adjacent Action Discrepancy via Frequency-Selective Filtering for Skeleton-Based Action Segmentation
• Pantheon360: Taming Digital Twin Generation via 3D-Aware 360° Video Diffusion
• TopoSlide: Topologically-Informed Histopathology Whole Slide Image Representation Learning
• Parameter-efficient Continual Learning for Enhancing Plasticity without Forgetting under Limited Model Capacity
• All in One: Unifying Deepfake Detection, Tampering Localization, and Source Tracing with a Robust Landmark-Identity Watermark
• HG-Lane: High-Fidelity Generation of Lane Scenes under Adverse Weather and Lighting Conditions without Re-annotation
• Real-Time Dynamic Scene Rendering with Controlled Compressibility and Contact Awareness
• Building a Precise Video Language with Human–AI Oversight
• Illumination-Consistent Human-Scene Reconstruction from Monocular Video
• Better than Average: Spatially-Aware Aggregation of Segmentation Uncertainty Improves Downstream Performance
• Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptation
• Learning Effective Sign Features without Text for Gloss-free Sign Language Translation
• GraphVLM: Benchmarking Vision Language Models for Multimodal Graph Learning
• Linguistic Priors for Visual Decoupling: Towards Symmetric Vision-Brain Alignment
• ReScene4D: Temporally Consistent Semantic Instance Segmentation of Evolving Indoor 3D Scenes
• Neuro-Cognitive Reward Modeling for Human-Centered Autonomous Vehicle Control
• SPEGC: Continual Test-Time Adaptation via Semantic-Prompt-Enhanced Graph Clustering for Medical Image Segmentation
• A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large Vision-Language Models
• PointCSP: Cross-Sample Semantic Propagation and Stability Preservation in Self-Supervised Point Cloud Learning
• TRM-VLA: Temporal-Aware Chain-of-Thought Reasoning and Memorization for Vision-Language-Action Models
• GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation
• Tokenization Allows Multimodal Large Language Models to Understand, Generate and Edit Architectural Floor Plans
• ChimeraLoRA: Multi-Head LoRA-Guided Synthetic Datasets
• InstantRetouch: Efficient and High-Fidelity Instruction-Guided Image Retouching with Bilateral Space
• Narrative Weaver: Towards Controllable Long-Range Visual Consistency with Multi-Modal Conditioning
• MV2UV: Generating High-quality UV Texture Maps with Multiview Prompts
• HulluEdit: Single-Pass Evidence-Consistent Subspace Editing for Mitigating Hallucinations in Large Vision-Language Models
• STAC: Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstruction
• Semi-supervised Echocardiography Video Segmentation via Anchor Semantic Awareness and Continuous Pseudo-label Reforging
• STiTch: Semantic Transition and Transportation in Collaboration for Training-Free Zero-Shot Composed Image Retrieval
• UZ3DVG: Unaided Zero-Shot 3D Visual Grounding with Generated Language Conditions
• AdaPrior: Bayesian-Inspired Adaptive Prior Correction for Long-Tailed Continual Learning
• Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning
• Anchoring and Rescaling Attention for Semantically Coherent Inbetweening
• ManifoldGD: Training-Free Hierarchical Manifold Guidance for Diffusion-Based Dataset Distillation
• Contact-Aware Neural Dynamics
• GLINT: Modeling Scene-Scale Transparency via Gaussian Radiance Transport
• THE MORE, THE MERRIER: CONTRASTIVE FUSION FOR HIGHER-ORDER MULTIMODAL ALIGNMENT
• Occluded Human Body Capture with Frequency Domain Denoising Prior
• EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformer
• From Manuals to Actions: A Unified VLA Model for Chain-of-Thought Manual Generation and Robotic Manipulation
• RetimeGS: Continuous-Time Reconstruction of 4D Gaussian Splatting
• Probabilistic Discrepancy Learning for Roadside LiDAR Scene Completion
• VDOT: Efficient Unified Video Creation via Optimal Transport Distillation
• LaMoGen: Language to Motion Generation Through LLM-Guided Symbolic Inference
• PhyGaP: Physically-Grounded Gaussians with Polarization Cues
• Let Your Image Move with Your Motion! -- Implicit Multi-Object Multi-Motion Transfer
• The devil is in the details: Enhancing Video Virtual Try-On via Keyframe-Driven Details Injection
• Improving Controllable Generation: Faster Training and Better Performance via x0-Supervision
• ChronoGS: Disentangling Invariants and Changes in Multi-Period Scenes
• Your Dissimilarities Define You: Complementary Learning Exploiting Class Diversities
• R3-PCQA: Ray-Reprojection-Reinforcement for No-Reference 3D Point Cloud Quality Assessment
• Adaptive Data Augmentation with Multi-armed Bandit: Sample-Efficient Embedding Calibration for Implicit Pattern Recognition
• Multi-view Crowd Tracking Transformer with View-Ground Interactions Under Large Real-World Scenes
• UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass
• Will Multimodal Models Be Dazzled by Multi-Image Visual Puzzles?
• Hoi! - A Multimodal Dataset for Force-Grounded, Cross-View Articulated Manipulation
• Composite-Attribute Person Re-Identification via Pose-Guided Disentanglement
• Inconsistency-aware Multimodal Schrödinger Bridge for Deepfake Localization
• EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editing
• Edit-aware RAW reconstruction
• OVI-MAP: Open-Vocabulary Instance-Semantic Mapping
• MaxMark: High-Capacity Diffusion-Native Watermarking via Robust and Invertible Latent Embedding
• Reinforcing Structured Chain-of-Thought for Video Understanding
• Bridging Domains through Subspace-Aware Model Merging
• Representing 3D Faces with Learnable B-Spline Volumes
• CRAFT-LoRA: Content-Style Personalization via Rank-Constrained Adaptation and Training-Free Fusion
• GaussianZoom: Progressive Zoom-in Generative 3D Gaussian Splatting with Geometric and Semantic Guidance
• Globally Optimal Pose from Orthographic Silhouettes
• PSDesigner: Automated Graphic Design with a Human-Like Creative Workflow
• Prune Wisely, Reconstruct Sharply: Compact 3D Gaussian Splatting via Adaptive Pruning and Difference-of-Gaussian Primitives
• Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection
• Seeing Through Touch: Tactile-Driven Visual Localization of Material Regions
• Exposing Functional Fusion: A New Class of Strategic Backdoor in Dynamic Prompt Architectures
• Gau-Occ: Geometry-Completed Gaussians for Multi-Modal 3D Occupancy Prediction
• MeshRipple: Structured Autoregressive Generation of Artist-Meshes
• SAM 3D: 3Dfy Anything in Images
• E-3DPSM: A State Machine for Event-based Egocentric 3D Human Pose Estimation
• MLLM-HWSI: A Multimodal Large Language Model for Hierarchical Whole Slide Image Understanding
• Learnability-Driven Submodular Optimization for Active Roadside 3D Detection
• MimiCAT: Mimic with Correspondence-Aware Cascade-Transformer for Category-Free 3D Pose Transfer
• UDAPose: Unsupervised Domain Adaptation for Low-Light Human Pose Estimation
• LoD-Loc v3: Generalized Aerial Localization in Dense Cities using Instance Silhouette Alignment
• SCE-SLAM: Scale-Consistent Monocular SLAM via Scene Coordinate Embeddings
• CLIP Is Shortsighted: Paying Attention Beyond the First Sentence
• NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoning
• Eliminate Distance Differences Induced by Backdoor Attacks: Layer-Selective Training and Clipping to Mask Backdoor Models
• CoLoR: The Devil is in Scene Coordinate Regression for Large-Scale Visual Localization
• Scene-Centric Unsupervised Video Panoptic Segmentation
• CrossVL: Complexity-Aware Feature Routing and Paired Curriculum for Cross-View Vision-Language Detection
• Translating Signals to Languages for sEMG-Based Activity Recognition
• Vinedresser3D: Towards Agentic Text-guided 3D Editing
• TAMER: A Tri-Modal Contrastive Alignment and Multi-Scale Embedding Refinement Framework for Zero-Shot ECG Diagnosis
• Omni-MMSI: Toward Identity-attributed Social Interaction Understanding
• Ref4D-VideoBench: Four-Dimensional Reference-Based Evaluation of Text-to-Video Generative Models
• What Matters in Practical Learned Image Compression
• PureProof: Diffusion-Resistant Black-box Targeted Attack on Large Vision-Language Models
• The Road Less Seen: Segment Exploration for Weakly Supervised Video Anomaly Detection
• LiDAS: Lighting-driven Dynamic Active Sensing for Nighttime Perception
• PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning
• Clair Obscur: an Illumination-Aware Method for Real-World Image Vectorization
• Physical Adversarial Clothing Evades Visible-Thermal Detectors via Non-Overlapping RGB-T Pattern
• An Instance-Centric Panoptic Occupancy Prediction Benchmark for Autonomous Driving
• Semantic-Adaptive Diffusion for Dynamic Spatiotemporal Fusion
• TruckDrive: Long-Range Autonomous Highway Driving Dataset
• First Frame Is the Place to Go for Video Content Customization
• SLVMEval: Synthetic Meta Evaluation Benchmark for Text-to-Long Video Generation
• SoliReward: Mitigating Susceptibility to Reward Hacking and Annotation Noise in Video Generation Reward Models
• R4-CGQA: Retrieval-based Vision Language Models for Computer Graphics Image Quality Assessment
• OMG-Avatar: One-shot Multi-LOD Gaussian Head Avatar
• WebGym: Scaling Training Environments for Long-Horizon Visual Web Agents with Realistic Tasks
• Frequency-domain Manipulation for Face Obfuscation
• Test-Time Multi-Prompt Adaptation for Open-Vocabulary Remote Sensing Image Segmentation
• HierUQ: Hierarchical Uncertainty Quantification with Adaptive Granularity Reconciliation for Degraded Image Classification
• DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers
• D-Prism: Differentiable Primitives for Structured Dynamic Modeling
• An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning
• FACE: A Face-based Autoregressive Representation for High-Fidelity and Efficient Mesh Generation
• Local Motion Matters: A Deconstruct–Recompose Paradigm for Reinforcement Learning Pre-training from Videos
• HAD: Heterogeneity-Aware Distillation for Lifelong Heterogeneous Learning
• WildCap: Facial Albedo Capture in the Wild via Hybrid Inverse Rendering
• Mostly Text, Smart Visuals: Asymmetric Text-Visual Pruning for Large Vision-Language Models
• Learning to Refuse: Refusal-Aware Reinforcement Fine-Tuning for Hard-Irrelevant Queries in Video Temporal Grounding
• GeoTikzBridge: Advancing Multimodal Code Generation for Geometric Perception and Reasoning
• UniRefiner: Teaching Pre-trained ViTs to Self-Dispose Dross via Contrastive Register
• InterRVOS: Interaction-Aware Referring Video Object Segmentation
• Heuristic-inspired Reasoning Priors Facilitate Data-Efficient Referring Object Detection
• TrackMAE: Video Representation Learning via Track Mask and Predict
• RARE: Learn to RAnk and REtrieve for Monocular 3D Object Detection
• Enhancing Mixture-of-Experts Specialization via Cluster-Aware Upcycling
• VA-π: Variational Policy Alignment for Pixel-Aware Autoregressive Generation
• MotionEdit: Benchmarking and Learning Motion-Centric Image Editing
• Stable Mean Flow: Lyapunov-Inspired One-Step Flow Matching
• A³: Towards Advertising Aesthetic Assessment
• PPISP: Physically-Plausible Compensation and Control of Photometric Variations in Radiance Field Reconstruction
• P2GS: Physical Prior-guided Gaussian Splatting for Photometrically Consistent Urban Reconstruction
• Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization
• D2FANet: Enhancing Video Object Detection with Dual-Domain Feature Aggregation Network
• META: Meta Evolution of Tool Trajectory Adaptation for Long-Video Understanding
• Visual-RRT: Finding Paths toward Visual-Goals via Differentiable Rendering
• SPDMark: Selective Parameter Displacement for Robust Video Watermarking
• ResiHMR: Residual-Limb Aware Single-Image 3D Human Mesh Recovery for Individuals with Limb Loss
• CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction
• OVSegDT: Segmenting Transformer for Open-Vocabulary Object Goal Navigation
• 4D Primitive-Mâché: Glueing Primitives for Persistent 4D Scene Reconstruction
• STAvatar: Soft Binding and Temporal Density Control for Monocular 3D Head Avatars Reconstruction
• MotionScale: Reconstructing Appearance, Geometry, and Motion of Dynamic Scenes with Scalable 4D Gaussian Splatting
• Radiance Meshes for Volumetric Reconstruction
• Memory-Efficient Fine-Tuning Diffusion Transformers via Dynamic Patch Sampling and Block Skipping
• MambaLiteUNet: Cross-Gated Adaptive Feature Fusion for Robust Skin Lesion Segmentation
• When Local Rules Create Global Order: Self-Organized Representation Learning for Latent Diffusion Models
• E^2-SCI: Elastic Edge–Cloud Speculative Decoding via Credit Inertia
• MoReGen: Multi-Agent Motion-Reasoning Engine for Code-based Text-to-Video Synthesis
• RecoverMark: Robust Watermarking for Localization and Recovery of Manipulated Faces
• Affostruction: 3D Affordance Grounding with Generative Reconstruction
• Variational Graph-based Normal Integration
• Affine Perspective-Three-Point Problem
• Breaking Multimodal LLM Safety via Video-Driven Prompting
• Energy-GS: Image Energy-guided Pose Alignment Gaussian Splatting with redesigned pose gradient flow
• PRIMU: Uncertainty Estimation for Novel Views in Gaussian Splatting from Primitive-Based Representations of Error and Coverage
• SGI: Structured 2D Gaussians for Efficient and Compact Large Image Representation
• DFD-HR: Generalizable Deepfake Detection via Hierarchical Routing Learning
• DRM: Diffusion-based Reward Model With Step-wise Guidance
• Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning
• Rethinking Occlusion Modeling for UAV Tracking
• Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post‑hoc Debiasing in Vision-Language Models
• TiViBench: Benchmarking Think-in-Video Reasoning for Video Generation
• Enhancing Accuracy of Uncertainty Estimation in Appearance-based Gaze Tracking with Probabilistic Evaluation and Calibration
• HamiPose: Hamiltonian Optimization for Unsupervised Domain Adaptive Pose Estimation
• E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Driving
• MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering
• Face2Scene: Using Facial Degradation as an Oracle for Diffusion-Based Scene Restoration
• Align Once to Explain: Feature Alignment for Scalable B-cosification of Foundational Vision Transformers
• Scaling Dense Event-Stream Pretraining from Visual Foundation Models
• S2D: Sparse to Dense Lifting for 3D Reconstruction with Minimal Inputs
• Towards Stable Self-Supervised Object Representations in Unconstrained Egocentric Video
• RetouchIQ: MLLM Agents for Instruction-Based Image Retouching with Generalist Reward
• Back to Source: Open-Set Continual Test-Time Adaptation via Domain Compensation
• COPE: Consistent Occlusion and Prompt Enhancement Network for Occluded Person Re-identification
• DiffSoup: Direct Differentiable Rasterization of Triangle Soup for Extreme Radiance Field Simplification
• SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotations
• Artiverse: A Diverse and Physically Grounded Dataset for Articulated Objects
• OpenVO: Open-World Visual Odometry with Temporal Dynamics Awareness
• SmokeSVD: Smoke Reconstruction from A Single View via Progressive Novel View Synthesis and Refinement with Diffusion Models
• Learning to See Through a Baby’s Eyes: Early Visual Diets Enable Robust Visual Intelligence in Humans and Machines
• SplatSuRe: Selective Super-Resolution for Multi-view Consistent 3D Gaussian Splatting
• Towards Sparse Video Understanding and Reasoning
• Diverse Video Generation with Determinantal Point Process-Guided Policy Optimization
• Omni-3DEdit: Generalized Versatile 3D Editing in One-Pass
• Yume1.5: A Text-Controlled Interactive World Generation Model
• MV-RoMa: From Pairwise Matching into Multi-View Track Reconstruction
• DuetSVG: Unified Multimodal SVG Generation with Internal Visual Guidance
• Anti-Degradation Lifelong Multi-View Clustering
• Learning to See and Act: Task-Aware Virtual View Exploration for Robotic Manipulation
• Scaling Self-Supervised and Cross-Modal Pretraining for Volumetric CT Transformers
• Common Inpainted Objects In-N-Out of Context
• SEASON: Mitigating Temporal Hallucination in Video Large Language Models via Self-Diagnostic Contrastive Decoding
• EmoTaG: Emotion-Aware Talking Head Synthesis on Gaussian Splatting with Few-Shot Personalization
• Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following
• Erasing Thousands of Concepts: Towards Scalable and Practical Concept Erasure for Text-to-Image Diffusion Models
• Hier-COS: Making Deep Features Hierarchy-aware via Composition of Orthogonal Subspaces
• LAMP: Language-Assisted Motion Planning for Controllable Video Generation
• Lynx: Towards High-Fidelity Personalized Video Generation
• Phrase-Grounding-Aware Supervised Fine-Tuning for Chart Recognition via Side-Masked Attention
• U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generation
• Towards Generalized Multimodal Homography Estimation
• Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment
• EfficientMonoHair: Fast Strand-Level Reconstruction from Monocular Video via Multi-View Direction Fusion
• MAMMA: Markerless Accurate Multi-person Motion Acquisition
• TerraSeg: Self-Supervised Ground Segmentation for Any LiDAR
• Physically Inspired Gaussian Splatting for HDR Novel View Synthesis
• SCAPO: Self-Supervised Category-Level Articulated Pose Estimation from a Single 3D Observation
• Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Driving
• BinaryAttention: One-Bit QK-Attention for Vision and Diffusion Transformers
• OneOcc: Semantic Occupancy Prediction for Legged Robots with a Single Panoramic Camera
• Optical Diffraction-based Convolution for Semiconductor Lithography
• Revisiting Optimal Coding for I-ToF under Practical Sensor Constraints
• Look Before You Fuse: 2D-Guided Cross-Modal Alignment for Robust 3D Detection
• What Is the Optimal Ranking Score Between Precision and Recall? We Can Always Find It and It Is Rarely F1
• Prompt-Free Universal Region Proposal Network
• NanoSD: Edge Efficient Foundation Model for Real Time Image Restoration
• SpaceTimePilot: Generative Rendering of Dynamic Scenes Across Space and Time
• POUR: A Provably Optimal Method for Unlearning Representation via Neural Collapse
• Omni-Attribute: Open-vocabulary Attribute Encoder for Visual Concept Personalization
• TokenHand: Discrete Token Representation for Efficient Hand Mesh Reconstruction
• BiOTPrompt: Bidirectional Optimal Transport Guided Prompting for Disease Evolution-aware Radiology Report Generation
• Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR
• Efficiently Reconstructing Dynamic Scenes One D4RT at a Time
• SOUPLE: Enhancing Audio-Visual Localization and Segmentation with Learnable Prompt Contexts
• Protego: User-Centric Pose-Invariant Privacy Protection Against Face Recognition-Induced Digital Footprint Exposure
• Ego: Embedding-Guided Personalization of Vision-Language Models
• Learning What Helps: Task-Aligned Context Selection for Vision Tasks
