ECCV 2026 Events with Videos

Keynotes

• From Machine Perception to Human Expertise
• Yann LeCun — World Models: Enabling the next AI revolution
• From Visual Recognition to Embodied AI

Orals

• Provable and Robust Wavefront Sensing via Self-Reference Interferometry
• Broadband Wide Field of View Imaging with Computational Mirrors
• Poppy: Polarization-Based Plug-and-Play Guidance for Enhancing Surface Normal Estimation
• A second-order theory of texture for depth from focus
• PRISM-VO: Scale-Aware Visual Odometry Using Photometric Plenoptic Bundle Adjustment
• Cross-View Yaw Estimation in Location Uncertainty with Line-Aligning Yaw Scoring
• Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability
• Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding
• Understanding Geometric Representations in Self-Supervised Vision Transformers via Subspace Intervention
• World Knowledge in the Weights: Reading Concept Circuits of Vision Transformers
• What CLIP Knows but Cannot Say: Recovering Negation from Frozen Intermediate Features
• Make Geometry Matter for Spatial Reasoning
• Heat Kernel Textures -- the Geodesic Gaussians That Do Not Splat
• NURBS Splatting: A Unified Differentiable Rendering Framework for Vector Graphics
• TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields
• Repurposing Geometric Foundation Models for Multi-view Diffusion
• Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching
• Geometric Context Transformer for Streaming 3D Reconstruction
• LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows
• GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation
• Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding
• Seeing Through the Weights: Privacy Leakage in Scene Coordinate Regression

Oral Sessions

• Oral Session: Computational Imaging, Shape Recovery and Camera Geometry
• Oral Session: Video Understanding, Generation and Multimodal Learning
• Oral Session: Vision Foundation Models: Interpretability and Reasoning
• Oral Session: 3D Graphics and Geometric Representations
• Oral Session: 3D Reconstruction, Registration and Scene Modeling

Panels

• The Age of LLMs: Who Is the Researcher Now? How LLMs Are Changing Search, Ideation, and Scientific Judgment
• Can AI Build New Knowledge?

Posters

• TopoGS: Planar Reconstruction via Topology-Aware 3D Gaussian Splatting
• One-Shot Feed-Forward 360° Animatable Avatar via Inpainted UV-Space Gaussian Modeling
• Sparse auto-regressive modeling for scene generation from multi-view images
• DLGStream: Dynamic Language-embedded Guassian Splatting for Open-vocabulary Enabled Free-viewpoint Video Streaming
• EventSpecPS: Photometric Stereo with Multispectral Reflectance Using an Event Camera
• ATOMIC: A Domain-Specific Vision-Language Model for Transmission Electron Microscopy
• Temporally Aware Densification for Dynamic 3D Gaussian Splatting
• Robust and Efficient Monocular 3D Gaussian SLAM for Kilometer-Scale Outdoor Scenes
• Targeted Structure Completion for Sparse-View 3D Reconstruction in Autonomous Driving
• The Devil Is in the Dark Pixels: Toward Brightness Bias-Robust Denoising
• Depth-guided Multi-view Exposure Bracketing for HDR Robot Vision
• TetraSDF: Analytic Isosurface Extraction with Multi-resolution Tetrahedral Grid
• Visual Prompt Discovery via Semantic Exploration
• Real-Time LiDAR Gaussian Splatting SLAM via Geometry-Aware Covariance Coupling
• DIGS: Differentiable, Incremental, Global, Scalable Pruning for Language Models
• FLM-Occ: Feed-forward Likelihood Maximization for Efficient Indoor Occupancy Prediction
• TRiGS: Temporal Rigid-Body Motion for Scalable 4D Gaussian Splatting
• DIVA: Instruction-Aware Vision Token Pruning via Dual-Probe Attention Discrepancy
• Cast and Attached Shadow Detection via Iterative Light and Geometry Reasoning
• Generalizable Neural Reconstruction of High-Fidelity Surfaces via Sparse Volumetric Representations
• Direct Preference Optimization for Perceptual Alignment via Vision-Language Consistency
• Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models
• Color Pass-Through via Camera-Display Coupling
• GAIA: A Data Flywheel System for Training GUI Test-Time Scaling Critic Models
• DASAM3D: A Unified Foundation Model for Enhanced 3D Scene Reconstruction and Segmentation
• ME-IQA: Memory-Enhanced Image Quality Assessment via Re-Ranking
• CURE: Cumulative Knowledge Reuse for Efficient Device-Server Hybrid Inference in Vision-Language Models
• Director: Instance-aware Gaussian Splatting for Dynamic Scene Modeling and Understanding
• FlashBEV: Fast and Memory-Efficient Exact BEV Transformation with IO-Awareness
• Learning from Primitive: Probing Visual Reasoning of LVLMs via Counting
• UniTriSplat: A Unified 3D Gaussian Splatting Framework with Uniform Spherical Rasterization for Universal Cameras
• Two Birds, One Projection: Harmonizing Safety and Utility in LVLMs via Inference-time Feature Projection
• Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models
• UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models
• Holo-Captioning: A Comprehensive Textual View of 3D Scenes
• Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction
• Predictive Photometric Uncertainty in Gaussian Splatting for Novel View Synthesis
• λSplit: Self-Supervised Content-Aware Spectral Unmixing for Fluorescence Microscopy
• VoxAnchor: Explicit Voxel-Semantic Grounding for Spatial Understanding in Videos
• SkipGS: Post-Densification Backward Skipping for Efficient 3DGS Training
• NeLU3D: Neural Inverse Structured Light without Modeling the Projector
• A Mechanism-Driven Theory of Phase Transitions in Active Learning
• RAU: Reference-based Anatomical Understanding with Vision-Language Models
• Stable and Scalable Bundle Adjustment of Holistic 3D Structures
• VLA-R1: Enhancing Reasoning in Vision-Language-Action Models
• SiPhy: Single-Image Physical Property Reasoning
• DreamEdit3D: Personalization of Multi-View Diffusion Models for 3D Editing
• E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation
• Gaussians on Fire: High-Frequency Reconstruction of Flames
• A second-order theory of texture for depth from focus
• Drop-In Perceptual Optimization for 3D Gaussian Splatting
• Dotting the Eye: An Intent-Driven Image Retouching Agent for Visual Focus Enhancement
• DiaDem: Advancing Dialogue Descriptions in Audiovisual Video Captioning for Multimodal Large Language Models
• PDF-Omni: Poincaré Dual Disk Distortion Field-based Recurrent Update for Omnidirectional Stereo Matching
• DPGS: A Diffusion-Prior Guided Framework for Large-Scale 3D Gaussian Splatting Reconstruction
• Sticking Information in Plain Sight: Encoding and Detecting Hidden Stickers in the Real World
• Molmo-Point: Better Pointing for VLMs with Grounding Tokens
• FoundDP: Revisiting Weak Disparity Observability in Dual-Pixel Depth Estimation
• ScenarioControl: Vision-language Controllable Vectorized Latent Scenario Generation
• WeatherReasonSeg: A Benchmark for Weather-Aware Reasoning Segmentation in Visual Language Models
• R3RECON: Radiance-Field-Free Active Reconstruction via Renderability
• From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space
• BioMTBee: Biologically Constrained Multi-View Template-Based 3D Reconstruction of Bumblebee
• ScAle: Attention Head Scaling as a Minimal Adapter for Spatial Reasoning in Vision–Language Models
• UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization
• Raymap-Guided Coupling for Drift-Robust Unposed Feed-Forward 3D Reconstruction
• KISS-GS: 3D Gaussian Splatting Compression Kept Simple
• Global Pose Control for Generative View Synthesis in Normalized Object Coordinate Space
• Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations
• WildDepth: A Multimodal Dataset for 3D Wildlife Perception and Depth Estimation
• RefracGS: Novel View Synthesis Through Refractive Water Surfaces with 3D Gaussian Ray Tracing
• V-REX: Benchmarking Exploratory Visual Reasoning via Chain-of-Questions
• SceneHI: High-Resolution 3D-Consistent Scene Texturing with Controllable Illumination
• StructSplat: Generalizable 3D Gaussian Splatting from Uncalibrated Sparse Views
• TDSR-VLA: Transition-aware Denoising Sequence Representations for Vision-Language-Action
• Minute4D: Training High-Fidelity 4D Gaussian Splatting in One Minute
• Estimating Individual Tree Height and Species from UAV Imagery
• IRIS: Intersection-aware Ray-based Implicit Editable Scenes
• World Reconstruction From Inconsistent Views
• Synthetic Sub-Aperture Phase Augmentation for Demosaicing 2×2 Shared Microlens Sensors
• GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherence
• SA-ResGS: Self-Augmented Residual 3D Gaussian Splatting for Next Best View Selection
• DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis
• Geo-ID: Test-Time Geometric Consensus for Cross-View Consistent Intrinsics
• VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignment
• TransVLM: A Vision-Language Framework and Benchmark for Detecting Any Shot Transitions
• Broadband Wide Field of View Imaging with Computational Mirrors
• Geometry-Preserving in 3D Gaussian Splatting for LiDAR-Camera Extrinsic Calibration
• DecoupleGS: Interactive 3D Gaussian Splatting for End-to-End Autonomous Driving Testing
• SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models
• AirSplat: Alignment and Rating for Robust Feed-Forward 3D Gaussian Splatting
• FaCT-GS: Fast and Scalable CT Reconstruction with Gaussian Splatting
• Boosting 6D Object Pose Estimation via Monocular Depth Cues
• GAP-Track: Bridging the Resolution Gap for Cross-Resolution RGBT Tracking
• From Phase to Phenomenon: Self-Supervised Learning of Subsurface Scattering with Minimal Phase-shift Inputs
• AutoV: Loss-Oriented Ranking for Visual Prompt Retrieval in LVLMs
• The 3D Mirage: Probing and Taming 3D Hallucinations
• GaINeR: Geometry-Aware Implicit Neural Representation for Image Editing
• Monte Carlo Energy Aggregation for Mobile 3D Gaussian Splatting
• Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction
• OmniRen: Neural Rendering wih Heterogeneous Scene Primitives
• Geometric Distillation from Rectified Stereo: Leveraging Epipolar Cues for Monocular Depth
• EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving
• LongVQUBench: Benchmarking Long-Term Video Quality Understanding of Vision-Language Models
• Delineating Knowledge Boundaries for Honest Large Vision-Language Models
• ReSplat: Learning Recurrent Gaussian Splatting
• PanoLess: Environment Reconstruction from Partial Reflective Views
• Foveated Reasoning: Stateful, Action-based Visual Focusing for Vision-Language Models
• Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation
• FillGS: Filling Observation Gaps in 4D Gaussian Splatting via Viewpoint-Time Selection and Generative Refinement
• Tricam-rPPG: A Multimodal Multispectral Dataset for remote Photoplethysmography
• Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction
• The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding
• Pixel-wise Planarity for High-Precision Monocular Plane Segmentation
• Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures
• Confidence-Based Mesh Extraction from 3D Gaussians
• EGGS: Explicitly Granular 3D Gaussian Splatting via Luma-Aware and Volume-Preserving Attribute Factorization
• TruthLens: Object Hallucination Detection via Self-Evaluating Truthfulness Scores in LVLMs
• Multi4D: High-Fidelity Dynamic Gaussian Splatting via Multi-Level Competitive Allocation
• How Far Are Vision-Language Models from Constructing the Real World? A Benchmark for Physical Generative Reasoning
• InstantHDR: Single-forward Gaussian Splatting for High Dynamic Range 3D Reconstruction
• RAGA: Real Time Ray Traced Gaussian Shadow Casting for 3DGS Avatar-Scene Interaction
• ARC-Loc: Leveraging Azimuthal Ray Convergence as a Geometric Cue for Direct Cross-View Localization
• Compact Low-Cost Hyperspectral Imaging via Angular-to-Spectral Diversity Conversion
• GKDT: General Keypoint Detection Transformer
• C3-Bench: A Context-Aware Change Captioning Benchmark
• Do Not Leave a Gap: Hallucination-Free Object Concealment in Vision-Language Models
• LinStereo: Linear-Complexity Global Attention for Multi-Scale Iterative Stereo Matching
• Incremental Online Scene Reconstruction by 3D Gaussian Triangulation
• SFD-Net: Sharp Feature Detection Network Based on Local Geometric Features
• To Adapt or Not to Adapt? Selective Adaptation for Vision-Language Models
• ESNE: Efficient Surface Normal Estimation for LiDAR Point Clouds with Sequential Modeling and Variability Guidance
• Edit3r: Instant 3D Scene Editing from Sparse Unposed Images
• Deformable Triangle Splatting: Flexible Primitives for Real-Time Radiance Field Rendering
• SpectralSplats: Robust Differentiable Tracking via Spectral Moment Supervision
• TriNLOS: Triplane Representations for Neural Non-Line-of-Sight Imaging
• SeeClear: Reliable Transparent Object Depth Estimation via Generative Opacification
• StratoSplat: Taming Layered Regularities for Sparse Aerial 3D Gaussian Splatting
• Identity-Preserving Human Reconstruction from a Single Image via 3D Token Inference
• Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action Alignment
• Do Flat Minima Improve Sparse Novel View Synthesis?
• High-speed Imaging through Turbulence with Event-based Light Fields
• VersaViT: Enhancing MLLM Vision Backbones via Task-Guided Optimization
• Dynamic World Generation Made Efficient
• mmIR: Frequency-Space Inverse Rendering for 3D Millimeter-Wave Radar ADC Synthesis
• Geometrically Consistent Multi-View Scene Generation from Freehand Sketches
• ViewSplat: View-Adaptive Dynamic Gaussian Splatting for Feed-Forward Synthesis
• Domain Generalization via Text-Anchored Information Bottleneck
• PuzLM: Solving Jigsaw Puzzles with Sequence-to-Sequence Language Models
• Don’t Mask Out the Background! Natural-Light Photometric Stereo via Illumination Reconstruction
• Fast and Compact 3D Gaussian Splatting with Polarized Opacity Prior
• Extending a Large View Synthesis Model for Multi-view Panoptic Segmentation
• DINO-SLAM: DINO-Informed RGB-D SLAM for Neural Implicit and Explicit Representations
• Weather-Conditioned Depth Anything
• Fourier Compressor: Frequency-Domain Visual Token Compression for Vision-Language Models
• Text-Guided 6D Object Pose Rearrangement via Closed-Loop VLM Agents
• DICE: Disentangled Instance-Class knowlEdge prompt tuning via SAE for Vision-Language Models
• TurboMPLE: Joint Infrared Turbulence Mitigation and Physical Fields Estimation via Mutual Progressive Layered Extraction
• Any to Full: Prompting Depth Anything for Depth Completion in One Stage
• CrossView: Can Vision-Language Models Reason Across Cameras?