• MR. Illuminate: Zero-Shot Low-Light Image Enhancement with Diffusion Prior
• ParallelVLM: Lossless Video-LLM Acceleration with Visual Alignment Aware Parallel Speculative Decoding
• APPO: Attention-guided Perception Policy Optimization for Video Reasoning
• What Are You Doing? A Closer Look at Controllable Human Video Generation
• Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching
• Same Content, Different Answers: Cross-Modal Inconsistency in MLLMs
• Towards High-Quality Image Segmentation: Improving Topology Accuracy by Penalizing Neighbor Pixels
• UAST: Unified Active Search and Tracking for Arbitrary Targets with UAVs
• Enhancing Hands in 3D Whole-Body Pose Estimation with Conditional Hands Modulator
• GeoFree-CoSeg: Unsupervised Point Cloud-Image Cross-Modal Co-Segmentation Without Geometric Alignment
• ID-Sim: An Identity-Focused Similarity Metric
• SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model
• DiffusionFF: A Diffusion-based Framework for Joint Face Forgery Detection and Fine-Grained Artifact Localization
• GUIDE: A Benchmark for Understanding and Assisting Users in Open-Ended GUI Tasks
• PGA: Prior-free Generative Attack for Practical No-box Scenario
• Lipschitz Optimization for Formal Verification of Homographies
• Cross-Scale Pansharpening via ScaleFormer and the PanScale Benchmark
• DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation
• Visual Grounding for Object Questions
• OnlineHMR: Video-based Online World-Grounded Human Mesh Recovery
• ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization
• MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models
• Dual-Prototype-Guided Multi-task Learning for Unsupervised Anomaly Detection and Classification
• Back to the Feature: Explaining Video Classifiers with Video Counterfactual Explanations
• PROMPTMINER: Black-Box Prompt Stealing against Text-to-Image Generative Models via Reinforcement Learning and VLM-Guided Optimization
• UniRain: Unified Image Deraining with RAG-based Dataset Distillation and Multi-objective Reweighted Optimization
• Language Does Matter for Cross-Domain Few-Shot Visual Feature Enhancement
• HTNav: A Hybrid Navigation Framework with Tiered Structure for Urban Aerial Vision-and-Language Navigation
• ShowUI-π: Flow-based Generative Models as GUI Dexterous Hands
• CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing
• SAR2Net: Learning Spatially Anchored Representations for Retrieval-Guided Cross-Stain Alignment
• AVATAR: Reinforcement Learning to See, Hear, and Reason Over Video
• Beyond Perceptual Shortcuts: Causal-Inspired Debiasing Optimization for Generalizable Video Reasoning in Lightweight MLLMs
• OSPO: Object-Centric Self-Improving Preference Optimization for Text-to-Image Generation
• BridgeEQA: Virtual Embodied Agents for Real Bridge Inspections
• HypeVPR: Exploring Hyperbolic Space for Perspective to Equirectangular Visual Place Recognition
• Z-Order Transformer for Feed-Forward Gaussian Splatting
• UST-Hand: An Uncertainty-aware Spatiotemporal Point Cloud Interaction Network for 3D Self-supervised Hand Pose Estimation
• Style-GRPO: Semantic-Aware Preference Optimization for Image Style Transfer Guided by Reward Modeling
• Do Vision-Language Models Leak What They Learn? Adaptive Token-Weighted Model Inversion Attacks
• Paparazzo: Active Mapping of Moving 3D Objects
• PHANTOM: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics
• Robust Remote Sensing Image–Text Retrieval with Noisy Correspondence
• OrionEdit: Bridging Reference and Source Images for Generalized Cross-Image Editing
• Neural Field-Based 3D Surface Reconstruction of Microstructures from Multi-Detector Signals in Scanning Electron Microscopy
• Multigrain-aware Semantic Prototype Scanning and Tri-Token Prompt Learning Embraced High-Order RWKV for Pan-Sharpening
• CADFS: A Big CAD Program Dataset and Framework for Computer-Aided Design with Large Language Models
• ACPV-Net: All-Class Polygonal Vectorization for Seamless Vector Map Generation from Aerial Imagery
• GR-Gauge: Cost-efficient Training Configuration By Gauging the Gradient Redundancy
• Disco-GS: Gaussian Splatting in Dynamic Color Lighting
• ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering
• From Few-way to Many-way: Rethinking Few-shot Fine-grained Image Classification
• DETACH : Decomposed Spatio-Temporal Alignment for Exocentric Video and Ambient Sensors with Staged Learning
• Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance Scheduling
• Residual Primitive Fitting of 3D Shapes with SuperFrusta
• NeuroFlow: Toward Unified Visual Encoding and Decoding from Neural Activity
• Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning
• Generalizable Radio-Frequency Radiance Fields for Spatial Spectrum Synthesis
• Leveraging Multispectral Sensors for Color Correction in Mobile Cameras
• LVLM-Aided Alignment of Task-Specific Vision Models
• ClusterMark: Towards Robust Watermarking for Autoregressive Image Generators with Visual Token Clustering
• BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generation
• FlashLips: 100-FPS Mask-Free Latent Lip-Sync using Reconstruction Instead of Diffusion or GANs
• Rectifying Latent Space for Generative Single-Image Reflection Removal
• AVION: Aerial Vision–Language Instruction from Offline Teacher to Prompt-Tuned Network
• CycleBEV: Regularizing View Transformation Networks via View Cycle Consistency for Bird’s-Eye-View Semantic Segmentation
• Context-Nav: Context-Driven Exploration and Viewpoint-Aware 3D Spatial Reasoning for Instance Navigation
• Real-World Point Tracking with Verifier-Guided Pseudo-Labeling
• PaNDaS: Learnable Shape Interpolation Modeling with Localized Control
• Selection-as-Nonlinearity: Bridging Attention and Activation via a Joint Game–Decision Lens for Interpretable, Discriminative Visual Representations
• CIGMA: Causal Information-Gain Mechanistic Attribution of Attention Heads in Vision Transformers
• G^2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning
• Beyond Success: Refining Elegant Robot Manipulation from Mixed-Quality Data via Just-in-Time Intervention
• CGU-Bayes: Causal Graph Uncertainty-Guided Bayesian Inference for Domain Generalization
• Towards Open-Vocabulary Industrial Defect Understanding with a Large-Scale Multimodal Dataset
• Cross-Hand Latent Representation for Vision-Language-Action Models
• StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars
• Geometry-Guided 3D Visual Token Pruning for Video-Language Models
• Multimodal Continual Instruction Tuning with Dynamic Gradient Guidance
• MuViT: Multi-Resolution Vision Transformers for Learning Across Scales in Microscopy
• TANGO: Learning Distribution-wise Foundation Prior Consistency and Instance-wise Style Calibration for Medical Image Generalization
• Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers
• FUSER: Feed-Forward Multiview 3D Registration Transformer and SE(3)^N Diffusion Refinement
• Dynamic Momentum Recalibration in Online Gradient Learning
• Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models
• COT-FM: Cluster-wise Optimal Transport Flow Matching
• ForceVLA2: Unleashing Hybrid Force-Position Control with Force Awareness for Contact-Rich Manipulation
• VideoNet: A Large-Scale Dataset for Domain-Specific Action Recognition
• PTC-Depth: Pose-Refined Monocular Depth Estimation with Temporal Consistency
• Rewis3d: Reconstruction Improves Weakly-Supervised Semantic Segmentation
• PET-DINO: Unifying Visual Cues into Grounding DINO with Prompt-Enriched Training
• Aesthetic Camera Viewpoint Suggestion with 3D Aesthetic Field
• Attention-aware Inference Optimizations for Large Vision-Language Models with Memory-efficient Decoding
• UniCorrn: Unified Correspondence Transformer Across 2D and 3D
• Keep it SymPL: Symbolic Projective Layout for Allocentric Spatial Reasoning in Vision-Language Models
• Rethinking Concept Bottleneck Models: From Pitfalls to Solutions
• Residual Diffusion Bridge Model for Image Restoration
• Hearing the Room Through the Shape of the Drum: Modal-Guided Sound Recovery from Multi-Point Surface Vibrations
• Bridging Facial Understanding and Animation via Language Models
• Ghosts in the Point Clouds: De-glaring LiDAR in the Transient Domain
• Pluggable Pruning with Contiguous Layer Distillation for Diffusion Transformers
• Ego-1K – A Large-Scale Multiview Video Dataset for Egocentric Vision
• RAID: Retrieval-Augmented Anomaly Detection
• Confidence-Guided Multi-Scale Aggregation for Sparse-View High-Resolution 3D Gaussian Splatting
• Predicting Spatial Transcriptomics from Histology Images via High-Order Multi-Cell Interaction Modeling
• FlexAvatar: Learning Complete 3D Head Avatars with Partial Supervision
• TROPHIES: Temporal Reconstruction of Places, Humans, and Cameras from Multi-view Videos
• Any2Any 3D Diffusion Models with Knowledge Transfer: A Radiotherapy Planning Study
• Dynamic Exposure Burst Image Restoration
• Layered 4D-Rotor Gaussian Splatting: A Compressed Representation for Long Dynamic Scenes
• Co-Me: Confidence Guided Token Merging for Visual Geometric Transformers
• M^3KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation
• Any4D: Unified Feed-Forward Metric 4D Reconstruction
• DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolution
• Kaleidoscopic Scintillation Event Imaging
• Self-Consistency for LLM-Based Motion Trajectory Generation and Verification
• CycleManip: Enabling Cycle-based Manipulation via Effective History Perception and Understanding
• CARD: Correlation Aware Restoration with Diffusion
• Event6D: Event-based Novel Object 6D Pose Tracking
• Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding
• SurgCoT: Advancing Spatiotemporal Reasoning in Surgical Videos through a Chain-of-Thought Benchmark
• OpenMarcie: Dataset for Multimodal Action Recognition in Industrial Environments
• YOLO-ULM: Ultra-Lightweight Models for Real-Time Object Detection
• Node-RF: Learning Generalized Continuous Space-Time Scene Dynamics with Neural ODE-based NeRFs
• HumanNOVA: Photorealistic, Universal and Rapid 3D Human Avatar Modeling from a Single Image
• A2GC: Asymmetric Aggregation with Geometric Constraints for Locally Aggregated Descriptors
• Learning complete and explainable visual representations from itemized text supervision
• Foundry: Distilling 3D Foundation Models for the Edge
• UniSER: A Foundation Model for Unified Soft Effects Removal
• Condensed Test-Time Adaptation of VLMs for Action Recognition
• GraspGen-X: Cross-Embodiment 6-DOF Diffusion-based Grasping
• L^2DGS: Low-Light Dynamic Gaussian Splatting
• Grid Distillation: Compositional Image Distillation via Structured Generative Grids
• ExpPortrait: Expressive Portrait Generation via Personalized Representation
• Delta Rectified Flow Sampling for Text-to-Image Editing
• When Transformers Meet Mamba: A Hybrid Transformer-Mamba Network for Video Object Detection
• Do You See What I Am Pointing At? Gesture-Based Egocentric Video Question Answering
• PhysGS: Bayesian-Inferred Gaussian Splatting for Physical Property Estimation
• Faster-GS: Analyzing and Improving Gaussian Splatting Optimization
• Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals
• Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching
• AssemblyBench: Physics-Aware Assembly of Complex Industrial Objects
• Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness
• Best Segmentation Buddies for Image-Shape Correspondence
• FlexAvatar: Flexible Large Reconstruction Model for Animatable Gaussian Head Avatars with Detailed Deformation
• Unlocking Positive Transfer in Incrementally Learning Surgical Instruments: A Self-reflection Hierarchical Prompt Framework
• Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Video
• CSF: Black-box Fingerprinting via Compositional Semantics for Text-to-Image Models
• LightSplat: Fast and Memory-Efficient Open-Vocabulary 3D Scene Understanding in Five Seconds
• Enhancing Continual Learning of Vision-Language Models via Dynamic Prefix Weighting
• Parameter-Efficient Semantic Augmentation for Enhancing Open-Vocabulary Object Detection
• ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation
• Beyond Caption-Based Queries in Video Moment Retrieval
• An Empirical Study on How Video-LLMs Answer Video Questions
• MoD-DPO: Towards Mitigating Cross-modal Hallucinations in Omni LLMs using Modality Decoupled Preference Optimization
• Efficient Frame Selection for Long Video Understanding via Reinforcement Learning
• Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation
• Mitigating Objectness Bias and Region-to-Text Misalignment for Open-Vocabulary Panoptic Segmentation
• HUMAPS-4D: A Multimodal Dataset for HUman Motion Analysis with Physiological and Semantic informations
• From Inpainting to Layer Decomposition: Repurposing Generative Inpainting Models for Image Layer Decomposition
• SIMSPINE: A Biomechanics-Aware Simulation Framework for 3D Spine Motion Annotation and Benchmarking
• Linear Image Generation by Synthesizing Exposure Brackets
• SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAM
• CD-Buffer: Complementary Dual-Buffer Framework for Test-Time Adaptation in Adverse Weather Object Detection
• VSRELL: A Simple Baseline for Video Super-Resolution and Enhancement in Low-Light Environment
• Dual-Level Confidence based Implicit Self-Refinement for Medical Visual Question Answering
• Towards Robust Vision Transformers: Path Dependency Analysis and a Simple Two-Stage Adversarial Training
• FAPE-IR: Frequency-Aware Planning and Execution Framework for All-in-One Image Restoration
• M3DocDep: Multi-modal, Multi-page, Multi-document Dependency Chunking with Large Vision-Language Models
• VGGT-360: Geometry-Consistent Zero-Shot Panoramic Depth Estimation
• WPT: World-to-Policy Transfer via Online World Model Distillation
• Haptic Neural Fields: Bringing Tactile Interactions to 3D Rendered Scenes
• PrivSynth: Alternating and Control-Based Optimization for Privacy and Utility in Synthetic Data
• From Exploration to Exploitation: A Two-Stage Entropy RLVR Approach for Noise-Tolerant MLLM Training
• SIGMA: A Physics-Based Benchmark for Gas Chimney Understanding in Seismic Images
• LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis
• WISER: Wider Search, Deeper Thinking, and Adaptive Fusion for Training-Free Zero-Shot Composed Image Retrieval
• Exemplar-Free Class Incremental Learning via Preserving Class-Discriminative Structure
• Semantic Derivative Flow: Graph-Guided Diffusion for Controllable Instance Interactions
• Point4Cast: Streaming Dynamic Scene Reconstruction and Forecasting
• ORCA: Orchestrated Reasoning with Collaborative Agents for Document Visual Question Answering
• Reconstructing Spiking Neural Networks Using a Single Neuron with Autapses
• CoFiDA-M: Concept-Aware Feature Modulation for Cross-Domain Adaptation with Image-Only Inference
• Human Interaction-Aware 3D Reconstruction from a Single Image
• Contrastive Cross-Bag Augmentation for Multiple Instance Learning-based Whole Slide Image Classification
• WiTTA-Bench: Benchmarking Test-Time Adaptation for WiFi Sensing
• Video-Only ToM: Enhancing Theory of Mind in Multimodal Large Language Models
• Suppressing Non-Semantic Noise in Masked Image Modeling Representations
• Cell-Type Prototype-Informed Neural Network for Gene Expression Estimation from Pathology Images
• StableMaterials: Enhancing Diversity in Material Generation via Semi-Supervised Learning
• Generate, Analyze, and Refine: Training-Free Sound Source Localization via MLLM Meta-Reasoning
• AE2VID: Event-based Video Reconstruction via Aperture Modulation
• FloVerse: Floor Plan-Guided Multi-Modal Navigation
• Next-Scale Autoregressive Models for Text-to-Motion Generation
• PyramidalWan: On Making Pretrained Video Model Pyramidal for Efficient Inference
• Recurrent Video Masked Autoencoders
• HFR and HDR Video from Multi-Attenuated Spikes Using a Rapidly Rotating SpokeND Filter
• PA-Attack: Guiding Gray-Box Attacks on LVLM Vision Encoders with Prototypes and Attention
• Domain-Skewed Federated Learning with Feature Decoupling and Calibration
• Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods
• Beyond Scanpaths: Graph-Based Gaze Simulation in Dynamic Scenes
• Synthesizing Visual Concepts as Vision-Language Programs
• CG-Floor: Centroid-Guided Diffusion for Large-Scale Floorplan Generation
• WEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation
• Meta-FC: Meta-Learning with Feature Consistency for Robust and Generalizable Watermarking
• Voxify3D: Pixel Art Meets Volumetric Rendering
• OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory
• Explaining Object Detectors via Collective Contribution of Pixels
• Foundation Encoders Are All You Need for Preference-Aware Personalization
• CHIRP dataset: towards long-term, individual-level, behavioral monitoring of bird populations in the wild
• RobotSeg: A Model and Dataset for Segmenting Robots in Image and Video
• Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes
• BuildAnyPoint: 3D Building Structured Abstraction from Diverse Point Clouds
• DDSF: Robust Few-Shot Learning via Disentangled Subspaces with Determinantal Point Process
• Learning What Matters: Prioritized Concept Learning via Relative Error-driven Sample Selection
• ProFocus: Proactive Perception and Focused Reasoning in Vision-and-Language Navigation
• CUE: Concept-Aware Multi-Label Expansion to Mitigate Concept Confusion in Long-Tailed Learning
• SIMPACT: Simulation-Enabled Action Planning using Vision-Language Models
• Mitigating Simplicity Bias in OOD Detection through Object Co-occurrence Analysis
• A Supervised Multi-task Framework for Joint cryo-ET Restoration Enabled by Generative Physical Simulation
• Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation
• Same or Not? Enhancing Visual Perception in Vision-Language Models
• Revisiting F-measure Optimization in Multi-Label Classification: A Sampling-based Approach
• Towards Motion Turing Test: Evaluating Human-Likeness in Humanoid Robots
• PromptEnhancer: Taming Your Rewriter for Text-to-Image Generation via Fine-Grained Reward
• FrankenMotion: Part-level Human Motion Generation and Composition
• FE2E: From Editor to Dense Geometry Estimator
• Lighting in Motion: Spatiotemporal HDR Lighting Estimation
• Aligning Text, Images and 3D Structure Token-by-Token
• Ghost-FWL: A Large-Scale Full-Waveform LiDAR Dataset for Ghost Detection and Removal
• Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors
• Dual Graph Regularized Deep Unfolding Network for Guided Depth Map Super-resolution
• FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection
• RewardFlow: Generate Images by Optimizing What You Reward
• AeroDGS: Physically Consistent Dynamic Gaussian Splatting for Single-Sequence Aerial 4D Reconstruction
• CogDriver: Integrating Cognitive Inertia for Temporally Coherent Planning in Autonomous Driving
• Coded-E2LF: Coded Aperture Light Field Imaging from Events
• Neural-Centric Video Processing Pipeline for Unified Multi-Task Inference
• OmniGround: A Comprehensive Spatio-Temporal Grounding Benchmark for Real-World Complex Scenarios
• Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression
• StructXLIP: Enhancing Vision-language Models with Multimodal Structural Cues
• Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs
• First Logit Boosting: Visual Grounding Method to Mitigate Object Hallucination in Large Vision-Language Models
• UniTEX: Universal High Fidelity Generative Texturing for 3D Shapes
• Seeing Clearly, Reasoning Confidently: Plug-and-Play Remedies for Vision Language Model Blindness
• InstantViR: Real-Time Video Inverse Problem Solver with Distilled Diffusion Prior
• Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers
• Scaling-Aware Data Selection for End-to-End Autonomous Driving Systems
• EV-CGNet: Co-visible Focused 3D-guided 2D Event Keypoint Detection Network
• RAVEN: Radar Adaptive Vision Encoders for Efficient Chirp-wise Object Detection and Segmentation
• OptiMVMap: Offline Vectorized Map Construction via Optimal Multi-vehicle Perspectives
• Visual Personalization Turing Test
• BulletTime: Decoupled Control of Time and Camera Pose for Video Generation
• Parallelised Differentiable Straightest Geodesics for 3D Meshes
• PersonaLive! Expressive Portrait Image Animation for Live Streaming
• CLIP-like Model as a Foundational Density Ratio Estimator
• SATTC: Structure-Aware Label-Free Test-Time Calibration for Cross-Subject EEG-to-Image Retrieval
• Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views
• Inference-time Physics Alignment of Video Generative Models with Latent World Models
• JANUS: A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution Optimization
• Gated KalmaNet: A Fading Memory Layer through Test-time Ridge Regression
• DeDelayed: Deleting Remote Inference Delay via On-Device Correction
• SparVAR: Exploring Sparsity in Visual AutoRegressive Modeling for Training-Free Acceleration
• ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding
• CARD: A Multi-Modal Automotive Dataset for Dense 3D Reconstruction in Challenging Road Topography
• Prompt-Anchored Vision–Text Distillation for Lifelong Person Re-identification
• ReFAct: Empowering Multimodal Web Agents with Visual and Context Focusing
• Towards Multimodal Domain Generalization with Few Labels
• Coverage Optimization for Camera View Selection
• FluidGaussian: Propagating Simulation-Based Uncertainty Toward Functionally-Intelligent 3D Reconstruction
• NeighborMAE: Exploiting Spatial Dependencies between Neighboring Earth Observation Images in Masked Autoencoders Pretraining
• PersonaVLM: Long-Term Personalized Multimodal LLMs
• gQIR: Generative Quanta Image Reconstruction
• SMVRT: Implicit Human 3D Modeling Using Sparse Multi-View Volumetric Reconstruction with Transformer Fusion
• NIL: No-data Imitation Learning
• QueryOcc: Query-based Self-Supervision for 3D Semantic Occupancy
• Few-for-Many Personalized Federated Learning
• A More Word-like Image Tokenization for MLLMs
• Image-Guided Geometric Stylization of 3D Meshes
• Boosting Reasoning in Large Multimodal Models via Activation Replay
• Learning from Noisy Supervision: A Denoising–Debiasing Framework for Weakly Supervised Video Anomaly Detection
• HieraMamba: Video Temporal Grounding via Hierarchical Anchor-Mamba Pooling
• No Way To Steal My Face: Proactive Defense Against Identity-Preserving Personalized Generation
• Robust Spiking Neural Networks by Temporal Mutual Information
• V^2-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence
• Keep It Frozen: Domain-Routed Conditional Residual Modulation for Multi-Domain Vision Transformers
• SceMoS: Scene-Aware 3D Human Motion Synthesis by Planning with Geometry-Grounded Tokens
• Semantic Scale Space: A Framework for Controllable Image Abstraction
• ClimaOoD: Improving Anomaly Segmentation via Physically Realistic Synthetic Data
• Geometry-Aware Cross-Modal Graph Alignment for Referring Segmentation in 3D Gaussian Splatting
• QuCNet: Quantum Deep Learning Driven Multi-Circuit Network for Remote Sensing Image Classification
• Image Generation from Contextually-Contradictory Prompts
• Text-Printed Image: Bridging the Image-Text Modality Gap for Text-centric Training of Large Vision-Language Models
• Spike-driven Discrete Aggregation for Event-based Object Detection
• Seeing Through the Shift: Causality-Inspired Robust Generalized Category Discovery
• Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models
• Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization
• From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity
• VQ-VA World: Towards High-Quality Visual Question-Visual Answering
• RoMo: A Large-Scale, Richly Organized Dataset and Semantic Taxonomy for Human Motion Generation
• FMPose3D: monocular 3D pose estimation via flow matching
• Eulerian Gaussian Splatting using Hashed Probability Pyramids
• DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference
• GenBreak: Red Teaming Text-to-Image Generation Using Large Language Models
• Learning to Solve PDEs on Neural Shape Representations
• Solving Minimal Problems Without Matrix Inversion Using FFT-Based Interpolation
• MultiShotMaster: A Controllable Multi-Shot Video Generation Framework
• When Safety Collides: Resolving Multi-Category Harmful Conflicts in Text-to-Image Diffusion via Adaptive Safety Guidance
• Polyphony: Diffusion-based Dual-Hand Action Segmentation with Alternating Vision Transformer and Semantic Conditioning
• Virtual Full-stack Scanning of Brain MRI via Imputing Any Quantised Code
• Rationale-Enhanced Decoding for Multi-modal Chain-of-Thought
• Few-shot Acoustic Synthesis with Multimodal Flow Matching
• HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis
• RF4D:Neural Radar Fields for Novel View Synthesis in Outdoor Dynamic Scenes
• Sparsity as a Key: Unlocking New Insights from Latent Structures for Out-of-Distribution Detection
• Designing to Forget: Deep Semi-parametric Models for Unlearning
• UniPixie: Unified and Probabilistic 3D Physics Learning via Flow Matching
• Evolutionary Multimodal Reasoning via Hierarchical Semantic Representation for Intent Recognition
• AnchorSplat: Feed-Forward 3D Gaussian Splatting With 3D Geometric Priors
• AdaRadar: Rate Adaptive Spectral Compression for Radar-based Perception
• Push-and-Step: From RL-Based Balance Recovery to Physical Simulation of Dense Crowds
• Negative Binomial Variational Autoencoders for Overdispersed Latent Modeling
• Differentially Private 2D Human Pose Estimation
• Cross-Domain Demo-to-Code via Neurosymbolic Counterfactual Reasoning
• OpenMMReasoner: Pushing the Frontiers in Multimodal Reasoning with an Open and General Recipe
• 2-Shots in the Dark: Low-Light Denoising with Minimal Data Acquisition
• Fine-Grained Multi Image Object Hallucination Benchmark
• Adaptive Confidence Regularization for Multimodal Failure Detection
• A Multi-Agent Perception-Action Alliance for Efficient Long Video Reasoning
• KAMP: Knowledge-Anchored Multimodal Pretraining Framework for Medical Image Representation
• A Sanity Check for Multi-In-Domain Face Forgery Detection in the Real World
• AffordGrasp: Cross-Modal Diffusion for Affordance-Aware Grasp Synthesis
• VEMamba: Efficient Isotropic Reconstruction of Volume Electron Microscopy with Axial-Lateral Consistent Mamba
• EmoDiffTalk: Emotion-aware Diffusion for Editable 3D Gaussian Talking Head
• Endless World: Real-Time 3D-Aware Long Video Generation
• Volumetric Functional Maps
• TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos
• Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement
• LoST: Level of Semantics Tokenization for 3D Shapes
• TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens
• Turbo-GS: Accelerating 3D Gaussian Fitting for High-Resolution Radiance Fields
• Gaussian Mapping for Evolving Scenes
• Copy-Transform-Paste: Zero-Shot Object-Object Alignment Guided by Vision-Language and Geometric Constraints
• GaussFusion: Improving 3D Reconstruction in the Wild with A Geometry-Informed Video Generator
• MDCS-MoAME: Multi-directional Composite Scanning with Mixture of Attention and Mamba Experts for Cancer Survival Prediction
• MV-TAP: Tracking Any Point in Multi-View Videos
• InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphs
• Balanced Hierarchical Contrastive Learning with Decoupled Queries for Fine-grained Object Detection in Remote Sensing Images
• CCF: Complementary Collaborative Fusion for Domain Generalized Multi-Modal 3D Object Detection
• ChordEdit: One-Step Low-Energy Transport for Image Editing
• InvAD: Inversion-based Reconstruction-Free Anomaly Detection with Diffusion Models
• SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models
• GaussianVision: Vision-Language Alignment from Compressed Image Representations using 2D Gaussian Splatting
• PPM-CLIP: Probabilistic Prompt Modeling for Generalizable AI-Generated Image Detection
• Boosting Quantitive and Spatial Awareness for Zero-Shot Object Counting
• Lafite: A Generative Latent Field for 3D Native Texturing
• Point Cloud as a Foreign Language for Multi-modal Large Language Model
• Action Motifs: Self-Supervised Hierarchical Representation of Human Body Movements
• Training-free Mixed-Resolution Latent Upsampling for Spatially Accelerated Diffusion Transformers
• Training-Only Heterogeneous Image-Patch-Text Graph Supervision for Advancing Few-Shot Learning Adapters
• Learning to Identify Out-of-Distribution Objects for 3D LiDAR Anomaly Segmentation
• EgoPoseFormer v2: Accurate Egocentric Human Motion Estimation for AR/VR
• GaussianPile: A Unified Sparse Gaussian Splatting Framework for Slice-based Volumetric Reconstruction
• LAMP: Localization Aware Multi-camera People Tracking in Metric 3D World
• Distilling Balanced Knowledge from a Biased Teacher
• Reinforcement-Guided Synthetic Data Generation for Privacy-Sensitive Identity Recognition
• TextFM: Robust Semi-dense Feature Matching with Language Guidance
• Obstruction Reasoning for Robotic Grasping
• Gradient Knows Best: Mixed-Precision Quantization via Gradient-Guided Bit Allocation for Super-Resolution
• Improving Adversarial Transferability with Local Perturbation Augmentation
• VOSR: A Vision-Only Generative Model for Image Super-Resolution
• MAD: Motion Appearance Decoupling for efficient Driving World Models
• MeshMosaic: Scaling Artist Mesh Generation via Local-to-Global Assembly
• From Spots to Pixels: Dense Spatial Gene Expression Prediction from Histology Images
• Hermite Radial Basis Function for Surface Reconstruction via Differentiable Rendering
• TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models
• TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detection
• SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching
• Open-world Hand-Object Interaction Video Generation Based on Structure and Contact-aware Representation
• POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs
• Unleashing the Power of Chain-of-Prediction for Monocular 3D Object Detection
• Generative Video Motion Editing with 3D Point Tracks
• CRIT: Graph-Based Automatic Data Synthesis to Enhance Cross-Modal Multi-Hop Reasoning
• RoboAgent: Chaining Basic Capabilities for Embodied Task Planning
• Less is More: Data-Efficient Adaptation for Controllable Text-to-Video Generation
• 3D Gaussian Splatting at Arbitrary Resolutions with Compact Proxy Anchors
• PAVAS: Physics-Aware Video-to-Audio Synthesis
• A Stitch in Time: Learning Procedural Workflow via Self-Supervised Plackett–Luce Ranking
• Part-aware Modeling of Articulated Objects using 3D Gaussian Splatting
• AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend
• FPSBench: A Benchmark for Video Understanding at High Frame Rates
• PMRNet: Physics-informed Multi-scale Refinement Network for Medical Image Segmentation
• Attribute-Preserving Pseudo-Labeling for Diffusion-Based Face Swapping
• DarkShake-DVS: Event-based Human Action Recognition under Low-light and Shaking Camera Conditions
• HyperGait: Unleashing the Power of Parsing for Gait Recognition in the Wild via Hypergraph
• Orthogonal Spatial-Aware Multi-View Anchor Graph Clustering for Incomplete Remote Sensing Data
• V-DPM: 4D Video Reconstruction with Dynamic Point Maps
• 3D-LATTE: Latent Space 3D Editing from Textual Instructions
• EnergyAction: Unimanual to Bimanual Composition with Energy-Based Models
• Similarity-as-Evidence: Calibrating Overconfident VLMs for Interpretable and Label-Efficient Medical Active Learning
• Rethinking Model Selection in VLM Through the Lens of Gromov-Wasserstein Distance
• Composing Concepts from Images and Videos via Concept-prompt Binding
• DMAligner: Enhancing Image Alignment via Diffusion Model Based View Synthesis
• MMCP-GEN: A Modality-Extensible Diffusion Language Model for Conditional Protein Sequence Generation
• Scalable Object Relation Encoding for Better 3D Spatial Reasoning in Large Language Models
• Self-Corrected Image Generation with Explainable Latent Rewards
• Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selection
• URScenes: A Multi-scenario Dataset for Unstructured Road Environments
• When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness
• Modeling the Visual Ambiguity of Human Sketches
• PoseD-Flow: Versatile and Guided Flow Matching Model of Human Pose
• Registration-Free Learnable Multi-View Capture of Faces in Dense Semantic Correspondence
• SynthRGB-T: Language-Vision Guided Image Translation for Diversity Synthesis
• IBISAgent: Reinforcing Pixel-Level Visual Reasoning in MLLMs for Universal Biomedical Object Referring and Segmentation
• Precise Object and Effect Removal with Adaptive Target-Aware Attention
• AlignPose: Generalizable 6D Pose Estimation via Multi-view Feature-metric Alignment
• AdaBet: Gradient-free Layer Selection for Efficient Training of Deep Neural Networks
• Block-based Learned Image Compression without Blocking Artifacts
• MixerCSeg: An Efficient Mixer Architecture for Crack Segmentation via Decoupled Mamba Attention
• Tunable Soft Equivariance with Guarantees
• Expanding mmWave Datasets for Human Pose Estimation with Unlabeled Data and LiDAR Datasets
• REALM: An MLLM-Agent Framework for Open World 3D Reasoning Segmentation and Editing on Gaussian Splatting
• MMTIT-Bench: A Multilingual and Multi-Scenario Benchmark with Cognition–Perception–Reasoning Guided Text-Image Machine Translation
• SPE-MVS: Spatial Position Encoding Enhanced Multi-View Stereo with Monocular Depth Priors
• Factorize, Reconstruct, Enhance: A Unified Framework for Multimodal Sentiment Analysis
• PhenoYieldNet: Learning Crop-Aware Phenological Responses for Multi-Crop Yield Prediction
• Geo2: Geometry-Guided Cross-view Geo-Localization and Image Synthesis
• HBridge: H-Shape Bridging of Heterogeneous Experts for Unified Multimodal Understanding and Generation
• LiDAR-to-4DRadar Diffusion Bridge via Cross-Modal Alignment and Translation in Latent Space
• S^2FT: Parameter-Efficient Fine-Tuning in Sparse Spectrum Domain
• UniM: A Unified Any-to-Any Interleaved Multimodal Benchmark
• VENI: Variational Encoder for Natural Illumination
• RMAE-ProGRess: Advancing Semantic Segmentation in Unstructured Environments
• VisiLock: Authorizing Instruction-based Image editing with Dual Score Distillation
• SIF: Semantically In-Distribution Fingerprints for Large Vision-Language Models
• Streaming Video Crime Anticipation with Spatio-Temporal Causal Reasoning
• Charge: A Comprehensive Novel View Synthesis Benchmark and Dataset to Bind Them All
• UIKA: Fast Universal Head Avatar from Pose-Free Images
• Echoes of Ownership: Adversarial-Guided Dual Injection for Copyright Protection in MLLMs
• Temporal Equilibrium MeanFlow: Bridging the Scale Gap for One-Step Generation
• Scene Reconstruction as Mapping Priors for 3D Detection
• SPARROW: Learning Spatial Precision and Temporal Referential Consistency in Pixel-Grounded Video MLLMs
• Restore, Assess, Repeat: A Unified Framework for Iterative Image Restoration
• TokenLight: Precise Lighting Control in Images using Attribute Tokens
• EffectMaker: Unifying Reasoning and Generation for Customized Visual Effect Creation
• History to Future: Evolving Agent with Experience and Thought for Zero-shot Vision-and-Language Navigation
• MetricHMSR: Metric Human Mesh and Scene Recovery from Monocular Images
• Beyond Myopic Alignment: Lookahead Optimization for Online Class-Incremental Learning
• Weight Space Representation Learning via Neural Field Adaptation
• Towards Balanced Multi-Modal Learning in 3D Human Pose Estimation
• DSFlash: Comprehensive Panoptic Scene Graph Generation in Realtime
• ProgTrack: A Multi-Object Tracking Algorithm with Progressive Matching Strategy
• Low-Resolution Editing is All You Need for High-Resolution Editing
• Draft and Refine with Visual Experts
• Edit-As-Act: Goal-Regressive Planning for Open-Vocabulary 3D Indoor Scene Editing
• Content-Adaptive Hierarchical Hyperprior for Neural Video Coding
• Zero-Shot Reconstruction of Animatable 3D Avatars with Cloth Dynamics from a Single Image
• Decompose and Transfer: CoT-Prompting Enhanced Alignment for Open-Vocabulary Temporal Action Detection
• Mario: Multimodal Graph Reasoning with Large Language Models
• Fine-Tuning Impairs the Balancedness of Foundation Models in Long-tailed Personalized Federated Learning
• Hyperbolic Defect Feature Synthesis for Few-Shot Defect Classification
• CanonCGT: Reference-Based Color Grading via Canonical Pivot Representation
• Energy Waveify and Redistribution for Test-Time Adaptation: A Control System Perspective
• Toward Real-world Infrared Image Super-Resolution: A Unified Autoregressive Framework and Benchmark Dataset
• Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining
• ReMoGen: Real-time Human Interaction-to-Reaction Generation via Modular Learning from Diverse Data
• Critical Patch-Aware Sparse Prompting with Decoupled Training for Continual Learning on the Edge
• Widget2Code: From Visual Widgets to UI Code via Multimodal LLMs
• Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing
• SMRABooth: Subject and Motion Representation Alignment for Customized Video Generation
• TAPE: Task-Adaptive Prototype Evolution in Audio-Language Models for Fully Few-shot Class-incremental Audio Classification
• Representation-Steered Incremental Adapter-Tuning for Class-Incremental Learning with Pre-Trained Models
• Generative Adversarial Perturbations with Cross-paradigm Transferability on Localized Crowd Counting
• PAS: Prelim Attention Score for Detecting Object Hallucinations in Large Vision-Language Models
• Grounded Latents for Entity-Centric 4D Scene Generation
• InternVideo-Next: Towards World-Understanding Video Models
• MicroFM: Physics-guided Flow Matching for Isotropic Microscopy Reconstruction
• How Far Can We Go With Synthetic Data for Audio-Visual Sound Source Localization?