• COSY: Compositional 3DGS Synthesis for Disentangled Human Head Editing
• PRISM-VO: Scale-Aware Visual Odometry Using Photometric Plenoptic Bundle Adjustment
• TecoPrompt: Temporal-Conservative Prompt Learning for Vision-Language Models
• Filterless Snapshot Hyperspectral Imaging using Guided Patch Diffusion
• SONIC: Spectral Optimization of Noise for Inpainting with Consistency
• SkyLume: A Large-Scale Multi-Illumination Aerial Benchmark for Urban Scene Reconstruction and Beyond
• Gaze-to-text Generation: Beyond Categorical Decoding of Human Attention
• From Blobs to Spokes: High-Fidelity Surface Reconstruction via Oriented Gaussians
• Less is More: A Simple yet Effective Object-Centric Prompting Strategy for Vision-Language Reasoning in Autonomous Driving
• URoPE: Universal Relative Position Embedding across Geometric Spaces
• Active View Selection with Perturbed Gaussian Ensemble for Tomographic Reconstruction
• Diversity-Aware View Partitioning for Scalable VGGT
• LiteGS: a high-performance framework to train 3dgs in subminutes via system and algorithm codesign
• Decoupled Illumination Priors for Spatially Controllable Multi-View Indoor Scene Relighting
• REFINE: Super-efficient Pruning for 3D Gaussian Splatting via Rendering-Free Primitive Importance
• Interact3D: Compositional 3D Generation of Interactive Objects
• SMP-UWGS: Coupled Physics-Geometry Optimization for Scalable Multi-Partition Underwater 3D Reconstruction
• Gender Bias in Vision-Language In-Context Learning
• Ceptor: Vision-Language Model-Infused Diverse Guidance for Detecting Anything
• GeoNVS: Geometry Grounded Video Diffusion for Novel View Synthesis
• HandSCS: Structural Coordinate Space for Animatable Hand Gaussian Splatting
• UniGeo: Unifying Geometric Constraints for Camera-Controllable Image Editing via Video Priors
• Open-Vocabulary BEV Segmentation with 3D-Aware Geometric Constraints
• HairOrbit: Multi-view Aware 3D Hair Modeling from Single Portraits
• Nexels: Neurally-Textured Surfels for Real-Time Novel View Synthesis with Sparse Primitives
• Seeing Isn't Orienting: A Cognitively Grounded Hierarchical Benchmark for Object Orientation in MLLMs
• EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learning
• Learning Physics-based Forward Model Corrections in Unrolled Networks for Diffuser-based Imaging
• GRAFT: Geometric Refinement and Fitting Transformer for Human Scene Reconstruction
• Learning to Deny: Action Denial in Multimodal Large Language Models
• CoDePose: Multi-View 3D Human Pose Estimation via Coupled 2D-3D Denoising Diffusion
• Provable and Robust Wavefront Sensing via Self-Reference Interferometry
• 3DGS3: Joint Super Sampling and Frame Interpolation for Real-Time Large-Scale 3DGS Rendering
• Poppy: Polarization-Based Plug-and-Play Guidance for Enhancing Surface Normal Estimation
• CrossFeat: Bridging Imaging Modalities in Feature Descriptor Space
• MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robots
• FixAnything: 3D-Consistent Rendering Refinement via Video Generative Priors
• MeGAS: Thermomechanical Dynamic Gaussian Splatting for Thermophysical Scene Editing
• VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM
• Learning Ego-Centric BEV Representations from a Perspective-Privileged View: Cross-View Supervision for Online HD Map Construction
• AVSplat:Dense-View Feed-Forward 3D Gaussian Splatting with Assist-View Preconditioning
• Natural Image Pretraining Improves Abstract Reasoning
• Video Can Teach PAN-Sharpening: PSF-Aware Cross-Domain Supervision
• Multi-view Multi-vehicle Driving Dataset for Novel View Synthesis
• From Gaze to Meaning: An AI Agent for Unified Zero-Shot Grounding and Explanation
• Dynamic Inverse Rendering for Enhanced Material-Lighting Decomposition
• CAM3R: Camera-Agnostic Model for 3D Reconstruction
• Unlocking Few-Shot Capabilities in LVLMs via Prompt Conditioning and Head Selection
• PriSplat: Propagating Reliable Multi-view Information for Distractor-Free 3DGS
• Flash-Refine: Frustum-Guided Local Incremental Learning for Efficient 3D Gaussian Splatting Completion
• SyncFix: Multi-View Consistent Diffusion Refinement of 3D Reconstructions
• StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning
• Enhancing Embodied Reasoning and Grounding by Novel View Synthesis
• Disentangling Pictorial Cue Understanding from Language Bias in VLMs via Depth Ordering Task
• Reflection-aware generative novel view synthesis
• Learning to Suppress SPAD-based LiDAR Flare
• Fourier Splatting: Generalized Fourier encoded primitives for scalable radiance fields
• MLP Splatting: Object-Centric Neural Fields
• Instant Expressive Gaussian Head Avatars at Over 100 FPS
• Beyond Atomic Layouts: Compositional Design Understanding with Vision-Language Models
• VERITAS: A Multi-agent Co-scientist for Verifiable Image-Derived Hypothesis Testing
• Token-Based Affordance Grounding with Large Vision-Language Models
• Physically Grounded Monocular Depth via Nanophotonic Wavefront Encoding
• Towards Geometry-Grounded Dense Semantic Matching with VGGT Priors
• Sparse-View Surface Reconstruction using Gaussian Splatting through High-Confidence Depth Propagation with Normal Priors
• City-Level 3D Surface Reconstruction with Viewpoint Orientation Partitioning and Scene Completion
• AutoWeather4D: Autonomous Driving Video Weather Conversion via G-Buffer Dual-Pass Editing
• Benchmarking Vision-Language Models for Microscopic Plant Image Understanding
• Wid3R: Wide Field-of-View 3D Reconstruction via Camera Model Conditioning
• Novel View Synthesis as Video Completion
• HIVE: Understanding Post Hallucination Reasoning in Vision Language Models
• Beyond Language: Grounding Referring Expressions with Hand Pointing in Egocentric Vision
• PaD-GS: Leveraging Distortion Map for Panoramic Gaussian Splatting
• ESC: Emotional Self-Correction for Reliable Vision-Language Models
• VLA Knows Its Limits
• Latent Fusion: Decoding Consolidated 3D Geometry from Feed-forward Geometry Transformer Latents
• OmniX: Any-view and Any-time 4D reconstruction via Feed-forward Trajectory Fields
• Neural Gate: Mitigating Privacy Risks in LVLMs via Neuron-Level Gradient Gating
• VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction
• StructureGS: Structure-aware Gaussian Splatting for Articulated Object Reconstruction
• Why Far Looks Up: Probing Spatial Representation in Vision-Language Models
• Partial Skeleton Visibility for Action Recognition: A Constrained Field-of-View Approach
• Attention-based Vision-Language Memory for Spatial Reasoning
• Towards Alias-Free 4D Gaussian Representations with Motion-Aware Filtering
• Triangle Splatting SLAM
• Geometry-Aware Style Transfer in 3D Gaussian Splatting
• NaVLM-PVC: Progressive Visual Compression for Efficient Native-Resolution Encoding in MLLMs
• EoS-FM: Can an Ensemble of Specialist Models act as a Generalist Feature Extractor?