• MoCoDiff: A Controllable Autoregressive Diffusion Model for Expressive Motion Generation
• CryoKRAQEN: Kernel-Regularized Annealing for Quantized Embedding Networks in Cryo-EM Heterogeneous Reconstruction
• IAG: Input-aware Backdoor Attack on VLM-based Visual Grounding
• TWINGS: Thin Plate Splines Warp-aligned Initialization for Sparse-View Gaussian Splatting
• Spatial-SAM: Spatially Consistent 3D Electron Microscopy Segmentation with SDF Memory and Semi-Supervised Learning
• FUN REC Reconstructing Functional 3D Scenes from Egocentric Interaction Videos
• SVAgent: Storyline-guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration
• AGFT: Alignment-Guided Fine-Tuning for Zero-Shot Adversarial Robustness of Vision-Language Models
• CGHair: Compact Gaussian Hair Reconstruction with Card Clustering
• Selectively Extracting and Injecting Visual Attributes into Text-to-Image Models
• SG-LoRA: Semantic-guided LoRA Parameters Generation
• HCL-FF: Hierarchical and Contrastive Learning for Forward-Forward Algorithm
• Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training
• Spectral Super-Resolution via Adversarial Unfolding and Data-Driven Spectrum Regularization: From Multispectral Satellite Data to NASA Hyperspectral Image
• Illustrator’s Depth: Monocular Layer Index Prediction for Image Decomposition
• PAF: Perturbation-Aware Filtering for Open-Set Semi-Supervised Learning
• HTTM: Head-wise Temporal Token Merging for Faster VGGT
• TopoMesh: High-Fidelity Mesh Autoencoding via Topological Unification
• Self-Diffusion Driven Blind Imaging
• TRANSPORTER: Transferring Visual Semantics from VLM Manifolds
• SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modeling
• StoryTailor:A Zero-Shot Pipeline for Action-Rich Multi-Subject Visual Narratives
• Parse, Search, and Confirmation: Training-Free Aerial Vision-and-Dialog Navigation with Chain-of-Thought Reasoning and Structured Spatial Memory
• Wave-Former: Through-Occlusion 3D Reconstruction via Wireless Shape Completion
• FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation
• AcTTA: Rethinking Test-Time Adaptation via Dynamic Activation
• VarSplat: Uncertainty-aware 3D Gaussian Splatting for Robust RGB-D SLAM
• ReasonEdit: Towards Reasoning-Enhanced Image Editing Models
• Stitch-a-Demo: Creating Video Demonstrations from Multistep Descriptions
• VecGlypher: Unified Vector Glyph Generation with Language Models
• Defending Unauthorized Model Merging via Dual-Stage Weight Protection
• SVHalluc: Benchmarking Speech–Vision Hallucination in Audio-Visual Large Language Models
• TRIDENT: A Trimodal Cascade Generative Framework for Drug and RNA-Conditioned Cellular Morphology Synthesis
• SPAR: Single-Pass Any-Resolution ViT for Open-vocabulary Segmentation
• A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helps
• Soft Modality-Guided Expert Specialization in MoE-VLMs
• AdaDexTrack: Dynamic Modulation for Adaptive and Generalizable Dexterous Manipulation Tracking
• SoccerMaster: A Vision Foundation Model for Soccer Understanding
• SafeDrive: Fine-Grained Safety Reasoning for End-to-End Driving in a Sparse World
• Perceptual 3D Simulation With Physical World Modeling
• Cleaning the Pool: Progressive Filtering of Unlabeled Pools in Deep Active Learning
• Random Wins All: Rethinking Grouping Strategies for Vision Tokens
• Learning to Adapt: Self-Improving Web Agent via Cognitive-Aware Exploration
• MuM: Multi-View Masked Image Modeling for 3D Vision
• WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning
• Unsupervised Multi-Scale Segmentation of 3D Subcellular World with Stable Diffusion Foundation Model
• 3D Gaussian Splatting with Self-Constrained Priors for High Fidelity Surface Reconstruction
• Portable Active Learning for Object Detection
• Generalized and Personalized Federated Learning with Black-Box Foundation Models via Orthogonal Transformations
• Depth Peeling for High-Fidelity Gaussian-Enhanced Surfel Rendering
• CCCaption: Dual-Reward Reinforcement Learning for Complete and Correct Image Captioning
• LLaDA-MedV: Exploring Large Language Diffusion Models for Biomedical Image Understanding
• SwiftTailor: Efficient 3D Garment Generation with Geometry Image Representation
• Perceiving the Near, Reasoning the Distant: Coherent Long-Horizon Trajectory Prediction for Autonomous Driving
• TGT: Text-Grounded Trajectories for Locally Controlled Video Generation
• Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward
• ConceptPose: Training-Free Zero-Shot Object Pose Estimation using Concept Vectors
• Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models
• Focus-to-Perceive Representation Learning: A Cognition-Inspired Hierarchical Framework for Endoscopic Video Analysis
• EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding
• Skullptor: High Fidelity 3D Head Reconstruction in Seconds with Multi-View Normal Prediction
• Revisiting Pose Sensitivity in Splat-based Computed Tomography under Sparse-view Reconstruction
• DASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examples
• Relightful Video Portrait Harmonization
• Generalizable Knowledge Distillation from Vision Foundation Models for Semantic Segmentation
• ProcessMaker: A Generalized Process Visualization Framework with Adaptive Sequence Steps on Diffusion Transformers
• Hierarchical Point-Patch Fusion with Adaptive Patch Codebook for 3D Shape Anomaly Detection
• Prototypical Action Reasoning Facilitated by Vision-Language Alignment for Egocentric Action Anticipation
• DARC: Dual Adjustment Reasoning with Counterfactuals for Trustworthy Chest X-ray Classification
• Towards Robust Multimodal Large Language Models Against Jailbreak Attacks
• Intrinsic Image Fusion for Multi-View 3D Material Reconstruction
• Learning 3D Shape Fidelity Metric from Real-world Distortions
• Aligning What Vision-Language Models See and Perceive with Adaptive Information Flow
• Efficient Hybrid SE(3)-Equivariant Visuomotor Flow Policy via Spherical Harmonics for Robot Manipulation
• 3D-IDE: 3D Implicit Depth Emergent
• IGen: Scalable Data Generation for Robot Learning from Open-World Images
• Stake the Points: Structure-Faithful Instance Unlearning
• Towards GUI Agents: Vision-Language Diffusion Models for GUI Grounding
• DriveVLN: Towards Mapless Vision-and-Language Navigation in Autonomous Driving
• HoneyBee: Data Recipes for Vision-Language Reasoners
• VGGT-Ω
• LoFA: Learning to Predict Personalized Prior for Fast Adaptation of Visual Generative Models
• Fed-ADE: Adaptive Learning Rate for Federated Post-adaptation under Distribution Shift
• V-RGBX: Video Editing with Accurate Controls over Intrinsic Properties
• Hidden Monotonicity: Explaining Deep Neural Networks via their DC Decomposition
• RefAV: Towards Planning-Centric Scenario Mining
• Test-Time Training for LiDAR Semantic Segmentation under Corruption via Geometric Inlier Discrimination
• MaskDiME: Adaptive Masked Diffusion for Precise and Efficient Visual Counterfactual Explanations
• Granulon: Awakening Pixel-Level Visual Encoders with Adaptive Multi-Granularity Semantics for MLLM
• FluoCLIP: Stain-Aware Focus Quality Assessment in Fluorescence Microscopy
• FAST: Topology-Aware Frequency-Domain Distribution Matching for Coreset Selection
• ELVIS: Enhance Low-Light for Video Instance Segmentation in the Dark
• PE3R: Perception-Efficient 3D Reconstruction
• LeapAlign: Post-training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories
• Improving Calibration in Test-Time Prompt Tuning for Vision-Language Models via Data-Free Flatness-Aware Prompt Pretraining
• Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Images
• Multi-speaker Attention Alignment for Multimodal Social Interaction
• PackUV: Packed Gaussian UV Maps for 4D Volumetric Video
• MEMO: Human-like Crisp Edge Detection Using Masked Edge Prediction
• Continuous Exposure-Time Modeling for Realistic Atmospheric Turbulence Synthesis
• GIFSplat: Generative Prior-Guided Iterative Feed-Forward 3D Gaussian Splatting from Sparse Views
• ShadowDraw: From Any Object to Shadow-Drawing Compositional Art
• Geometric-Photometric Event-based 3D Gaussian Ray Tracing
• FRAMER: Frequency-Aligned Self-Distillation with Adaptive Modulation Leveraging Diffusion Priors for Real-World Image Super-Resolution
• Rethinking Pose Refinement in 3D Gaussian Splatting under Pose Prior and Geometric Uncertainty
• Quant Experts: Token-aware Adaptive Error Reconstruction with Mixture of Experts for Large Vision-Language Models Quantization
• Cycle-Consistent Tuning for Layered Image Decomposition
• INSID3: Training-Free In-Context Segmentation with DINOv3
• MorphSeek: Fine-grained Latent Representation-Level Policy Optimization for Deformable Image Registration
• Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance
• GraPHFormer: A Multimodal Graph Persistent Homology Transformer for the Analysis of Neuroscience Morphologies
• MatSpray: Fusing 2D Material World Knowledge on 3D Geometry
• Dual Ascent Diffusion for Inverse Problems
• DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation
• TriSim: Tri-Dimensional Similarity Modeling with Extreme Value Theory for False-Negative Mitigation in Remote Sensing Image-Text Retrieval
• The Geometry of Robustness: Optimizing Loss Landscape Curvature and Feature Manifold Alignment for Robust Finetuning of Vision-Language Models
• Beyond Geometry: Artistic Disparity Synthesis for Immersive 2D-to-3D
• PAD-Hand: Physics-Aware Diffusion for Hand Motion Recovery
• PaQ-DETR: Learning Pattern and Quality-Aware Dynamic Queries for Object Detection
• PointThinker: Point-Incentivized Parallel Thinking for Multimodal Large Language Model
• Particulate: Feed-Forward 3D Object Articulation
• Learning to See through Illumination Extremes with Event Streaming in Multimodal Large Language Models
• Unified Number-Free Text-to-Motion Generation Via Flow Matching
• PQDT: Pseudo-Query Dual Transformer for Robust Point Cloud Restoration
• Zoo3D: Zero-Shot 3D Object Detection at Scene Level
• Diagram2Structure: Unlocking LLMs' Diagram Comprehension through DiagramDiff, an Offline Diagram Structuring Framework
• Generalizing Visual Geometry Priors to Sparse Gaussian Occupancy Prediction
• Dynamic Visual SLAM using a General 3D Prior
• DuoGen: Towards Autonomous Interleaved Multimodal Generation
• Exemplar-Free Continual Learning for State Space Models
• B^3-Seg: Camera-Free, Training-Free 3DGS Segmentation via Analytic EIG and Beta-Bernoulli Bayesian Updates
• Pixel Motion Diffusion is What We Need for Robot Control
• Breaking the Scalability Limit of Multi-Projector Calibration with Embedded Cameras
• Unsupervised Multi-agent and Single-agent Perception from Cooperative Views
• Reconstruction-Guided Slot Curriculum: Addressing Object Over-Fragmentation in Video Object-Centric Learning
• GIFT: Global Irreplaceability Frame Targeting for Efficient Video Understanding
• FEAST: Fully Connected Expressive Attention for Spatial Transcriptomics
• Frame2Freq: Spectral Adapters for Fine-Grained Video Understanding
• Hierarchical Process Reward Models are Symbolic Vision Learners
• NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering
• PIX-TAB: Efficient PIXel-Precise TABle Structure Recognition Approach with Speculative Decoding and Region-Based Image Segmentation
• Modeling Cross-vision Synergy for Unified Large Vision Model
• High-Fidelity Diffusion Face Swapping with ID-Constrained Facial Conditioning
• Fully Decentralized Certified Unlearning
• Gallant: Voxel Grid-based Humanoid Locomotion and Local-navigation across 3-D Constrained Terrains
• ReLaGS: Relational Language Gaussian Splatting
• FSFSplatter: Geometrically Accurate Reconstruction with Free Sparse-view Images within 2 minutes
• Looking Beyond the Window: Global-Local Aligned CLIP for Training-free Open-Vocabulary Semantic Segmentation
• AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models
• M3Grounder: Mask-Based Multi-Span and Multi-Granular Grounding for Document QA
• MDS-VQA: Model-Informed Data Selection for Video Quality Assessment
• GenHOI: Towards Object-Consistent Hand–Object Interaction with Temporally Balanced and Spatially Selective Object Injection
• Harmonized Feature Conditioning and Frequency-Prompt Personalization for Multi-Rater Medical Segmentation
• Efficient Encoder-Free Fourier-based 3D Large Multimodal Model
• Prototype-as-Prompt: Multimodal Sentiment Prototypes Endowing Large Language Models the Capability to Perform Multimodal Sentiment Analysis
• TimeRipples: Accelerating vDiTs by Understanding the Spatio-Temporal Correlations in Latent Space
• UniDAC: Universal Metric Depth Estimation for Any Camera
• FFP-300K: Scaling First-Frame Propagation for Generalizable Video Editing
• Probabilistic Precipitation Nowcasting with Rectified Flow Transformers
• Text-guided Feature Disentanglement for Cross-modal Gait Recognition
• Realiz3D: 3D Generation Made Photorealistic via Domain-Aware Learning
• One-to-More: High-Fidelity Training-Free Anomaly Generation with Attention Control
• MUFASA: A Multi-Layer Framework for Slot Attention
• Seeing through Light and Darkness: Sensor-Physics Grounded Deblurring HDR NeRF from Single-Exposure Images and Events
• From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detection
• Linking Perception, Confidence and Accuracy in MLLMs
• OrienPose: Orientation-Guided Novel View Synthesis for Single-Image Unseen Object Pose Estimation
• AdaSVD: Singular Value Decomposition with Adaptive Mechanisms for Large Multimodal Models
• WorldGen: From Text to Traversable and Interactive 3D Worlds
• EcoSplat: Efficiency-controllable Feed-forward 3D Gaussian Splatting from Multi-view Images
• Verifying Neural Network Robustness with Dual Perturbations
• Synthetic Curriculum Reinforces Compositional Text-to-Image Generation
• RelightAnyone: A Generalized Relightable 3D Gaussian Head Model
• ShelfOcc: Native 3D Supervision beyond LiDAR for Vision-Based Occupancy Estimation
• GeoSANE: Learning Geospatial Representations from Models, Not Data
• PhyOceanCast: Global Ocean Forecasting with Physics-Informed Diffusion
• SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object Detection
• VGGT-Segmentor: Geometry-Enhanced Cross-View Segmentation
• Retrieving Counterfactuals Improves Visual In-Context Learning
• Sparse–View Localization via Online Neural 3D Regression
• Evidential Deep Partial Label Learning to Quantify Disambiguation Uncertainty
• RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image Alignment
• HAMMER: Harnessing MLLMs via Cross-Modal Integration for Intention-Driven 3D Affordance Grounding
• ORIC: Benchmarking Object Recognition under Contextual Incongruity in Large Vision-Language Models
• ODGS-SLAM: Omnidirectional Gaussian Splatting SLAM
• Do VLMs Perceive or Recall? Probing Visual Perception vs. Memory with Classic Visual Illusions
• H2-Surv: Hierarchical Hyperbolic Multimodal Representation Learning for Survival Prediction
• ViRC: Enhancing Visual Interleaved Mathematical CoT with Reason Chunking
• RAW-Domain Degradation Models for Realistic Smartphone Super-Resolution
• UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking
• DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution
• Temporal Inversion for Learning Interval Change in Chest X-Rays
• PRISM: Video Dataset Condensation with Progressive Refinement and Insertion for Sparse Motion
• Solvability of the Viewing Graph Under the Affine Camera Model
• GazeShift: Unsupervised Gaze Estimation and Dataset for VR
• InterPrior: Scaling Generative Control for Physics-Based Human-Object Interactions
• Enhancing Spatial Understanding in Image Generation via Reward Modeling
• Thinking in 360°: Humanoid Visual Search in the Wild
• Detecting Unknown Objects via Energy-based Separation for Open World Object Detection
• OccuFly: A 3D Vision Benchmark for Semantic Scene Completion from the Aerial Perspective
• Phantom: Physical Object Interactions as Dynamic Triggers for NMS-Exploited Backdoors
• ReFTA: Breaking the Weight Reconstruction Bottleneck in Tensorized Parameter-Efficient Fine-Tuning
• CI-VID: A Coherent Interleaved Text-Video Dataset
• VidTAG: Temporally Aligned Video to GPS Geolocalization with Denoising Sequence Prediction at a Global Scale
• Streamlined Knowledge Distillation
• UniVBench: Towards Unified Evaluation for Video Foundation Models
• Cut to the Chase: Training-free Multimodal Summarization via Chain-of-Events
• SARL-STG: A Spatially Aware Reinforcement Learning Framework for Refining MLLMs in Spatio-Temporal Video Grounding
• CaptionQA: Is Your Caption as Useful as the Image Itself?
• SABER: Spatially Consistent 3D Universal Adversarial Objects for BEV Detectors
• DreamStereo: Towards Real-Time Stereo Inpainting for HD Videos
• Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation
• RoadSceneBench: A Lightweight Benchmark for Mid-Level Road Scene Understanding
• PowerCLIP: Powerset Alignment for Contrastive Pre-Training
• DC-Merge: Improving Model Merging with Directional Consistency
• Mistake Attribution: Fine-Grained Mistake Understanding in Egocentric Videos
• Ground Reaction Inertial Poser: Physics-based Human Motion Capture from Sparse IMUs and Insole Pressure Sensors
• TIGER: A Unified Framework for Time, Images and Geo-location Retrieval
• Clay-to-Stone: Phase-wise 3D Gaussian Splatting for Monocular Articulated Hand-Object Manipulation Modeling
• DynBridge: Bridging Imagination and Control through Interaction Dynamics for Robot Manipulation
• Generalizable Video Quality Assessment via Weak-to-Strong Learning
• PR-MaGIC: Prompt Refinement Via Mask Decoder Gradient Flow For In-Context Segmentation
• EchoPOSE: 6D Pose Estimation of Sparse Echocardiograms for Left-Ventricular 3D Shape Reconstruction
• Resolving the Stability-Plasticity Dilemma in Reinforcement Learning via Complementary Continual Critics
• A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens
• AntiStyler: Defending Object Detection Models Against Adversarial Patch Attacks Using Style Removal
• MooCap: A Multi-View Benchmark for Cow-Object-Human Interaction and Behavior Dynamics
• Linear Fundamental Matrix Estimation from 7 or 5 Points
• CREward: A Type-Specific Creativity Reward Model
• WHU-MARS: A Multispectral Aerial-Ground Benchmark Towards Any-Scenario Person Re-Identification
• TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering
• Select Less, Reason More: Prioritizing Evidence Purity for Video Reasoning
• Dynamic Token Reweighting for Robust Vision-Language Models
• BUSSARD: Normalizing Flows for Bijective Universal Scene-Specific Anomalous Relationship Detection
• SpeeDe3DGS: Speedy Deformable 3D Gaussian Splatting with Temporal Pruning and Motion Grouping
• Adaptive Bayesian Early-Exit Networks for Efficient Non-Transferable Learning
• EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents
• InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexity
• Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers
• PECCVAI: Overcoming the Brittleness of AI Image Watermarking Under Visual Paraphrasing Attacks
• ParTY: Part-Guidance for Expressive Text-to-Motion Synthesis
• NEAF: Natural Image Editing with Attention Fusion for Generalizable Test-time Optimization in Text-Guided Image Editing
• Real2Edit2Real: Generating Robotic Demonstrations via a 3D Control Interface
• HyperGaussians: High-Dimensional Gaussian Splatting for High-Fidelity Animatable Face Avatars
• MARCO: Navigating the Unseen Space of Semantic Correspondence
• MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphing
• NitroGen: An Open Foundation Model for Generalist Gaming Agents
• Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification
• R^2-Seg: Training-Free OOD Medical Tumor Segmentation via Anatomical Reasoning and Statistical Rejection
• MAGICIAN: Efficient Long-Term Planning with Imagined Gaussians for Active Mapping
• Spherical Voronoi: Directional Appearance as a Differentiable Partition of the Sphere
• RAMEN: Resolution-Adjustable Multimodal Encoder for Earth Observation
• Stronger Normalization-Free Transformers
• Monocular Open Vocabulary Occupancy Prediction for Indoor Scenes
• Beyond Layer-Wise Merging: Chain-of-Merging for Vision-Language Models
• FisherPoser: Human Motion Estimation from Sparse Observations with Hierarchical Region-Wise Fisher-Matrix Uncertainty Modeling
• ShapeR: Robust Conditional 3D Shape Generation from Casual Captures
• FastGaMer: Efficient GainMap Learning for Practical Inverse Tone Mapping
• Featurising Pixels from Dynamic 3D Scenes with Linear In-Context Learners
• Circuit Mechanisms for Spatial Relation Generation in Diffusion Transformers
• Nestwork: Conditional 3D Furnished House Layout Generation through Latent Heterogeneous Graph Diffusion
• BiFM: Bidirectional Flow Matching for Few-Step Image Editing and Generation
• Mixture of Prototypes for Test-time Adaptive Segmentation
• Seele: A Unified Acceleration Framework for Real-Time Gaussian Splatting on Mobile Devices
• MoVie: Broaden Your Views with Human Motion for Action Detection
• Learning Scene Coordinate Reconstruction from Unposed Images via Pose Graph Optimization
• When Anonymity Breaks: Identifying Models Behind Text-to-Image Leaderboards
• FunFact: Building Probabilistic Functional 3D Scene Graphs via Factor-Graph Reasoning
• OctoMed: Data Recipes for State-of-the-Art Multimodal Medical Reasoning
• VIMCAN: Visual-Inertial 3D Human Pose Estimation with Hybrid Mamba-Cross-Attention Network
• TSTM: Temporal Segmentation for Task-relevant Mask in Visual Reinforcement Learning Generalization
• Text-Driven 3D Hand Motion Generation from Sign Language Data
• See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles
• Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention Transformers
• Phrase-grounded APO for Improving Chest X-ray Report Generation
• FEAT: Fashion Editing and Try-On from Any Design
• LaRP: Efficient Multi-View Inpainting with Latent Reprojection Priors
• GaussianFluent: Gaussian Simulation for Dynamic Scenes with Mixed Materials
• Deep Feature Deformation Weights
• Multimodal Distribution Matching for Vision-Language Dataset Distillation
• Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models
• Scaling Spatial and Temporal Context for Robotic Imitation Learning Policies With Scene Graphs
• VideoARM: Agentic Reasoning over Hierarchical Memory for Long-Form Video Understanding
• HorizonForge: Driving Scene Editing with Any Trajectories and Any Vehicles
• Unifying Precise Keyframes and Semantic Control via Multi-level Diffusion
• Boosting Vision-Language-Action Finetuning with Feasible Action Neighborhood Prior
• DPAR: Dynamic Patchification for Efficient Autoregressive Visual Generation
• Enhancing Part-Level Point Grounding for Any Open-Source MLLMs
• PC-Talk: Precise Facial Animation Control for Audio-Driven Talking Face Generation
• REL-SF4PASS: Panoramic Semantic Segmentation with REL Depth Representation and Spherical Fusion
• DiffBMP: Differentiable Rendering with Bitmap Primitives
• GHPT: Real-Time Relightable Gaussian Splatting using Hybrid Path Tracing
• Coupling Liquid Time‑Constant Encoders with Modern Hopfield Memory
• Reparameterized Tensor Ring Functional Decomposition for Multi-Dimensional Data Recovery
• PAI-Bench: A Comprehensive Benchmark For Physical AI
• When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models
• Muses: Designing, Composing, Generating Nonexistent Fantasy 3D Creatures without Training
• Generative Diffusion Priors for 3D Mapping of the Dark Universe
• Splat-Based Metal Artifact Reduction in Cone-Beam CT via Compact Attenuation Modeling
• Seeing What Matters: Visual Preference Policy Optimization for Visual Generation
• Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction
• Unlocking Strong Supervision: A Data-Centric Study of General-Purpose Audio Pre-Training Methods
• REVIVE 3D: Refinement via Encoded Voluminous Inflated prior for Volume Enhancement
• Shape-of-You: Fused Gromov-Wasserstein Optimal Transport for Semantic Correspondence in-the-Wild
• YieldSAT: A Multimodal Benchmark Dataset for High-Resolution Crop Yield Prediction
• Differentiable Stroke Planning with Dual Parameterization for Efficient and High-Fidelity Painting Creation
• GraspLDP: Towards Generalizable Grasping Policy via Latent Diffusion
• RNN as Linear Transformer: A Closer Investigation into Representational Potentials of Visual Mamba Models
• Hypergraph-State Collaborative Reasoning for Multi-Object Tracking
• AirSim360: A Panoramic Simulation Platform within Drone View
• EagleNet: Energy-Aware Fine-Grained Relationship Learning Network for Text-Video Retrieval
• On the Role of Temporal Granularity in the Robustness of Spiking Neural Networks
• PhysGen: Physically Grounded 3D Shape Generation for Industrial Design
• Zero-Shot Image Denoising via Hybrid Prior-Guided Pseudo Sample Generation
• EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation
• OccAny: Generalized Unconstrained Urban 3D Occupancy
• Beyond the Static World: Continual Category Discovery under Visual Drift
• Brewing Stronger Features: Dual-Teacher Distillation for Multispectral Earth Observation
• Is your VLM Sky-Ready? A Comprehensive Spatial Intelligence Benchmark for UAV Navigation
• PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation
• Enhancing Out-of-Distribution Detection with Extended Logit Normalization
• OmniVTG: A Large-Scale Dataset and Training Paradigm for Open-World Video Temporal Grounding
• 240FPS Stereo Vision from Monocular Mixed Spikes
• SCE-Depth: A Spherical Compound Eye Framework for Wide FOV Depth Estimation
• Every Error has Its Magnitude: Asymmetric Mistake Severity Training for Multiclass Multiple Instance Learning
• AdaSpot: Spend Resolution Where It Matters for Precise Event Spotting
• Unique Lives, Shared World: Learning from Single-Life Videos
• Task-Driven Implicit Representations for Automated Design of LiDAR Systems
• Global Structure-from-Motion Meets Feedforward Reconstruction
• GS-ASM: 2DGS-Supervised Active Stereo Matching
• GardenDesigner: Encoding Aesthetic Principles into Jiangnan Garden Construction via a Chain of Agents
• Feed-forward Gaussian Registration for Head Avatar Creation and Editing
• EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generation
• TEXTRIX: Latent Attribute Grid for Native Texture Generation and Beyond
• Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation
• Resolving Endpoint Underfitting in Diffusion Bridges via Noise Alignment
• Captain Safari: A World Engine with Pose-Aligned 3D Memory
• Can a Second-View Image Be a Language? Geometric and Semantic Cross-Modal Reasoning for X-ray Prohibited Item Detection
• Vibe Spaces for Creatively Connecting and Expressing Visual Concepts
• MMLandmarks: a Cross-View Instance-Level Benchmark for Geo-Spatial Understanding
• Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillation
• CHEEM: Continual Learning by Reuse, New, Adapt and Skip - A Hierarchical Exploration-Exploitation Approach
• LumiX: Structured and Coherent Text-to-Intrinsic Generation
• FARMER: Flow AutoRegressive Transformer over Pixels
• No Calibration, No Depth, No Problem: Cross-Sensor View Synthesis with 3D Consistency
• 4DSurf: High-Fidelity Dynamic Scene Surface Reconstruction
• Interact2Ar: Full-Body Human-Human Interaction Generation via Autoregressive Diffusion Models
• BabyVLM-V2: Toward Developmentally Grounded Pretraining and Benchmarking of Vision Foundation Models
• OraPO: Oracle-educated Reinforcement Learning for Data-efficient and Factual Radiology Report Generation
• InverFill: One-Step Inversion for Enhanced Few-Step Diffusion Inpainting
• BrepGaussian: CAD reconstruction from Multi-View Images with Gaussian Splatting
• Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts
• SeeThrough3D: Occlusion Aware 3D Control in Text-to-Image Generation
• MagicQuill V2: Precise and Interactive Image Editing with Layered Visual Cues
• Structural Graph Probing of Vision–Language Models
• VABench: A Comprehensive Benchmark for Audio-Video Generation
• CARLoS: Retrieval via Concise Assessment Representation of LoRAs at Scale
• Rethinking Token Reduction for Large Vision-Language Models
• Opti-NeuS: Neural Reconstruction for Dual-Layered Transparent and Opaque Objects
• X-PCR: A Benchmark for Cross-modality Progressive Clinical Reasoning in Ophthalmic Diagnosis
• CASPA: Graph-Structured Concept Anchors for Modality-Agnostic Adaptation in Vision–Language Models
• Virtual Immunohistochemistry Staining with Dual-Aligned Multi-Task Feature Guidance
• ChArtist: Generating Pictorial Charts with Unified Spatial and Subject Control
• SegMo: Co-Designing Content-Aware Sparsity and Locally-Cohesive Segment Parallelism for Efficient VLM Inference
• Structure-Aware Representation Distillation for Tiny-Dense Object Segmentation
• HAD: Hallucination-Aware Diffusion Priors for 3D Reconstruction
• Adapting In-context Generation for Enhanced Composed Image Retrieval
• A Bit is All You Need! Efficient Video Capture via Single Bit Imaging
• Selective Amnesia using Contrastive Subnet Erasure for Class Level Unlearning in Vision Models
• VCP-Attack: Visual-Contrastive Projection for Transferable Black-Box Targeted Attacks on Large Vision-Language Models
• VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
• Free-Grained Hierarchical Visual Recognition
• ORD: Object-Relation Decoupling for Generalized 3D Visual Grounding
• Spot The Ball: A Benchmark for Visual Social Inference
• SPOT: Spatiotemporal Prompt Optimization for Motion-Stabilized MLLM-Guided Video Segmentation
• BALM: A Model-Agnostic Framework for Balanced Multimodal Learning under Imbalanced Missing Rates
• Learnable Motion-Focused Tokenization for Effective and Efficient Video Unsupervised Domain Adaptation
• Multi-modal Test-time Adaptation via Adaptive Probabilistic Gaussian Calibration
• IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment
• PanDA: Unsupervised Domain Adaptation for Multimodal 3D Panoptic Segmentation in Autonomous Driving
• Robustness Under Data Scarcity: Few-Shot Continual Adversarial Training for Evolving Threats
• Hist2Style: Histogram-Guided Stylization with Bilateral Grids
• MultiModalPFN: Extending Prior-Data Fitted Networks for Multimodal Tabular Learning
• Consensus vs. Controversy: Mapping the Decision Space Where Architectures Diverge
• A Semantically Disentangled Unified Model for Multi-category 3D Anomaly Detection
• BioVITA: Biological Dataset, Model, and Benchmark for Visual-Textual-Acoustic Alignment
• Focus on Background: Exploring SAM's Potential in Few-shot Medical Image Segmentation with Background-centric Prompting
• TC-Padé: Trajectory-Consistent Padé Approximation for Diffusion Acceleration
• FireScope: Wildfire Risk Raster Prediction With a Chain-of-Thought Oracle
• BEV-SLD: Self-Supervised Scene Landmark Detection for Global Localization with LiDAR Bird’s-Eye View Images
• Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models
• BoostSLT: Boosting Sign Language Translation via a Plug-and-Play Diffusion-Based Semantic Enhancer
• Forging a Dynamic Memory: Retrieval-Guided Continual Learning for Generalist Medical Foundation Models
• TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition
• Agentic Retoucher for Text-To-Image Generation
• VRR-QA: Visual Relational Reasoning in Videos Beyond Explicit Cues
• ProSoftArena: Benchmarking Hierarchical Capabilities of Multi-modal Agents in Professional Software Environments
• Progressive Multi-cue Alignment for Unaligned RGBT Tracking
• SVBench: Evaluation of Video Generation Models on Social Reasoning
• Guiding Diffusion Models with Fine-Grained Conditions and Semantics-Preserving Sampling for One-Shot Federated Learning
• Align Images Before You Generate
• Learning Diffeomorphism for Medical Image Registration with Time-Embedded Architectures Using Semigroup Regularization
• SHAPE: Structure-aware Hierarchical Unsupervised Domain Adaptation with Plausibility Evaluation for Medical Image Segmentation
• High-Quality and Efficient Turbulence Mitigation with Events
• Roots Beneath the Cut: Uncovering the Risk of Concept Recovery in Pruning-Based Unlearning for Diffusion Models
• Compressed-Domain-Aware Online Video Super-Resolution
• FreeForm: Reduced-Order Deformable Simulation from Particle-Based Skinning Eigenmodes
• Understanding Task Transfer in Vision-Language Models
• Rethinking Asymmetric Quantization: Hidden Symmetry in Vision Model Weights
• Explaining CLIP Zero-shot Predictions Through Concepts
• FaceCam: Portrait Video Camera Control via Scale-Aware Conditioning
• Region-Aware Instance Consistency Learning for Micro-Expression Recognition
• Quota-Calibrated Fine-Grained Alignment with Context-Aware Marginals for Text-based Person Retrieval
• TAR: Token-Aware Refinement for Fine-grained Generalized Category Discovery
• Mixture-of-Experts based Feature Decoupling for Open Vocabulary Scene Graph Generation
• Depth Any Endoscopy: Towards Self-Supervised Generalizable Depth Estimation in Monocular Endoscopy
• Open-Ended Instruction Realization with LLM-Enabled Multi-Planner Scheduling in Autonomous Vehicles
• Follow the Saliency: Supervised Saliency for Retrieval-augmented Dense Video Captioning
• QuadSync: Quadrifocal Tensor Synchronization via Tucker Decomposition