• Rotate Your Character: Revisiting Video Diffusion Models for High-Quality 3D Character Generation
• Semantic Line Diffusion: Character-Consistent Line Art from text-annotated Storyboards
• CFM: Language-aligned Concept Foundation Model for Vision
• InstGS: Shared-Template Gaussian Instancing for Object-Redundancy-Free Rendering
• CoIn: Comprehensive 2D-3D Inpainting with Gaussian Splatting Guidance
• TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs
• Zoom-IQA: Image Quality Assessment with Reliable Region-Aware Reasoning
• NoPA: Non-Parametric Online 3D Scene Graph Generation
• On Test-Time Scaling for Vision-Language Models
• Efficient Camera Pose Augmentation for View Generalization in Robotic Policy Learning
• CulinaryCut: A Physics-aware Vision-Language-Action Benchmark for Food Cutting via Material Point Method
• Cube-Splat: High-Fidelity 360° Gaussian Splatting SLAM via Cubemap Factorization and Adjoint-Consistent Optimization
• Art Beyond Semantics: Sheaf-Informed Contrastive Learning for Multi-Relational Representations
• AdaptiveSplat: Texture Aware Controllable 3D Gaussian Allocation for Feed-Forward Reconstruction
• DEX-AR: A Dynamic Explainability Method for Autoregressive Vision-Language Models
• PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models
• Same Person, Different Depiction: Counterfactual Evaluation of Vision-Language Models on Individuals with Limb Deficiencies
• Less is More: Reducing Complexity in Vision-Language-Action Systems
• Fisheye3R: Adapting Unified 3D Feed-Forward Foundation Models to Fisheye Lenses
• Tackling Misattribution in 3D Intrinsic Decomposition via Proximity Attention Point Rendering
• DefenseSplat: Enhancing the Robustness of 3D Gaussian Splatting via Frequency-Aware Filtering
• Geometry-Aware Visual Representation for Remaining Useful Life Prediction
• Gripper-aware Vision Language Action Models
• SubSplat: High-Resolution Pixel-aligned 3DGS via Sub-pixel Gaussian Reparameterization
• MonoSR: Open-Vocabulary Spatial Reasoning on Monocular Images
• PixVOD: Pixel-Distributed Direct Visual Odometry and Depth Estimation
• Show Me Examples: Inferring Visual Concepts from Image Sets
• AdaBoosting Text Prompts for Vision-Language Models
• Decompose, Compare, and Decide: Multimodal LLMs are Implicit Few-Shot Learners
• Skin-R1: Clinical Knowledge-Guided Dermatological Diagnosis Using Vision-Language Models
• HCSU: A Dataset and Benchmark for Fine-Grained Historical Calligraphy Style Understanding
• 3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering
• Mapping Dark-Matter Clusters via Physics-Guided Diffusion Models
• Capacity-Controlled Multi-View Stylization of 3D Gaussian Splatting
• NanoGS: Training-Free and Lightweight Gaussian Splat Simplification
• UHD-MFF: Shattering Barriers in Multi-Focus Ultra-High-Definition Image Fusion via Learnable Lookup Tables
• FUSE: Filter-Free Unified Spatiotemporal Estimation of SpO2 via Wave-Transport Modeling
• MVGS: Multi-view Regulated Gaussian Splatting for Novel View Synthesis
• PanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-based 3D Visual Grounding
• RL-AWB: Deep Reinforcement Learning for Auto White Balance Correction in Low-Light Night-time Scenes
• Graph-GSReg: Leveraging 3D Scene Graphs for Gaussian Splatting Registration
• Improving Sparse-View 3DGS Generalization via Flat Minima Optimization
• MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors
• EGM: Efficient Visual Grounding Language Models
• Under One Sun: Multi-Object Generative Perception of Materials and Illumination
• SharpGS: Sharpness-Preserving 3D Gaussian Splatting with Differentiable Blur-Driven Density Control
• TPCNet: A Low-Light Image Enhancement Network Inspired by Triple Physical Constraints
• StarDojo: Benchmarking Open-Ended Behaviors of Agentic Multimodal LLMs in Production–Living Simulations with Stardew Valley
• Geometry-Propagated Gaussian Splatting for Aerial Sparse Novel View Synthesis
• When 3D Gaussian Splatting Recovers Real Surfaces
• Towards Reliable Medical Large Vision-Language Models via Counterfactual Preference Optimization
• HiReFF: High-Resolution Feedforward Human Reconstruction from Uncalibrated Sparse-View Video
• SkySplat-OV: Generalizable Language Gaussian Splatting for Open-Vocabulary Scene Understanding from Sparse Satellite Views
• MVFusion-GS: Motion-Variance Guided Temporal Attention for High-Quality Dynamic Gaussian Splatting
• GlassGS: Geometry and Concept-Aware 3D Gaussian Splatting for Reflective Enclosures
• AiSCREAM: Absolute Target Localization with Language-Conditioned Cross-View Alignment for Autonomous Vehicles
• Video Generative Models as Geometry Learner
• Why Do Vision Language Models Struggle To Recognize Human Emotions?
• ZeroSplat: Generalized Referring Segmentation in 3D Gaussian Splatting
• Open Your Eyes: Benchmarking the Detection of Fabricated Realities and Weaponized Ethics in VLMs
• ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views
• IndoorSplat: Enhanced Indoor Scene Reconstruction with Structured 2D Gaussian Splatting
• ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models
• WilLaGS: Latent-Conditional 3D Appearance Fields for Robust Gaussian Splatting In-the-Wild
• Asymmetric Anchoring: Opening the Black Box of MLLMs for Forgery Detection
• SpatiO: Adaptive Test-Time Orchestration of Vision-Language Agents for Spatial Reasoning
• SynLF: Zero-Shot Metric Depth from Light Field Cameras via Physics-Grounded Synthesis
• SPECSIA: Stylization Dataset for Novel-View Enhancement in Drawing-based 3D Animation
• ∂DIBR: Differentiable Depth Image-based Rendering for Fast Novel View Synthesis
• Proto-Gaussian: MRI Modality Translation Based on Learnable Structural Prototypes and 2D Gaussian Splatting
• Ranked Activation Shift for Post-hoc Out-of-Distribution Detection
• SDSA: Shallow-Deep Squeezing Adapter for Vision-Language Models
• OneHSI: A Unified Hyperspectral Foundation Model with Physical Consistency
• CapFrame: Text-Instructed Viewpoint Grounding in 3D Gaussian Scenes via Geometric Pseudo Labels
• WiFlow: Estimating Optical Flow using WiFi Channel State Information
• Dynamic Cluster Data Sampling for Efficient and Long-Tail-Aware Vision-Language Pre-training
• CASA: Cross-Attention over Self-Attention for Efficient Vision-Language Fusion
• GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens
• Concept-as-Tree: A Controllable Synthetic Data Framework Makes Stronger Personalized VLMs
• Gradient sparsity regularization for training unlearning-compatible models
• Where to Look Matters: Learning Influential Views for VLM-based 3D Visual Grounding
• The Cost of Reasoning: Chain-of-Thought Induces Overconfidence in Vision-Language Models
• DP-BOA: Dirichlet-Process Birth-or-Assign for On-the-Fly Category Discovery
• Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views
• Racing in Volume with Flow Ensembles
• EAGS: Error-Aware Gaussian Splatting with Dual-Confidence-Guided Modeling for Uncalibrated Driving Scenes
• AIMold: An Autonomous AI-based Pipeline for Complex Mold Design
• LiteMatch: Lightweight Zero-Shot Stereo Matching via Cost Volume Stabilization
• Towards Robustness against Typographic Attack with Training-free Concept Localization
• AGE: Agentic Gaussian Editing in 3D Scenarios
• VISOR++ : VISUAL INPUT BASED STEERING FOR LARGE VISION LANGUAGE MODELS