• VidEoMT: Your ViT is Secretly Also a Video Segmentation Model
• NavForesee: A Unified Vision-Language World Model for Hierarchical Planning and Dual-Horizon Navigation Prediction
• Driving on Registers
• Diffusion-Based sRGB Real Noise Generation via Prompt-Driven Noise Representation Learning
• AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors
• Personalized Federated Training of Diffusion Models with Privacy Guarantees
• Better, Stronger, Faster: Tackling the Trilemma in MLLM-based Segmentation with Simultaneous Textual Mask Prediction
• Generalizable Co-Salient Object Detection via Mixed Content-Style Modulation
• TM-BSN: Triangular-Masked Blind-Spot Network for Real-World Self-Supervised Image Denoising
• Focal–General Diffusion Model with Semantic Consistent Guidance for Sign Language Production
• Mirror Illusion Art
• KVSmooth: Mitigating Hallucination in Multi-modal Large Language Models through Key-Value Smoothing
• WaTeRFlow: Watermark Temporal Robustness via Flow Consistency
• SHARP: Short-Window Streaming for Accurate and Robust Prediction in Motion Forecasting
• Efficient Equivariant Transformer for Self-Driving Agent Modeling
• Universal Guideline-Driven Image Clustering via a Hybrid LLM Agent
• HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning
• Factorized Context Aggregation for Robust Cancer Risk Estimation via Soft Re-Ranked Retrieval and Hierarchical Anchors
• IntrinsicWeather: Controllable Weather Editing in Intrinsic Space
• FantasyVLN: Unified Multimodal Chain-of-Thought Reasoning for Vision-and-Language Navigation
• WildPose: A Unified Framework for Robust Pose Estimation in the Wild
• Cross-Axis Feature Fusion with Joint-Wise Motion Difference Prediction for Text-Based 3D Human Motion Editing
• Ov3R: Open-Vocabulary Semantic 3D Reconstruction from RGB Videos
• DSERT-RoLL: Robust Multi-Modal Perception for Diverse Driving Conditions with Stereo Event-RGB-Thermal Cameras, 4D Radar, and Dual-LiDAR
• VIRO: Robust and Efficient Neuro-Symbolic Reasoning with Verification for Referring Expression Comprehension
• PixelRush: Ultra-Fast, Training-Free High-Resolution Image Generation via One-step Diffusion
• Describe Anything Anywhere At Any Moment
• Breaking the Regional Perception Bottleneck of Multimodal Large Language Models via External Reasoning Framework
• Finding Distributed Object-Centric Properties in Self-Supervised Transformers
• Relightable Holoported Characters: Capturing and Relighting Dynamic Human Performance from Sparse Views
• DynFusion: Rethinking Condition Fusion for Adaptive Multi-Conditional Text-to-Image Generation
• Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep
• Physics-Consistent Diffusion for Efficient Fluid Super-Resolution via Multiscale Residual Correction
• Designing Instance-Level Sampling Schedules via REINFORCE with James-Stein Shrinkage
• No Hard Negatives Required: Concept Centric Learning Leads to Compositionality without Degrading Zero-shot Capabilities of Contrastive Models
• Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model
• SineProject: Machine Unlearning for Stable Vision-Language Alignment
• Depth Hypothesis Guided Iterative Refinement for Event–Image Monocular Depth Estimation
• Order Matters: 3D Shape Generation from Sequential VR Sketches
• FAAR: Efficient Frequency-Aware Multi-Task Fine-Tuning via Automatic Rank Selection
• From Corners to Fiducial Tags: Revisiting Checkerboard Calibration for Event Cameras
• VectorArk: Learning Practical Image Vectorization with Rounded Polygon Representation
• RoboTAG: End-to-end Robot Pose Estimation via Topological Alignment Graph
• MAPS: Preserving Vision-Language Representations via Module-Wise Proximity Scheduling for Better Vision-Language-Action Generalization
• 2D-LFM: Lifting Foundation Model without 3D Supervision
• INSIGHT Bench: Towards Grounded IN-SItu Guidance for Robotic ManipulaTion
• TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis
• Foundation Model Priors Enhance Object Focus in Feature Space for Source-Free Object Detection
• ARMFlow: AutoRegressive MeanFlow for Online 3D Human Reaction Generation
• Parallel Rigidity Matters for Bundle Adjustment
• Is the Modality Gap a Bug or a Feature? A Robustness Perspective
• KLIP: Localized Distribution Shift Detection via KL-Divergence with Diffusion Priors in Inverse Problems
• Towards Uncertainty-aware Unsupervised Domain Adaptation for Videos and Time-Series with Causal Optimal Transport
• Dynamic Magic: Unleashing Restricted Knowledge for Lifelong Person Re-Identification
• Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models
• Red-teaming Retrieval-Augmented Diffusion Models via Poisoning Knowledge Bases
• Reliable Policy Transfer for Safety-Aware End-to-End Driving with Deep Reinforcement Learning
• cryoSENSE: Compressive Sensing Enables High-throughput Microscopy with Sparse and Generative Priors on the Protein Cryo-EM Image Manifold
• Minimal Constraint Relaxation for Multiview Autocalibration
• EfficientVPR: Toward Efficient Visual Place Recognition via Scene-Aware Prompt Tuning and Adaptive Feature Enhancement
• OrthoFuse: Training-free Riemannian Fusion of Orthogonal Style-Concept Adapters for Diffusion Models
• CADC: Content Adaptive Diffusion-Based Generative Image Compression
• Unlocking the Power of Critical Factors for 3D Visual Geometry Estimation
• NeuroSeg Meets DINOv3: Transferring 2D Self-Supervised Visual Priors to 3D Neuron Segmentation via DINOv3 Initialization
• ReasonX: MLLM-Guided Intrinsic Image Decomposition
• How to Take a Memorable Picture? Empowering Users with Actionable Feedback
• TESO: Online Tracking of Essential Matrix by Stochastic Optimization
• RemedyGS: Defend 3D Gaussian Splatting Against Computation Cost Attacks
• DSO: Direct Steering Optimization for Bias Mitigation
• UniPart: Part-Level 3D Generation with Unified 3D Geom–Seg Latents
• Reward Sharpness-Aware Fine-Tuning for Diffusion Models
• SonoWorld: From One Image to a 3D Audio-Visual Scene
• MimicTalker: A Multimodal Interactive and Memory-Enhanced Framework for Real-Time Dyadic 3D Head Generation
• DualPrim: Compact 3D Reconstruction with Positive and Negative Primitives
• Latent Implicit Visual Reasoning
• MoECLIP: Patch-Specialized Experts for Zero-shot Anomaly Detection
• Denoise and Align: Towards Source-Free UDA for Robust Panoramic Semantic Segmentation
• Focus, Don’t Prune: Identifying Instruction-Relevant Regions for Information-Rich Image Understanding
• SAVE: Speech-Aware Video Representation Learning for Video-Text Retrieval
• Scene Grounding in the Wild
• InstructMix2Mix: Consistent Sparse-View Editing Through Multi-View Model Personalization
• TempoMaster: Efficient Long Video Generation via Next-Frame-Rate Prediction
• High Resolution Neural Video Coding with Bi-directional Confidence-Guided Reference Information Modeling
• Iris: Integrating Language into Diffusion-based Monocular Depth Estimation
• AdaSFormer: Adaptive Serialized Transformers for Monocular Semantic Scene Completion from Indoor Environments
• G-MIXER: Geodesic Mixup-based Implicit Semantic Expansion and Explicit Semantic Re-ranking for Zero-Shot Composed Image Retrieval
• MarkushGrapher-2: End-to-end Multimodal Recognition of Chemical Structures
• ORION: ORthonormal Text Encoding for Universal VLM AdaptatION
• Multinex: Lightweight Low-light Image Enhancement via Multi-prior Retinex
• RHO: Robust Holistic OSM-Based Metric Cross-View Geo-Localization
• GM-R^2: Generative Matching Learning for Unsupervised Geometric Representation and Registration
• FabricGen: Microstructure-Aware Woven Fabric Generation
• Mirai: Autoregressive Visual Generation Needs Foresight
• OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation
• Time Blindness: Why Video-Language Models Can’t See What Humans Can?
• SAT-RRG: LLM-Guided Self-Adaptive Training for Radiology Report Generation with Token-Level Push–Pull Optimization
• Evo-Retriever: LLM-Guided Curriculum Evolution with Viewpoint-Pathway Collaboration for Multimodal Document Retrieval
• Is Bin Generation Indispensable? A Bin-Generation-Free Dataset Quantization via Semantic Perspective
• MERG3R: A Divide-and-Conquer Approach to Large-Scale Neural Visual Geometry
• Guiding Token-Sparse Diffusion Models
• LiREC-Net: A Target-Free and Learning-Based Network for LiDAR, RGB, and Event Calibration
• GeneVAR: Causal MeanFlow for Autoregressive Gene-to-WSI Tile Synthesis
• CURVE: A Benchmark for Cultural and Multilingual Long Video Reasoning
• LayoutAD: Exploring Semantic-Geometric Misalignment Reasoning for Scene Layout Anomaly Detection
• MindPower: Enabling Theory-of-Mind Reasoning in VLM-based Embodied Agents
• VideoWeaver: Multimodal Multi-View Video-to-Video Transfer for Embodied Agents
• GGPT: Geometry-Grounded Point Transformer
• LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
• See Through the Noise: Improving Domain Generalization in Gaze Estimation
• EasyV2V: A High-quality Instruction-based Video Editing Framework
• ViterbiPlanNet: Injecting Procedural Knowledge via Differentiable Viterbi for Planning in Instructional Videos
• Predict Before You Explore: Predictive Planning with Specialized Memory for Embodied Question Answering
• Life-IQA: Boosting Blind Image Quality Assessment through GCN-enhanced Layer Interaction and MoE-based Feature Decoupling
• Latent Diffusion Inversion Requires Understanding the Latent Space
• Video Panels for Long Video Understanding
• 4D Local Modeling Toward Dynamic Global Perception for Ambiguity-free Rotation-Invariant Point Cloud Analysis
• SparseCam4D: Spatio-Temporally Consistent 4D Reconstruction from Sparse Cameras
• Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images
• Discover, Segment, and Select: A Progressive Mechanism for Zero-shot Camouflaged Object Segmentation
• Online Data Curation for Object Detection via Marginal Contributions to Dataset-level Average Precision
• Easy2Hard: From Partially to Fully Unmatched Modalities as Negative Samples in Contrastive Learning
• Global-Aware Edge Prioritization for Pose Graph Initialization
• Efficient and Training-Free Single-Image Diffusion Models
• 4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation
• CRFT: Consistent–Recurrent Feature Flow Transformer for Cross-Modal Image Registration
• Vista4D: Video Reshooting with 4D Point Clouds
• InnoAds-Composer: Efficient Condition Composition for E-Commerce Poster Generation
• HybridDriveVLA: Vision-Language-Action Model with Visual CoT reasoning and ToT Evaluation for Autonomous Driving
• IVAAN: Instance-level Vision-Language Alignment via Attribute-Guided Text Prompts Generation for Nuclei Analysis
• FedRAC: Rolling Submodel Allocation for Collaborative Fairness in Federated Learning
• SEA: Evaluating Sketch Abstraction Efficiency via Element-level Commonsense Visual Question Answering
• Towards Decompositional Human Motion Generation with Energy-Based Diffusion Models
• Can Natural Image Autoencoders Compactly Tokenize fMRI Volumes for Long-Range Dynamics Modeling?
• Sketch2Colab: Sketch-Conditioned Multi-Human Animation via Controllable Flow Distillation
• Merge3D: Efficient 3D Multimodal LLMs via Joint 2D-3D Token Merging
• MSRL: Scaling Generative Multimodal Reward Modeling via Multi-Stage Reinforcement Learning
• Anomaly-Related Residual Fields for Cross-domain Anomaly Detection
• Beyond the Ground Truth: Enhanced Supervision for Image Restoration
• NVGS: Neural Visibility for Occlusion Culling in 3D Gaussian Splatting
• LUMINA: A Multi-Vendor Mammography Benchmark with Energy Harmonization Protocol
• The Universal Normal Embedding
• Sampling-Aware Quantization for Diffusion Models
• PAMotion: Physics-Aware Motion Generation for Full-Body Interaction with Multiple Objects
• EXOTIC: External Vision-driven Incomplete Multi-view Classification
• GeoRelight: Learning Joint Geometrical Reconstruction and Relighting with Flexible Multi-Modal Diffusion Transformers
• Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
• SAG-GNN: Semantic-Aware Guided GNN for Descriptor-Free 2D-3D Matching
• VIRD: View-Invariant Representation through Dual-Axis Transformation for Cross-View Pose Estimation
• MVLM: Template-Free Tracking via Vision–Language Margin Confidence and Memory-Gated Tracking
• TLMA: Mitigating the Impact of Weakly Labeled Information for Video Anomaly Detection
• CausalVAD: De-confounding End-to-End Autonomous Driving via Causal Intervention
• Photo3D: Advancing Photorealistic 3D Generation through Structure‑Aligned Detail Enhancement
• Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models
• Align While Search: Belief-Guided Exploratory Inference for World-Grounded Embodied Agents
• Self-guided Semantic Inspection for Zero-Shot Composed Image Retrieval
• Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR
• More than the Sum: Panorama-Language Models for Adverse Omni-Scenes
• One Algorithm to Align Them All
• LLaVAShield: Safeguarding Multimodal Multi-Turn Dialogues in Vision-Language Models
• GenieDrive: Towards Physics-Aware Driving World Model with 4D Occupancy Guided Video Generation
• MM-ACT: Learn from Multimodal Parallel Generation to Act
• Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection
• Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving
• LaDy: Lagrangian-Dynamic Informed Network for Skeleton-based Action Segmentation via Spatial-Temporal Modulation
• SWIFT: Sliding Window Reconstruction for Few-Shot Training-Free Generated Video Attribution
• MUSE: Harnessing Precise and Diverse Semantics for Few-Shot Whole Slide Image Classification
• LS-ViT: Least-Squares Hessian Based Block Reconstruction for Low-Bit Post-Training Quantization of Vision Transformers
• Camera Control for Text-to-Image Generation via Learning Viewpoint Tokens
• MaskDexGrasp: Generative Masked Modeling for Part-Aware Dexterous Grasp Synthesis
• Revisiting the Necessity of Full Accuracy: Weakly Supervised Object-Level Offset Correction for Misaligned Building Labels
• Learning to Drive is a Free Gift: Large-Scale Label-Free Autonomy Pretraining from Unposed In-The-Wild Videos
• FastEventDGS: Deformable Gaussian Splatting for Fast Dynamic Scenes from a Single Event Camera
• QUANTIPHY: A Quantitative Benchmark Evaluating Physical Reasoning Abilities of Vision-Language Models
• UniT: Unified Multimodal Chain-of-Thought Test-time Scaling
• From Rays to Projections: Better Inputs for Feed-Forward View Synthesis
• OLATverse: A Large-scale Real-world Object Dataset with Precise Lighting Control
• When Do Models Actually Decide? Mapping the Layer-Wise Decision Timeline in Pretrained Neural Networks
• mmWaveFlow: Unified Enhancement and Generation of mmWave Human Point Clouds
• BiGain: Unified Token Compression for Joint Generation and Classification
• PhysHO: Physics-Based Dynamic 3D Gaussian Human and Object from Monocular Video
• Physically-Grounded Turbulence Mitigation with Frame-Shared Degradation Parameters
• Temporal Interaction in Spiking Transformers with Multi-Delay Mixer
• PHAC: Promptable Human Amodal Completion
• SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation
• Question-guided Visual Compression with Memory Feedback for Long-Term Video Understanding
• Catalyst4D: High-Fidelity 3D-to-4D Scene Editing via Dynamic Propagation
• ExtrinSplat: Decoupling Geometry and Semantics for Open-Vocabulary Understanding in 3D Gaussian Splatting
• Dexterous World Models
• WRIVINDER: Towards Spatial Intelligence for Geo-locating Ground Images onto Satellite Imagery
• VGA-Bench: A Unified Benchmark and Multi-Model Framework for Video Aesthetics and Generation Quality Evaluation
• StreamDiT: Real-Time Streaming Text-to-Video Generation
• Mechanisms of Object Localization in Vision–Language Models
• VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactions
• LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight
• UniLight: A Unified Representation for Lighting
• D-Convexity: A Unified Differentiable Convex Shape Prior via Quasi-Concavity for Data-driven Image Segmentation
• CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering
• See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis
• Diffusion Mental Averages
• Simple but Effective Triplet-Based Compression Strategies for Compact Visual Localization
• Beyond Ground-Truth: Leveraging Image Quality Priors for Real-World Image Restoration
• MUST: Modality-Specific Representation-Aware Transformer for Diffusion-Enhanced Survival Prediction with Missing Modality
• Mining Attribute Subspaces for Efficient Fine-tuning of 3D Foundation Models
• SwitchCraft: Training-Free Multi-Event Video Generation with Attention Controls
• Goldilocks Test Sets for Face Verification
• MODIX: A Training-Free Multimodal Information-Driven Positional Index Scaling for Vision-Language Models