• Cross-View Yaw Estimation in Location Uncertainty with Line-Aligning Yaw Scoring
• ReGen3D: Generalizable Unified Representation Learning for 3D Understanding
• GaussianLens: Localized High-Resolution Reconstruction via On-Demand Gaussian Densification
• Anchored, Not Graded: How Vision-Language Models Fail at Slant-from-Texture Perception
• MMBU: A Massive Multi-modal Biomedical Understanding Benchmark to Probe the Perception Capabilities of Vision-Language Models
• From Perspective to Fisheye Depth Estimation and Open-Vocabulary Segmentation
• RayRoPE: Projective Ray Positional Encoding for Multi-view Attention
• PointGT: Simultaneous Geometric and Textural Editing for Point-Based Representations
• P-CORE: Self-Supervised Surface Consistency for Point-Based Neural Editing
• CVSBench: A Comprehensive Benchmark for Cross-view Spatial Reasoning and Dreaming
• Large-Scale Light Field Synthesis from Videos Enables Geometrically Consistent Bokeh Editing
• GAINS: Gaussian-based Inverse Rendering from Sparse Multi-View Captures
• DreamWorld: Geometry-Grounded Video Diffusion for 3D-Consistent World Modeling
• The Sterkfontein Caves Dataset: A Novel View Rendering Challenge from the Cradle of Humankind
• Read or Ignore? A Unified Benchmark for Typographic-Attack Robustness and Text Recognition in Vision-Language Models
• ReShift: Aha-Moment-Driven Reasoning-Level Backdoor Attacks on Vision–Language Models
• LiDAR-EVS: Enhance Extrapolated View Synthesis for 3D Gaussian Splatting with Pseudo-LiDAR Supervision
• UniFusion: Sparse-View 4D Reconstruction via Unified Spatio-temporal Depth Alignment
• Geometry Grounding: Elevating Blind Distortion Correction with 3D Structural Priors
• Relaxed Rigidity with Ray-based Grouping for Dynamic Gaussian Splatting
• WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images
• Generalized Biomedicine Discovery
• MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics
• Stabilizing Deep Reconstruction Operators with Contractive Anchoring
• GEO-Detective: Unveiling Location Privacy Risks in Images with LLM Agents
• 3D Gaussian Texture for Real-time Mesoscale Appearance Synthesis and Rendering
• Towards More Efficient Decoding for Autoregressive Vision-language-action Models
• SOMA: From Surface Observations to Muscle Anatomy
• FLEG: Feed-Forward Language Embedded Gaussian Splatting from Any Views via Compact Semantic Representation
• BLASt3R: Bundle Adjustment of Any Image Set with Multi-View Matching and Monocular priors
• RaysUp: Ultra-light Universal Feature Upsampling via Geometry-Aware Ray Representation
• EmbedCopilot: Evaluating Vision-Language Models for Hardware-Aware Embedded System Development
• Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations
• Off the Planckian Locus: Using 2D Chromaticity to Improve In-Camera Color
• REALM: An RGB and Event Aligned Latent Manifold for Cross-Modal Perception
• Linear Scaling Video VLMs for Long Video Understanding
• Don’t Teach Instability, Teach Robustness: Selective Sensitivity Gating for Adversarial Robust Distillation
• Small Vision-Language Models are Smart Compressors for Long Video Understanding
• MG-RWKV: Multi-Grained Context-Aware RWKV for Temporal Forgery Localization
• MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning
• Urban Boundaries, Social Barriers: A Benchmark and Vision-Centric Framework for Mapping Gated Communities and Equity Implications
• LineGraph2Road: Structural Graph Reasoning on Line Graphs for Road Network Extraction
• Rethinking Temporal Modeling in Visual Object Tracking via Decoupled Auxiliary Supervision
• Objects as Audio-Visual Modal Sound Fields
• Distribution-Alignment Bridge for Uncertainty-Aware Text-to-Video Retrieval
• HorizonRelight: Relighting Long-horizon Videos Consistently via Diffusion Transformers
• One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models
• FeatTracker: Short- and Long-Range Temporal Feature Consistency for Robust Underwater Object Tracking
• MoCA3D: Monocular 3D Bounding Box Prediction in the Image Plane
• REDistill: Robust Estimator Distillation for Balancing Robustness and Efficiency
• Q-TriM: Question-Guided Tri-Modal Attention for Audio–Visual Question Answering
• GTR: Guide-Then-Refine Token Compression for Training-Free Acceleration of Video-LLMs
• From Script to Shot: A Benchmark for Grounding Screenplays in Movies
• Bayesian Self-Attention with Local Pixel Correlations for Lightweight Denoising Transformers
• Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation
• 2D Features Are All You Need for 3D Shape Understanding
• LINA: Learning INterventions Adaptively for Physical Alignment and Counterfactual Generation in Diffusion Models
• SFDATrack: Generalized Source-Free Domain Adaptive Tracking Under Adverse Weather Conditions
• SMART: When is it Actually Worth Expanding a Speculative Tree?
• Breaking High Confidence: Practical Face Impersonation under High-Security Thresholds
• DeRA: Decoupled Representation Alignment for Video Tokenization
• RainODE: Continuous-Time Precipitation Forecasting with Latent Neural ODEs
• ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding
• Actor as Its Own Critic: Unifying Region Understanding and Localization via CycleGRPO
• Demystifing Video Reasoning
• Different Changes Require Different Reasoning: Change-Type-Specialized Experts for Robust Change Captioning
• ID-LoRA: Identity-Driven Audio-Video Personalization with In-Context LoRA
• Pushing the Limits of High-Resolution Weather Forecasting through Data Scaling
• TopoAgent: An Agentic Framework for Automated Topology Learning in Medical Imaging
• XPos3R: Cross-Modal Transformer for Intraoperative 2D/3D Registration
• Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs
• GryphOne: Symbol-Aware Masked Diffusion for Structural Refinement in Offline Handwritten Mathematical Expression Recognition
• TR-MoE: Temporal Reliability-Aware Mixture-of-Experts for Robust Tracking
• SlowBA: An efficiency backdoor attack towards VLM-based GUI agents
• Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench
• Accelerating Text-to-Video Generation with Calibrated Sparse Attention
• FreqPhys: Repurposing Implicit Physiological Frequency Prior for Robust Remote Photoplethysmography
• Learning from Adversity: Semantic-Aware Mask Refinement through Adversarial Perturbation
• MedSPOT: A Workflow-Aware Sequential Grounding Benchmark for Clinical GUI
• IDeaL: Data-Free Multi-Teacher Distillation via Improved Dead Leaves
• Weight-Space Mixture-of-Experts for Implicit Neural Representation Classification
• TopoGAT: Plug-and-Play Topological Graph Attention for Fine-Grained 3D Segmentation
• From Multi-Resolution Cells to Gigapixel Whole Slide Images Foundation Model for Computational Pathology
• VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting
• Task-driven Processing with Coarse-to-Fine Glimpse-based Active Perception
• Pistachio: Towards Synthetic, Balanced, and Long-Form Video Anomaly Benchmarks
• Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention
• Remembering Across Blocks: Topology-Conditioned Block-Progressive Memory for Skeleton-Based Action Recognition
• CLDefocus: Physically Grounded Compound-Lens Defocus Blur Synthesis
• GEAR-Seg: A Grounded Explainable Agent for Reasoning Segmentation and Data Engine
• Self-Evolving MCP-GUI Agents via Automated Environment Generation and Experience Learning
• CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts
• Reasoning with Memory: A Temporal Granularity-Adaptive Framework for Training-Free Long Video Understanding
• NanoVSR: Towards Real-Time Video Super-Resolution on Edge Devices
• Memory-Supported Synergistic Adaptation for Training-Free Test-Time Medical Image Segmentation
• Spectral Gradient Orthogonalization Improves Differentially Private Training at Scale
• Fidelity- and Perception-Aware Local Implicit Attention for Arbitrary-Scale Image Super-Resolution
• HSFM: Hard-Set-Guided Feature-Space Meta-Learning for Robust Classification under Spurious Correlations
• Improving Knowledge Distillation Under Unknown Covariate Shift Through Confidence-Guided Data Augmentation
• Implicit Neural Representation Facilitates Unified Universal Vision Encoding
• AlphaRad: Grounded Zero-Shot Classification in Chest Radiology via α-Corrected Binary Cross Entropy and Factorized Latent Supervision
• Spectral Gating via Damped Oscillations for Adaptive Implicit Neural Representations
• Defending from GeoLocalization through Adversarial Road Trips
• ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling
• PeCA: Palette Context Assisted Inference for Test-Time Paint-Bucket Colourisation on Animation Videos
• SDUM: A Scalable Deep Unrolled Model for Universal Cardiac MRI Reconstruction
• Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection
• RobustRDP: Advancing Reaction Diagram Parsing via Synthetic-to-Real Data Scaling and Robustness-Oriented Training
• Clue Matters: Empower Video Reasoning with Brain-Inspired Latent Clue Learning
• Less Tokens, Better Forecasts: Sparse Residual Routing for Efficient Weather Prediction
• Ring Forcing: Towards Precise Long-Term Memory for Autoregressive Video Diffusion
• Finding Highlight Images In Your Albums:From Benchmark To MLLM
• SHIFT: Motion Alignment in Video Diffusion Models with Adversarial Hybrid Fine-Tuning
• IConE: Batch Independent Collapse Prevention for Self-Supervised Representation Learning
• Robustness Emerges Early in Training Dynamics, but Is Not Preserved
• ClearText-Video: A Large-Scale Text-Centric Video Dataset Bridging Video Restoration and Scene-Text Enhancement
• Geometry-Anchored Transport Framework for Exemplar-Free Class-Incremental Learning
• DiffVP:Differential Visual Semantic Prompting for LLM-Based CT Report Generation
• EcoVideo: Entropy-Orchestrated Video Generation Paradigm in Cloud-Edge Dynamics
• Puppet-CNN: Continuous Parameter Dynamics for Input-Adaptive Convolutional Networks
• ProtoMappingNet: Interpretable Hierarchical Prototypes through Relational Prototype Mappings
• C3ASD: Multi-Level Consistency-Driven Representation Learning for Robust Active Speaker Detection
• Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability
• WARP: Wide Attention with Rich Projections for Image Super-Resolution
• LoT-Pass: Long-term-robust Image Watermarking for Image to Video Generation
• Explainability-aware Frustum Attack: Exposing Structural Vulnerabilities in LiDAR-Based 3D Object Detectors
• Step-by-Step Video-to-Audio Synthesis via Negative Audio Guidance
• QSVideo: Query-Conditioned Semantic Temporal Retrieval for Video Understanding
• Open-Vocabulary Long Term Action Anticipation
• Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models
• Reconstructing Dense Depth of Dark Scenes with Sparse LiDAR, Noisy Events, and Blurry RGB
• Multi-Channel Uncertainty-Weighted Score Matching for Conditional Diffusion in Medical UDA
• Calibrated Harmonic Overlaid Implicit Neural Representations for Multi-Dimensional Data
• STVFocus: Query-guided Spatio-Temporal Visual Focusing for Video LLMs
• Spectral-Aware Analytic Class-Incremental Learning for Long-Tailed Distributions
• SWAN: World-Aware Adaptive Multimodal Networks for Runtime Variations
• EgoCogNav: Cognition-aware Human Egocentric Navigation
• RoME: Robust Mixture of Low-Rank Experts against Multiple Adversarial Perturbations
• PanoSAM2: Lightweight Distortion- and Memory-aware Adaptions of SAM2 for 360 Video Object Segmentation
• EgoPHI: Estimating 3D Hand-Object Contact and Force from Egocentric Vision
• 3D Field of Junctions: A Noise-Robust, Training-Free Structural Prior for Volumetric Inverse Problems
• EventSTU: Event-Guided Efficient Spatio-Temporal Understanding for Video-LLMs
• NGPS: Structure-Preserving Self-Supervised Denoising via Neighbor-Guided Patch Sampling
• Multi-Block-Attention-based Color Constancy
• RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks
• SurvMILKD: A Weakly Supervised Survival Analysis Framework for Multi-Teacher Knowledge Distillation using Pathology Foundation Models
• A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP
• PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning
• Topology-Weighted Effective Rank: A Zero-Cost Proxy for Training Dynamics Stability in Neural Architecture Search
• LumiDepth: Stable Monocular Depth in Multi-Illumination Scenes
• Fast and Flexible Robustness Certificates for Semantic Segmentation
• Concept-to-Pixel: Prompt-Free Universal Medical Image Segmentation
• SignBind-LLM: Multi-Stage Modality Fusion for Sign Language Translation
• HIDA: A Human-Intuition-Guided Depth-Aware Framework for Zero-Shot Amodal Segmentation
• ProLaViT: Learning Progressive Latent Visual Thoughts in Structured Latent Space
• iSyncTab: Learning Cross-Modal Feature Sequencing for Image-Tabular Data via Neural Synchrony
• Hybrid Event–Frame Sensors: Modeling, Calibration, and Simulation
• When the Teacher Has More Bits: Self-Teacher Latent Distillation for Learned Image Compression
• Human-Level Accuracy, Non-Human Strategies: Revealing Model-Human Divergence in Video Physical Reasoning
• SIGNET: Motion-Level Knowledge Transfer for Cross-Language Sign Language Translation
• FastSTAR: Spatiotemporal Token Pruning for Efficient Autoregressive Video Synthesis
• Quantile‑Adaptive Temperature Scaling for Confidence Calibration
• HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising
• RotateAttention : RoPE-Aware Rotation and Range Rectification for INT4 Quantized Attention in Video Generation
• D-VLAM: Differential Vision and Language Mixing for Rehearsal Free Continual Learning
• CUST : Clustered Unit-level Similarity Transformer for Lightweight Image Super-Resolution
• Mimicking Radiologists: A Coarse-to-Fine Framework with Structural Sparse Tokens for Dual-LLM Computed Tomography Report Generation
• Don't Let the Video Speak: Audio-Contrastive Preference Optimization for Audio-visual Language Models
• DART: Difficulty-Adaptive Routing for Zero-Shot Video Temporal Grounding
• Beyond Time Shifts: Adapting Omni-LLM as a Reference-Free Evaluator for Generative Audio-Visual Models
• Break Visual-Linguistic Asymmetry: Unleashing VLM's Cross-Modal Potential for General Face Forgery Detection
• Video-Oasis: Rethinking Evaluation of Video Understanding
• SpecEyes: Accelerating Agentic Multimodal LLM via Speculative Planning and Perception
• Leveraging Dark Knowledge for Intrinsic Multimodal Out-of-Distribution Detection
• Region-Aware Multimodal Large Language Model via SlowFast Tokenization and Pseudo-Mask Guidance for 3D CT Report Generation
• MorphJEPA: Morphology-Aware Latent Prediction for Hyperspectral Images
• ProAct: Agentic Lookahead in Interactive Environments
• Gen2Balance: Generative Balancing for Long-Tailed Video Action Recognition
• Hyper-Network Neural Functional Maps for Unsupervised Robust 3D Shape Matching
• AffoGato: Open-Vocabulary Affordance Grounding with Automated Data Generation at Scale
• Progression as Latent Drift: Generative Forecasting of Slow-Evolving Pathologies
• AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation
• SVI360: Spherical Video Interpolation
• MediRound: Multi-Round Entity-Level Reasoning Segmentation in Medical Images
• SPHERE: From MRI Sampling Mechanisms to Spatial Priors for Generalizable Brain Tumor Segmentation
• DiffUE: Enhancing Utility-Unlearnability Trade-off of Unlearnable Examples via Diffusion Autoencoders
• Reasoning-Guided Part-Level Visual Grounding via Reinforcement Learning
• SAM-MT: Real-Time Interactive Multi-Target Video Segmentation
• Reflect-R1: Evidence-Driven Reflection for Self-Correction in Long Video Understanding
• DART: Deformable Adaptive Reasoning with Temporal Queries for Online Skeleton-Based Action Recognition
• Gaussian Belief Propagation Network for Depth Completion
• Frames2Residual: Spatiotemporal Decoupling for Self-Supervised Video Denoising
• MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learning
• Closing the Capacity–Convergence Gap: Globally Optimal Configuration of Implicit Neural Representations
• Audio-Visual Continual Test-Time Adaptation without Forgetting
• HAS: Highlight-guided Attention Steering for Multimodal LLM Video Summarization
• No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairs
• Proximity-Constrained Counterfactual Decoding for Hallucination-Robust Medical VQA
• Beyond Random Sampling: Distribution-Aware Alignment for Semi-Supervised Medical Image Segmentation
• Rethinking Training and Inference for Trajectory Forecasting: Linking Winner-Take-All back to GMMs
• PolarAPP: Beyond Polarization Demosaicking for Polarimetric Applications
• Weight Feedback Computes the Exact Jacobian Transpose in Modern Deep Networks
• Structural Assessment for Understanding and Guiding Dataset Distillation in Discrete Token Space
• Comprehensive language–image pre-training for 3D medical image understanding
• BackTranslation2.0 - A Linguistically Motivated Metric to Assess Sign Language Production
• Pol-CACTI: A System and dataset forHigh-Speed Polarized Video Compressive Imaging
• MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution
• Video-HolmesV2: Can MLLMs Reason with Spatio-Temporal Audio-Visual Evidence in Long Videos?
• Adapting MLLMs for Nuanced Video Retrieval
• AracNet: Revealing Debiasing Signals across Layers with Shallow Monitors
• Conversational Human Audio-visual Talking Dialogue Generation
• Guiding the Blind: Generalizing GUI Agents to Unseen Websites via Multimodal Tutorials
• Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning
• When Higher Order Hurts: Pre-Asymptotic Order Collapse in Generative ODE Sampling — A Theory of Discretization–Learning Interaction
• Exposing Implicit Vulnerabilities in Text-to-Image Models via Adversarial Agentic Probing
• MOOZY: A Patient-First Foundation Model for Computational Pathology
• RPM-Distill: Physiology-guided Adaptive Cross-modal Distillation for Robust Remote Physiological Measurement
• DRIFT: Difficulty-aware Rectified Flows for Through-plane MRI Super-Resolution
• From Minimal Clinical Prompts to 3D: Spacing-Aware Prompt Propagation for Multimodal Prostate Lesion Segmentation in bpMRI
• Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussions
• GeoCFM: Positive-Only Conditional Flow Matching for Mineral Occurrence Sampling
• MegaFlow: Zero-Shot Large Displacement Optical Flow
• MMControl: Unified Multi-Modal Control for Joint Audio-Video Generation
• EgoPolice: A Benchmark for Egocentric Video Understanding in High-Stakes Police Body-Worn Camera Footage
• Cambrian-P: Pose-Grounded Video Understanding
• MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding
• GeoBrowse: A Geolocation Benchmark for Agentic Tool Use with Expert-Annotated Reasoning Traces
• Continuous Heart Rate Variability Estimation from Egocentric Systems for Skill Assessment
• Transferability Between Understanding and Generation in Unified Multimodal Models
• UC-VLM: Consistency-Driven Learning for AI-Generated Image Detection with Vision-Language Large Models
• Learning Consistent Temporal Grounding between Related Tasks in Sports Coaching
• Histopathology Multi-modal Embedding for Pathology Composed Retrieval
• Towards Trustworthy Dermatology MLLMs: A Benchmark and Multimodal Evaluator for Diagnostic Narratives
• Mitigating Modality and Language-Style Gaps for Zero-Shot Video Moment Retrieval
• Stokes-Informed Diffusion for Robust Linear Polarization Estimation
• VesselTok: Tokenizing Vessel-like 3D Biomedical Graph Representations for Reconstruction and Generation
• Look But Don't Touch with Sparse Autoencoders for Unlearning in Diffusion Models
• DeLux: Cross-Modal Local Artifact Restoration in Video Using Neuromorphic Data
• Raw-JPEG Adapter: Efficient Raw Image Compression with JPEG
• Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification
• OCTOPUS: Multi‑Agentic Universal Compositional Visual Retrieval
• Structured SIR: Efficient and Expressive Importance-Weighted Inference for High-Dimensional Image Registration
• MedCAGD: Context-Aware Gated Decoder for Robust Medical Image Segmentation
• Generating Multi-view Adversarial Examples for Visual Geometry Grounded Transformer
• RIGS: Radar-Informed Gaussian Splatting for Uncertainty-Aware 3D Occupancy and Motion Prediction
• STARLINC: Satellite Trail Artifact Removal using Inter-Frame Correlation
• REVA-PO: Stabilizing Reinforcement Learning for Chest X-ray Report Generation
• Gaussian Volumetric Representation for Efficient Shear–Warp Visualization
• BiCE-HG: A Bi-Conditional Egocentric Hand Gesture Dataset for Intelligent Reality Systems
• Learn to Rank: Visual Attribution by Learning Importance Ranking
• Parsimonious Flow Matching for Efficient Image Generation
• Moonstone: A Multimodal Foundation Model and Benchmark for Lunar Remote Sensing
• TRAM: Finetuning-Free Test-Time Adaptation for Generalized Face Anti-Spoofing with Only a Few Bonafide Samples
• From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for Video Generative Models
• NeuralDMD: Interpretable Untrained Neural Network for Imaging from Sparse and Noisy Observations
• LIIFusion: Coarse-to-fine Framework for Generative MEF via Implicit Neural Representation
• LogicIR: Logic Gate Networks for Image Restoration
• Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents
• Escaping the Low-Frequency Bias: Adversarial Frequency Perturbation for Generalisable Gaze Estimation
• Fast and Accurate Image Restoration with Rank Enhanced Linear Attention
• ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion
• Progressive and Localized Super-Resolution of 3D Objects via Localized Latent Voxel Diffusion
• Test Time Training for Long Videos via Frame Forgetting Network
• Prior-Conditioned Gaussian Discriminants for Generalizable AI-generated Image Detection
• Fine-Grained Text-to-Video Retrieval for Camera-Trap Data
• Benchmarking Dynamic Affective Reasoning: A Viewer-Centric Video Emotion Dataset
• Spatiotemporal Flux Probing for Single-Photon Videography
• If It's Not Efficient, It's Not Usable: Real-Time OOD Detection with Latent De-Biasing and High-Quality Negative Samples
• ECoSim: Data Efficient Fine-Tuning for Controllable Traffic Simulation