• BAMI: Training-Free Bias Mitigation in GUI Grounding
• DriveCombo: Benchmarking Compositional Traffic Rule Reasoning in Autonomous Driving
• Bridging the Perception Gap in Image Super-Resolution Evaluation
• PhysSkin: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning
• Generalizable Sparse-View 3D Reconstruction from Unconstrained Images
• Urban-GS: A Unified 3D Gaussian Splatting Framework for Compact and High-Fidelity Aerial-to-Street Reconstruction
• Mitigating Multimodal Hallucinations via Gradient-based Self-Reflection
• F^2HDR: Two-Stage HDR Video Reconstruction via Flow Adapter and Physical Motion Modeling
• ProgressiveAvatars: Progressive Animatable 3D Gaussian Avatars
• ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion
• Pointing at Parts: Training-Free Few-Shot Grounding in Multimodal LLMs
• GeoSemba: Reconstructing State Space Model for Cross Paradigm Representation in Medical Image Segmentation
• IPR-1: Interactive Physical Reasoner
• LA-Pose: Latent Action Pretraining Meets Pose Estimation
• Bidirectional Multimodal Prompt Learning with Scale-Aware Training for Few-Shot Multi-Class Anomaly Detection
• FG-Portrait: 3D Flow Guided Editable Portrait Animation
• C^2FG: Control Classifier-Free Guidance via Score Discrepancy Analysis
• Adapting Lightweight Image-based Counting Models for Video Crowd Counting
• TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment
• OpenDance: Multimodal Controllable 3D Dance Generation with Large-scale Internet Data
• InterPhys: Physics-aware Human Motion Synthesis in a Dynamic Scene
• DLVP-CLIP: Enhancing Fine-Grained Zero-Shot Anomaly Detection via Dynamic Local Visual Prompting
• MM-SeR: Multimodal Self-Refinement for Lightweight Image Captioning
• SLARM: Streaming and Language-Aligned Reconstruction Model for Dynamic Scenes
• Semantic Foam: Unifying Spatial and Semantic Scene Decomposition
• Topology-aware Feature Propagation for Unsupervised Non-rigid Point Cloud Correspondence
• Decision Boundary-aware Generation for Long-tailed Learning
• UCMNet: Uncertainty-Aware Context Memory Network for Under-Display Camera Image Restoration
• Visual Autoregressive Modeling via Next Focus Prediction
• LifeEval: A Multimodal Benchmark for Assistive AI in Egocentric Daily Life Tasks
• SearchAD: Large-Scale Rare Image Retrieval Dataset for Autonomous Driving
• GeoDiff4D: Geometry-Aware Diffusion for 4D Head Avatar Reconstruction
• Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translation
• Dropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splatting
• Detecting Compressed AI-Generated Images via Phase Spectrum Robustness
• Revisiting Monocular SLAM with Spatio-Temporal Scene Modeling
• When Token Pruning is Worse than Random: Understanding Visual Token Information in VLLMs
• Immunizing Models Against Harmful Long-Horizon Fine-Tuning via Contractive Optimization Dynamics
• OS-Fed: One Snapshot Is All You Need
• Changes in Real Time: Online Scene Change Detection with Multi-View Fusion
• DBMSolver: A Training-free Diffusion Bridge Sampler for High-Quality Image-to-Image Translation
• Cross-domain Dual-stream Feature Disentanglement for Brain Disorder Prediction with Sparsely Labeled PET
• Sparse Spectral LoRA: Routed Experts for Medical VLMs
• Scale Space Diffusion
• Dark3R: Learning Structure from Motion in the Dark
• PolySLGen: Online Multimodal Speaking-Listening Reaction Generation in Polyadic Interaction
• RGB-Event based Pedestrian Attribute Recognition: A Benchmark Dataset and An Asymmetric RWKV Fusion Framework
• PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Urban Scenes
• SR3R: Rethinking Super-Resolution 3D Reconstruction With Feed-Forward Gaussian Splatting
• Rethinking Glyph Spatial Information in Font Generation
• Hierarchical Long Video Understanding with Audiovisual Entity Cohesion and Agentic Search
• ReLaX: Reasoning with Latent Exploration for Large Reasoning Models
• RAP: Fast Feedforward Rendering-Free Attribute-Guided Primitive Importance Score Prediction for Efficient 3D Gaussian Splatting Processing
• Attention Surgery: An Efficient Recipe to Linearize Your Video Diffusion Transformer
• Rethinking Camera Choice: An Empirical Study on Fisheye Camera Properties in Robotic Manipulation
• Structure-to-Intensity Diffusion for Adverse-Weather LiDAR Generation
• GenTract: Generative Global Tractography
• KV-Tracker: Real-Time Pose Tracking with Transformers
• Adapter Shield: A Unified Framework with Built-in Authentication for Preventing Unauthorized Zero-Shot Image-to-Image Generation
• ElasticFormer: Detecting Objects in HRW Shots via Elastic Computing Vision Transformer
• Plug-and-Play PDE Optimization for 3D Gaussian Splatting: Toward High-Quality Rendering and Reconstruction
• HOG-Layout: Hierarchical 3D Scene Generation, Optimization and Editing via Vision-Language Models
• SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding
• High-Fidelity Mobile Avatars with Pruned Local Blendshapes
• EVLF: Early Vision-Language Fusion for Generative Dataset Distillation
• SCIEval: Evaluating and Benchmarking the Faithfulness of Scientific Image Generation and Interpretation with Large Multimodal Models
• Match-and-Fuse: Consistent Generation from Unstructured Image Sets
• Distributed Image Compression with Multimodal Side Information at Extremely Low Bitrates
• Think-Then-Generate: Structural Chain-of-Thought Reasoning for Consistent 3D Generation
• ReaGEN: Adaptive Generation of Structured Chains-of-Thought for Efficient Multimodal Reasoning
• CamDirector: Towards Long-Term Coherent Video Trajectory Editing
• PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction
• Unleashing Stealthy Backdoor Pandemic by Infecting a Single Diffusion Model
• IAFMNet: Information-Aware Feature Modulation for Efficient Super-Resolution
• MPL: Match-guided Prototype Learning for Few-shot Action Recognition
• Content-Aware Dynamic Patchification for Efficient Video Diffusion
• UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in RL
• DiGraphHal-Bench: Evaluating Multimodal Large Language Models on Complex Directed Graphs
• Bridge: Basis-Driven Causal Inference Marries VFMs for Domain Generalization
• ExPose: Reinforcing Video Generation Models for Extreme Pose Estimation
• Inter-Photon-Limited Videography
• OpenFS: Multi-Hand-Capable Fingerspelling Recognition with Implicit Signing-Hand Detection and Frame-Wise Letter-Conditioned Synthesis
• A Closed-Form Solution for Debiasing Vision-Language Models with Utility Guarantees Across Modalities and Tasks
• Evidential Neural Radiance Fields
• Scenes as Tokens: Multi-Scale Normal Distributions Transform Tokenizer for General 3D Vision–Language Understanding
• Coupled Diffusion Sampling for Training-Free Multi-View Image Editing
• Bridging RGB and Hematoxylin Components: An Interleaved Guidance and Fusion Framework for Point Supervised Nuclei Segmentation
• IDperturb: Enhancing Variation in Synthetic Face Generation via Angular Perturbations
• VoxTell: Free-Text Promptable Universal 3D Medical Image Segmentation
• TriLite: Efficient Weakly Supervised Object Localization with Universal Visual Features and Tri-Region Disentanglement
• HOLO: Homography-Guided Pose Estimator Network for Fine-Grained Visual Localization on SD Maps
• Human Geometry Distribution for 3D Animation Generation
• Through the Frequency Lens: Cross-Domain Generalisable Gaze Estimation with Adaptive Modulation
• Dense Metric Depth Completion from Sparse Direct Time-of-Flight Sensors
• SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL
• Interactive Episodic Memory with User Feedback
• SHands: A Multi-View Dataset and Benchmark for Surgical Hand-Gesture and Error Recognition Toward Medical Training
• Hear What You See: Video-to-Audio Generation with Diffusion Transformer and Semantic-Temporal Alignment-Ranked Direct Preference Optimization
• Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understanding
• Mixture of States: Routing Token-Level Dynamics for Multimodal Generation
• MedLIME: A Distribution-Aligned and Evidence-Supported Framework for Medical Saliency Explanations
• Otil: Accelerating Diffusion Model Inference via Communication-Efficient Multi-GPU Parallelism
• BiomedCCPL: Causal Conditional Prompt Learning for Biomedical Vision-Language Models
• LumiMotion: Improving Gaussian Relighting with Scene Dynamics
• ScenDi: 3D-to-2D Scene Diffusion Cascades for Urban Generation
• Learning Forgery-Aware Lip Representations Without Forgery Priors
• PnP-CM: Consistency Models as Plug-and-Play Priors for Inverse Problems
• Fresco: Frequency–Spatial Consistent Optimization for Fine-Grained Head Avatar Modeling
• Landscape-Awareness for Geometric View Diffusion Model
• Multi-Modal Representation Learning via Semi-Supervised Rate Reduction for Generalized Category Discovery
• Rascene: High-Fidelity 3D Scene Imaging with mmWave Communication Signals
• InsCal: Calibrated Multi-Source Fully Test-Time Prompt Tuning for Object Detection
• SASNet: Spatially-Adaptive Sinusoidal Networks for INRs
• Mark4D: Temporally-Consistent Watermarking for 4D Gaussian Splatting
• Hyperbolic Busemann Neural Networks
• GeCo-SRT: Geometry-aware Continual Adaptation for Cross-Task Sim-to-Real Transfer
• Space-Time Forecasting of Dynamic Scenes with Motion-aware Gaussian Grouping
• StableMTL: Repurposing Latent Diffusion Models for Multi-Task Learning from Partially Annotated Synthetic Datasets
• Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout
• Hear What Matters! Text-conditioned Selective Video-to-Audio Generation
• DLWM: Dual Latent World Models enable Holistic Gaussian-centric Pre-training in Autonomous Driving
• Progress by Pieces: Test-Time Scaling for Autoregressive Image Generation
• Guiding Diffusion Models with Semantically Degraded Conditions
• IMAIA: Interactive Maps AI Assistant for Travel Planning and Geo-Spatial Intelligence
• REACH: Explicit Recovery Behavior for Diffusion Policies
• D2T2 - Multimodal Automated Planning for Brachytherapy
• Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors
• SketchRevive: Fine-Grained Pixel-to-Vector Sketch Completion with Diffusion-Prior-Guided Multimodal LLMs
• 3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding
• Spatio-Temporal Difference Guided Motion Deblurring with the Complementary Vision Sensor
• CTCal: Rethinking Text-to-Image Diffusion Models via Cross-Timestep Self-Calibration
• Teaching DINOv3 About Partial 3D Geometry: A Self-Supervised Geometry-Aware Approach
• tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction
• ELiC: Efficient LiDAR Geometry Compression via Cross-Bit-depth Feature Propagation and Bag-of-Encoders
• DiffGraph: An Automated Agent-driven Model Merging Framework for In-the-Wild Text-to-Image Generation
• Benchmarking Endoscopic Surgical Image Restoration and Beyond
• ELITE: Efficient Gaussian Head Avatar from a Monocular Video via Learned Initialization and Test-time Generative Adaptation
• EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision
• TimeBridge: Self-Supervised Video Representation Learning via Start-End Joint Embedding and In-Between Frame Prediction
• LoL: Longer than Longer, Scaling Video Generation to Hour
• DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding
• SegGBC: Justifiable Coarse-to-Fine Granular-Ball Computing for Enhancing Clustering Image Segmentation
• MERIT: Multi-domain Efficient RAW Image Translation
• ReHyAt: Recurrent Hybrid Attention for Video Diffusion Transformers
• UAV-CB: A Complex-Background RGB–T Dataset and Local Frequency Bridge Network for UAV Detection
• The Drift Kernel: Why Diffusion Models Change Even When Told Not To
• NS-Diff: Fluid Navier–Stokes Guided Video Diffusion via Reinforcement Learning
• Emergent Extreme-View Geometry in 3D Foundation Models
• M4Human: A Large-Scale Multimodal mmWave Radar Benchmark for Human Mesh Reconstruction
• iLRM: An Iterative Large 3D Reconstruction Model
• FedBPrompt: Federated Domain Generalization Person Re-Identification via Body Distribution Aware Visual Prompts
• PvP: Data-Efficient Humanoid Robot Learning with Proprioceptive-Privileged Contrastive Representations
• Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning
• Learning 3D Reconstruction with Priors in Test Time
• ThinkingViT: Matryoshka Thinking Vision Transformer for Elastic Inference
• Revisiting Model Stitching In the Foundation Model Era
• Unified Camera Positional Encoding for Controlled Video Generation
• When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm
• Personalized Image Descriptions from Attention Sequences
• Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation
• Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight
• UniChange: Unifying Change Detection with Multimodal Large Language Model
• PV-Ground: Text-Guided Point-Voxel Interaction for 3D Visual Grounding
• VLM-Loc: Localization in Point Cloud Maps via Vision-Language Models
• FlowDIS: Language-Guided Dichotomous Image Segmentation with Flow Matching
• ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body
• CrossHOI-Bench: A Unified Benchmark for HOI Evaluation across Vision-Language Models and HOI-Specific Methods
• CineBrain: A Large-Scale Multi-Modal Audiovisual Brain Dataset for Brain-Conditioned Video Generation
• SAQN: Semantic-based Adaptive Query Network for 3D Referring Expression Segmentation
• DetectSCI: Toward Object-Guided ROI Reconstruction for High-Resolution Video Snapshot Compressive Imaging
• DriverGaze360: OmniDirectional Driver Attention with Object-Level Guidance
• Ego-Grounding for Personalized Question-Answering in Egocentric Videos
• AnthroTAP: Learning Point Tracking with Real-World Motion
• Beyond [CLS] Token: Query-Driven Token-Level Forgery Purification for Generalizable Deepfake Detection
• VecAttention: Vector-wise Sparse Attention for Accelerating Long Context Inference
• A Temporal and Content Co-Awareness Latent Diffusion for Controllable Hand Image Generation
• FlashVSR: Towards Real-time Diffusion-Based Streaming Video Super Resolution
• GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristics
• RenderFlow: Single-Step Neural Rendering via Flow Matching
• WalkGPT: Grounded Vision–Language Conversation with Depth-Aware Segmentation for Pedestrian Navigation
• PARSE: Part-Aware Relational Spatial Modeling
• Smoothing the Score Function to Enhance Generalization in Diffusion Models
• Multi-Hierarchical Contrastive Spectral Fusion for Multi-View Clustering
• A Difference-in-Difference Approach to Detecting AI-Generated Images
• BriMA: Bridged Modality Adaptation for Multi-Modal Continual Action Quality Assessment
• Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations
• Seeing Motion Through Polarity for Event-based Action Recognition
• R4: Retrieval-Augmented Reasoning for Vision-Language Models in 4D Spatio-Temporal Space
• Why Not Hyperparameter-Friendly Optimisation? A Monotonic Adaptive Norm Rescaling Approach For Long-Tailed Recognition
• Investigating Self-Supervised Representations for Audio-Visual Deepfake Detection
• Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation
• Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimation
• Let it Snow! Animating 3D Gaussian Scenes with Dynamic Weather Effects via Physics-Guided Score Distillation
• 3D sans 3D Scans: Scalable Pre-training from Video-Generated Point Clouds
• RFDM: Residual Flow Diffusion Models for Video Editing
• StreamReady: Learning What to Answer and When in Long Streaming Videos
• FiDeSR: High-Fidelity and Detail-Preserving One-Step Diffusion Super-Resolution
• MSGNav: Unleashing the Power of Multi-modal 3D Scene Graph for Zero-Shot Embodied Navigation
• Anti-I2V: Safeguarding your Photos from Malicious Image-to-video Generation
• Concept-Aware LoRA for Domain-Aligned Segmentation Dataset Generation
• TIACam: Text-Anchored Invariant Feature Learning with Auto-Augmentation for Camera-Robust Zero-Watermarking
• Scaling Test-Time Robustness of Vision-Language Models via Self-Critical Inference Framework
• ViKey: Enhancing Temporal Understanding in Videos via Visual Prompting
• The LLM Bottleneck: Why Open-Source Vision LLMs Struggle with Hierarchical Visual Recognition
• Learning Where to Look and How to Judge: Resolution-agnostic Image Quality Assessment with Quality-aware Saliency
• VITAL: Vision-Encoder-centered Pre-training for LMMs in Visual Quality Assessment
• AutoCut: End-to-end advertisement video editing based on multimodal discretization and controllable generation
• Inside-Out: Measuring Generalization in Vision Transformers Through Inner Workings
• Robust Promptable Video Object Segmentation
• Generative Modeling of Weights: Generalization or Memorization?
• See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding
• Controllable Federated Prompt Learning at Test Time
• MM-OVSeg: Multimodal Optical–SAR Fusion for Open-Vocabulary Segmentation in Remote Sensing
• MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE
• Progressive Mask Distillation for Self-supervised Video Representation
• CoWTracker: Tracking by Warping instead of Correlation
• DEVA: Fine-tuning Multimodal Large Language Models for Visual Perception Tasks
• EventHub: Data Factory for Generalizable Event-Based Stereo Networks without Active Sensors
• BiEvLight: Bi-level Learning of Task-Aware Event Refinement for Low-Light Image Enhancement
• Progressive Supernet Training for Efficient Visual Autoregressive Modeling
• Collaborative Multi-Mode Pruning for Vision-Language Models
• AdvFM: Lookahead Flow-Matching Velocity-Field Attacks for Imperceptible and Transferable Adversarial Examples
• DROID-SLAM in the Wild
• DPL: Decoupled Prototype Learning for Enhancing Robustness of Vision–Language Transformers to Missing Modalities
• From Panel to Pixel: Zoom-In Vision–Language Pretraining from Biomedical Scientific Literature
• PriVi: Towards a General-Purpose Video Model for Primate Behavior in the Wild
• SpiralDiff: Spiral Diffusion with LoRA for RGB-to-RAW Conversion Across Cameras
• Hint2Gen: Bridging Understanding and Generation via Code-structured Hints
• SIR: Structured Image Representations for Explainable Robot Learning
• SkillSight: Efficient First-Person Skill Assessment with Gaze
• VinQA: Visual Elements Interleaved Long-form Answer Generation for Real-World Multimodal Document QA
• Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion
• FlowMotion: Training-Free Flow Guidance for Video Motion Transfer
• RDFace: A Benchmark Dataset for Rare Disease Facial Image Analysis under Extreme Data Scarcity and Phenotype-Aware Synthetic Generation
• Generative Neural Video Compression via Video Diffusion Prior
• GH-NAF: Grid-Adaptive Hash-Level–Attended Neural Attenuation Fields for Discrepancy-Aware CBCT
• FISHuman: Fine-grained Single-image 3D Human Reconstruction via Multi-view 4D Remeshing
• HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models
• Towards Storytelling Animations: Joint Synthesis of Human and Camera Motions
• Mining Instance-Centric Vision–Language Contexts for Human–Object Interaction Detection
• Measuring the (Un)Faithfulness of Concept-Based Explanations
• Scaling Parallel Sequence Models to Vision Foundation Models
• Phased DMD: Few-step Distribution Matching Distillation via Score Matching within Subintervals
• StreamVLO: Streaming Visual–LiDAR Odometry with Cumulative Drift Compensation
• Beyond Text Prompts: Precise Concept Erasure through Text–Image Collaboration
• From Intuition to Investigation: A Tool-Augmented Reasoning MLLM Framework for Generalizable Face Anti-Spoofing
• LangRef3DGS: Natural Language-Guided 3D Referential Segmentation from Partial Observations via 3D Gaussian Splatting
• It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models
• Causal Motion Diffusion Models for Autoregressive Motion Generation
• Computer Vision with a Superpixelation Camera
• MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator
• Learnability-Guided Diffusion for Dataset Distillation
• The Invisible Gorilla Effect in Out-of-distribution Detection
• Nonlinear Color Transfer via Learnable Bezier Flows
• CAST: Context-Aware Dynamic Latent Space Transformation for Interactive Text-to-Image Retrieval
• Language Models Can Explain Visual Features via Steering
• Cinematic Audio Source Separation Using Visual Cues
• Beyond Static Frames: Temporal Aggregate-and-Restore Vision Transformer for Human Pose Estimation
• Failure Modes for Deep Learning–Based Online Mapping: How to Measure and Address Them
• LEMON: A Large Endoscopic MONocular Dataset and Foundation Model for Perception in Surgical Settings
• Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset
• PETAR: Localized Findings Generation with Mask-Aware Vision-Language Modeling for PET Automated Reporting
• Scene-VLM: Multimodal Video Scene Segmentation via Vision-Language Models
• Towards Intrinsic-Aware Monocular 3D Object Detection
• DeX-Portrait: Disentangled and Expressive Portrait Animation via Explicit and Latent Motion Representations
• CoT-Edit: Let CoT Guide Instruction Video Editing
• Language-guided Frequency Modulation for Large Vision-Language Models
• TopoCL: Topological Contrastive Learning for Medical Imaging
• Conversational Image Segmentation: Grounding Abstract Concepts with Scalable Supervision
• Semantic Alignment for Pose-Invariant Identity Preserving Diffusion
• Exposing and Evaluating Hallucinations for GUI Grounding
• Image-based Outlier Synthesis With Training Data
• Kontinuous Kontext: Continuous Strength Control for Instruction-based Image Editing
• DiffusionHarmonizer: Bridging Neural Reconstruction and Photorealistic Simulation with Online Diffusion Enhancer
• Geometrically-Constrained Agent for Spatial Reasoning
• Tutor-Student Reinforcement Learning: A Dynamic Curriculum for Robust Deepfake Detection
• MatchED: Crisp Edge Detection Using End-to-End, Matching-based Supervision
• TempoControl: Temporal Attention Guidance for Text-to-Video Models
• Inter-Edit: First Benchmark for Interactive Instruction-Based Image Editing
• RECS4R: Bridging Semantics and Geometry for Referring Remote Sensing Interpretation
• TokenSplat: Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstruction
• GeoSURGE: Geo-localization using Semantic Fusion with Hierarchy of Geographic Embeddings
• MultiCrafter: High-Fidelity Multi-Subject Generation via Disentangled Attention and Identity-Aware Preference Alignment
• Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Models
• TokenTrace: Multi-Concept Attribution through Watermarked Token Recovery
• Human-like Abstract Visual Reasoning via Understanding and Solving Reasoning Loop
• HierEdit: Region-Aware Hierarchical Diffusion for Efficient High-Resolution Editing
• Neu-PiG: Neural Preconditioned Grids for Fast Dynamic Surface Reconstruction on Long Sequences
• Δynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From Videos
• FedAdamom: Adaptive Momentum for Improved Generalization in Federated Optimization
• MoRGS: Efficient Per-Gaussian Motion Reasoning for Streamable Dynamic 3D Scenes
• LASER: Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstruction
• EvoID: Reinforced Evolution for Identity-Preserving Video Generation
• Photo-Guided Tooth Segmentation on 3D Oral Scan Model
• Interpretable Debiasing of Vision-Language Models for Social Fairness
• Post-training Feature Pruning for Fundus Images Classification
• Tracking-Guided 4D Generation: Foundation-Tracker Motion Priors for 3D Model Animation
• LATA: Laplacian-Assisted Transductive Adaptation for Conformal Uncertainty in Medical VLMs
• Revisiting Visual Corruptions in LVLMs: A Shape–Texture Perspective on Model Failures
• MacTok: Robust Continuous Tokenization for Image Generation
• Anchor-Guided Gradient Alignment for Incomplete Multimodal Learning
• Efficient Unrolled Networks for Large-Scale 3D Inverse Problems
• Stability-Driven Motion Generation for Object-Guided Human-Human Co-Manipulation
• Hierarchical Visual Relocalization with Nearest View Synthesis from Feature Gaussian Splatting
• Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptation
• Mocap-2-to-3: Multi-view Lifting for Monocular Motion Recovery with 2D Pretraining
• KαLOS finds Consensus: A Meta-Algorithm for Evaluating Inter-Annotator Agreement in Complex Vision Tasks
• Multi-view Pyramid Transformer: Look Coarser to See Broader
• Hyperbolic Gramian Volumes for Multimodal Alignment
• PhysVid: Physics Aware Local Conditioning for Generative Video Models
• Learning by Analogy: A Causal Framework for Compositional Generalization
• Visual Diffusion Models are Geometric Solvers
• VGent: Visual Grounding via Modular Design for Disentangling Reasoning and Prediction
• SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Driving
• Remote Sensing Image Super-Resolution for Imbalanced Textures: A Texture-Aware Diffusion Framework
• Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers
• HierAmp: Coarse-to-Fine Autoregressive Amplification for Generative Dataset Distillation
• More Than Meets the Eye: A Unified Image Fusion Framework via Semantic-Pixel Entropy Trade-off for Zero-Shot Generalization
• RL‑ScanIQA: Reinforcement-Learned Scanpaths for Blind 360° Image Quality Assessment
• Pose-guided Enriched Feature Learning for Federated-by-camera Person Re-identification
• MU-GeNeRF: Multi-view Uncertainty-guided Generalizable Neural Radiance Fields for Distractor-aware Scene
• HFedATM: Hierarchical Federated Domain Generalization via Optimal Transport and Regularized Mean Aggregation
• Taming Video Models for 3D and 4D Generation via Zero-Shot Camera Control
• DualReg: Dual-Space Filtering and Reinforcement for Rigid Registration
• 2ndMatch: Finetuning Pruned Diffusion Models via Second-Order Jacobian Matching
• PyraTok: Language-Aligned Pyramidal Tokenizer for Video Understanding and Generation
• Test-Time Alignment of Text-to-Image Diffusion Models via Null-Text Embedding Optimisation
• Improving Sparse Autoencoder with Dynamic Attention
• When Lines Meet Textures: Spatial-Frequency Aligned Diffusion Features for Cross-Sparsity Correspondence
• Medic-AD: Towards Medical Vision-Language Model's Clinical Intelligence
• Unified Vector Floorplan Generation via Markup Representation
• LEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving
• Drainage: A Unifying Framework for Addressing Class Uncertainty
• MoLingo: Motion–Language Alignment for Text-to-Human Motion Generation
• Decoupling Vision and Language: Codebook Anchored Visual Adaptation
• OmniBrainBench: A Comprehensive Multimodal Benchmark for Brain Imaging Analysis Across Multi-stage Clinical Tasks
• Cross-modal Fuzzy Alignment Network for Text-Aerial Person Retrieval and A Large-scale Benchmark
• PropFly: Learning to Propagate via On-the-Fly Supervision from Pre-trained Video Diffusion Models
• PR-IQA: Partial-Reference Image Quality Assessment for Diffusion-Based Novel View Synthesis
• PLACID: Identity-Preserving Multi-Object Compositing via Video Diffusion with Synthetic Trajectories
• Abstract 3D Perception for Spatial Intelligence in Vision-Language Models
• SimRecon: SimReady Compositional Scene Reconstruction from Real Videos
• Expand and Prune: Maximizing Trajectory Diversity for Effective GRPO in Generative Models
• CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning
• PFGNet: A Fully Convolutional Frequency-Guided Peripheral Gating Network for Efficient Spatiotemporal Predictive Learning
• BEA-GS: BEyond RAdiance Supervision in 3DGS for Precise Object Extraction
• Color-Encoded Illumination for High-Speed Volumetric Scene Reconstruction
• VideoCoF: Unified Video Editing with Temporal Reasoner
• Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought Models
• Beyond Single Images: A Comprehensive Benchmark for Album-Level Vision-Language Understanding
• CURE: Curriculum-guided Multi-task Training for Reliable Anatomy Grounded Report Generation
• Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm
• DIMOS: Disentangling Instance-level Moving Object Segmentation
• SFR-Net: Steering-Fusion-Refining Network in Multi-label Zero-Shot Sewer Defect Detection
• Differentiable Laplacian Matrix Guided Superpixel Segmentation
• Neural Differentiation in Deep Networks: A Theoretical Framework for Expressivity and Representational Diversity
• Recurrent Reasoning with Vision-Language Models for Estimating Long-Horizon Embodied Task Progress
• Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding
• SpiderCam: Low-Power Snapshot Depth from Differential Defocus
• Machine Unlearning via Adaptive Gradient Reweighting and Multi-stage Objective Optimization
• ZOO-Prune: Training-Free Token Pruning via Zeroth-Order Gradient Estimation in Vision-Language Models
• AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation
• TaskForce: Cooperative Multi-agent Reinforcement Learning for Multi-task Optimization
• CME-CAD: Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generation
• PromptLoop: Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model Alignment
• FastRef: Fast Prototype Refinement for Few-shot Industrial Anomaly Detection
• Deformation-based In-Context Learning for Point Cloud Understanding
• MoRel: Long-Range Flicker-Free 4D Motion Modeling via Anchor Relay-based Bidirectioanl Blending with Hierarchical Densification
• MMR-AD: A Large-Scale Multimodal Dataset for Benchmarking General Anomaly Detection with Multimodal Large Language Models
• DuetMerging: Synergizing Dynamic and Static Strategies for Mitigating Task Interference in Model Merging
• Learning to Infer Parameterized Representations of Plants from 3D Scans
• Boundary-Responsive Differentiable Gating for Superpixel-Based Segmentation
• Making the Classification Explanation Faithful to the Confidence Score
• Specificity-aware reinforcement learning for fine-grained open-world classification
• UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attenders
• ReBaPL: Repulsive Bayesian Prompt Learning
• Rethinking Two-Stage Referring-by-Tracking in Referring Multi-Object Tracking: Make it Strong Again
• CountGD++: Generalized Prompting for Open-World Counting
• Adaptive Auxiliary Prompt Blending for Target-Faithful Diffusion Generation
• Hyper-PCN: Hypergraph-Based Point Cloud Completion via High-Order Correlation Modeling
• SketchFaceGS: Real-Time Sketch-Driven Face Editing and Generation with Gaussian Splatting
• SimScale: Learning to Drive via Real-World Simulation at Scale
• FedRE: A Representation Entanglement Framework for Model-Heterogeneous Federated Learning
• TagSplat: Topology-Aware Gaussian Splatting for Dynamic Mesh Modeling and Tracking
• Sketch2CT: Multimodal Diffusion for Structure-Aware 3D Medical Volume Generation
• DeltaQuant: 4-bit Video Diffusion Models with Spatiotemporal Delta Smoothing
• StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation
• MusicInfuser: Making Video Diffusion Listen and Dance
• ShapeAR: Generating Editable Shape Layers via Autoregressive Diffusion
• DiverseDiT: Towards Diverse Representation Learning in Diffusion Transformers
• Learning Straight Flows: Variational Flow Matching for Efficient Generation
• Robo-SGG: Exploiting Layout-Oriented Normalization and Restitution Can Improve Robust Scene Graph Generation
• Solving a Nonlinear Blind Inverse Problem for Tagged MRI with Physics and Deep Generative Priors
• Mapping Networks
• Forecasting 3D Scanpaths in Egocentric Video
• Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality
• MMSD3.0: A Multi-Image Benchmark for Real-World Multimodal Sarcasm Detection
• Probabilistic Prompt Adaptation for Unified Image Aesthetics and Quality Assessment
• SegQuant: A Semantics-Aware and Generalizable Quantization Framework for Diffusion Models
• TherA: Thermal-Aware Visual-Language Prompting for Controllable RGB-to-Thermal Infrared Translation
• NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos
• SemLayer: Semantic-aware Generative Segmentation and Layer Construction for Abstract Icons
• Latent Chain-of-Thought World Modeling for End-to-End Driving
• GeodesicNVS: Probability Density Geodesic Flow Matching for Novel View Synthesis
• BluRef: Unsupervised Image Deblurring with Dense-Matching References
• Spatiotemporal Pyramid Flow Matching for Climate Emulation
• From 2D Alignment to 3D Plausibility: Unifying Heterogeneous 2D Priors and Penetration-Free Diffusion for Occlusion-Robust Two-Hand Reconstruction
• EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editing
• PS-SR: Pseudo-Single-Step Video Super-Resolution via Speculative Diffusion
• AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions
• When Pretty Isn’t Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators
• Masking Matters: Unlocking the Spatial Reasoning Capabilities of LLMs for 3D Scene-Language Understanding
• Learning Mutual View Information Graph for Adaptive Adversarial Collaborative Perception
• IFCSR: Inference-Free Fidelity-Realism Control for One-Step Diffusion-based Real-World Image Super-Resolution
• FairLLaVA: Fairness-Aware Parameter-Efficient Fine-Tuning for Large Vision-Language Assistants
• Adaptive Video Distillation: Mitigating Oversaturation and Temporal Collapse in Few-Step Generation
• OctoNav: Towards Generalist Embodied Navigation
• MV-Fashion: Towards Enabling Virtual Try-On and Size Estimation with Multi-View Paired Data
• MAD: Modality-Adaptive Decoding for Mitigating Cross-Modal Hallucinations in Multimodal Large Language Models
• RobustVisRAG: Causality-Aware Vision-Based Retrieval-Augmented Generation under Visual Degradations
• GOR-IS: 3D Gaussian Object Removal In the Intrinsic Space
• Learning from Oblivion: Predicting Knowledge-Overflowed Weights via Retrodiction of Forgetting
• EgoXtreme: A Dataset for Robust Object Pose Estimation in Egocentric Views under Extreme Conditions
• MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks
• Uni-Hema: Unified Model for Digital Hematopathology
• Seeing Conversations: Communication Context Identification in Egocentric Video
• Object-WIPER: Training-Free Object and Associated Effect Removal in Videos
• ActiveGrasp: Information-Guided Active Grasping with Calibrated Energy-based Model
• TaskIT: Memory-Efficient Fine-Tuning of Multi-LoRA LLMs via Cross-Task Importance Transfer
• SECOS: Semantic Capture for Rigorous Classification in Open-World Semi-Supervised Learning
• Diffusion MRI Transformer with a Diffusion Space Rotary Positional Embedding (D-RoPE)
• AeroGS: Scale-Aware Gaussian Splatting for Pose-Free Dynamic UAV Scene Reconstruction
• TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Size
• GPFlow: Gaussian Prototype Probability Flow for Unsupervised Multi-Modal Anomaly Detection
• Learning Convex Decomposition via Feature Fields
• OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning
• RLFTSim: Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning Fine-Tuning
• FILTR: Extracting Topological Features from Pretrained 3D Models
• Good Can Sometimes be Bad: A Unified Attack against 3D Point Cloud Classifier by a Flexible Isotropic Resampling
• SALMUBench: A Benchmark for Sensitive Association-Level Multimodal Unlearning
• Virtual Nodes Guided Dynamic Graph Neural Network for Brain Tumor Segmentation with Missing Modalities
• RankOOD - Class Ranking-based Out-of-Distribution Detection
• EDGS: Eliminating Densification for Efficient Convergence of 3DGS
• RealVLG-R1: A Large-Scale Real-World Visual-Language Grounding Benchmark for Robotic Perception and Manipulation
• ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrieval
• EMMA: Concept Erasure Benchmark with Comprehensive Semantic Metrics and Diverse Categories
• Learning Long-term Motion Embeddings for Efficient Kinematics Generation
• DSCA: Dynamic Subspace Concept Alignment for Lifelong VLM Editing
• End-to-End Language-Action Model for Humanoid Whole Body Control
• HeSS: Head Sensitivity Score for Sparsity Redistribution in VGGT
• Lenses: Toward Polysemous Vision–Language Understanding
• D2Cache: Second-Order Delta Caching for Higher Video Diffusion Acceleration
• Towards Calibrating Prompt Tuning of Vision- Language Models
• Diagnose, Correct, and Learn from Manipulation Failures via Visual Symbols
• Image-to-Point Cloud Feature Back-Projection for Multimodal Training of 3D Semantic Segmentation
• Masked Auto-Regressive Variational Acceleration: Fast Inference Makes Practical Reinforcement Learning
• CoIn3D: Revisiting Configuration-Invariant Multi-Camera 3D Object Detection
• Deciphering Genotype-Phenotype Mechanisms from High-Content Profiling via Knowledge-Guided Multi-modal Graph Learning
• MIBURI: Towards Expressive Interactive Gesture Synthesis
• IMU-HOI: A Symbiotic Framework for Coherent Human-Object Interaction and Motion Capture via Contact-Conscious Inertial Fusion
• OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens
• Resolving the Identity Crisis in Text-to-Image Generation
• Revisiting Multimodal KV Cache Compression: A Frequency-Domain-Guided Outlier-KV-Aware Approach
• TrafficAlign: Aligning Large Language Models for Traffic Scenario Generation
• Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced Images

Report issues here.