• Towards Reliable Multi-Label Classification via Conditional Dependency Modeling
• Neuromorphic X-ray Computed Tomography
• 340 FPS Reflection-free Video from Spikes Modulated by a Rapidly Rotating Polarizer
• GeoDetect: Geometric Adversarial Detection for VLPs
• PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference
• MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing
• Surprise Forcing: What to Remember, When to Skip in Long Video Generation
• Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance
• Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors
• EgoVITA: Learning to Plan and Verify for Egocentric Video Reasoning
• Whence the Voice? Self-supervised Dual-source Audio-Visual Localisation via Selective Convergence
• Beyond Script Family Boundaries: Towards Unified Open-Set Scene Text Recognition
• Adaptive Latent Trajectory Anchoring for Action Segmentation Dataset Condensation
• Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction
• ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device
• Trajectory-Level Continuous Action Representation for Robotic Manipulation
• Pay Attention to Attention Distribution: A New Local Lipschitz Bound for Transformers
• Unified Video Dense Prediction from Disjoint Data
• Bridging Theory and Practice in Source-Free Domain Adaptation via Adversarial Proxy Perturbation
• Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos
• Keep Your Friends Close, and the Right Neighbours Closer: Disaster-Conditioned Kernel-Regularized Graph Attention for Building Damage Classification
• FedLAS: Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration
• Fully Rotation-Equivariant Spectral-Spatial Learning for Multispectral Object Detection
• JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching
• WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching
• Structured-Noise Masked Modeling for Video, Audio and Beyond
• Seeing What Matters: Lesion-Aware High-Resolution Patch Discovery and Fusion for Chest X-ray Report Generation
• Beyond Sequential Distance: Inter-Modal Distance Invariant Position Encoding
• CritiqueDriveVLM: From Verifier-Guided Reinforcement Learning to Latent Thought Distillation for Autonomous Driving
• Scaling Laws for Black-box Adversarial Attacks
• Synesthesia via Direct Latent Augmentation: Bypassing the Decode-Encode Loop for Cross-Modal Distillation
• Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning
• TaxoMIL: Taxonomy-Constrained Learning for Hierarchical Whole Slide Image Analysis
• Precise Video-to-Audio Generation with Cross-Modal Alignment in Latent Space
• Atlas is Your Perfect Context: One-Shot Customization for Generalizable Foundational Medical Image Segmentation
• Improving Adversarial Robustness by Mitigating Instability through Relearning
• STAC: Selective Spatiotemporal Aggregation and Compression for Video Reasoning Segmentation
• EgoEverything: A Benchmark for Human Behavior–Inspired Long-Context Egocentric Video Understanding in AR Environment
• Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding
• Masked BRep Autoencoder via Hierarchical Graph Transformer
• UniTemp: Unlocking Video Generation in Any Temporal Order via Autoregressive Distillation
• Compact and Structurally Transparent Cervical Cytology with Geometry-Driven Features and Closed-Form Attention
• Event-based Sparse-view Background-Oriented Schlieren Tomography
• Semantic-Anchored Evidential Fusion for Domain-Robust Whole-Slide Survival Analysis
• On the Reliability of Cue Conflict and Beyond
• VICAL: Vicinal Consistency Alignment for Long-Tailed Visual Recognition
• MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment
• Flexible Control of 3D CT Generation via Text and Semantically-Defined Segmentation Prompts
• Simple Filtering Improves Masked Autoencoders
• Score-Based Matching with Target Guidance for Cryo-EM Denoising
• Data Circuit Breaker: Identifying Training, Test, and Generated Data in Image Generative Models
• Proteus: Model Leakage-Induced Adversarial Attack in Federated Learning
• Natural Language Camera Movement Understanding
• MomentSeg: Moment-Centric Sampling for Enhanced Referring Video Object Segmentation
• MCPNet:Masked Coordinate Pooling-based Attention Network for Medical Landmark Detection
• OnPoint: Offline-to-Online Multi-Level Distillation for Point-Supervised Online Temporal Action Localization
• Learning to Mask: Cross-Modal Noise Modulation for Hallucination Mitigation in Multi-modal Large Language Models
• EvDiff: High Quality Video with an Event Camera
• Resolution-Agnostic Neural Operators for Multi-Rate Sparse-View CT
• InterEdit: Navigating Text-Guided Multi-Human 3D Motion Editing
• Dual-Output Multi-Exposure HDR Reconstruction via SDR Fusion and Gain Map Inverse Tone Mapping
• Integrated Forward–Inverse Network for Reconstruction for Lensless Image Reconstruction
• CLARITY: Medical World Model for Guiding Treatment Decisions by Simulating Context-Aware Disease Trajectories in Latent Space
• Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks
• S3-Prune: Stability-Aware Token Budgeting for Long-Form Video-Language Models
• On the Plasticity Collapse in Continual Machine Unlearning
• PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion
• Zero-shot Depth from Defocus
• Foundation-Guided Representation Alignment for Multimodal Medical Image Registration
• EventVGGT: Exploring Cross-Modal Distillation for Consistent Event-based Depth Estimation
• VersatileMotion: A Unified Framework for Motion Synthesis and Comprehension
• InterCMDM: Block-Causal Diffusion for Autoregressive Human Interaction Generation
• Do Multimodal LLMs Understand Intraoral Dental Data? Dataset, Platform, and Baselines
• Keep-or-Drop? Adaptive Tokenizer for Compact Video Representation
• Φeat: Physically-Grounded Material Feature Representation
• Adversarial Attack and Disturbance Detection by Hadamard-Coded Output Representations for Object Detection and Semantic Segmentation
• Physics-Guided Deep Learning for Linear Mueller Matrix Acquisition
• MedRepBench: Benchmarking Structured Understanding of Medical Report Images
• SHINE-PPG: Non-Lambertian Intrinsic Decomposition for Illumination-Robust rPPG
• SV-TAD: Native Sparse Convolutions for Efficient Temporal Action Detection
• iMED: A Multi-Endoscope Dataset for Surgical 3D Perception
• Implicit Neural Representation for Spherical Harmonics Reconstruction of Motion-Corrupted Fetal Diffusion MRI
• LongEgoRefer: A Benchmark for Long-Form Egocentric Video Referring Expression Comprehension
• OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure
• Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos
• FeVOS: Foresight Expression Video Object Segmentation
• Learning Probabilistic Prompt for Continual Learning
• OneVAE: Joint Discrete and Continuous Optimization Helps Discrete Video VAE Train Better
• Revisiting Weakly-Supervised Video Scene Graph Generation via Pair Affinity Learning
• Safe Responses Matter: Output-Aware Safety Guardrail Mitigate Over-Refusal in MLLMs
• Denoised Variance-Based Pruning with Optimal Brain Bias Compensation
• Temporal and Cross-modal Alignment for Enhanced Audiovisual Video Captioning
• SIGNER: Temporally Grounded Sign Language Generation via Time-Resolved Conditioning
• SeekFlow: Synergizing Radiology and Pathology Foundation Models for Precision Oncology via Knowledge-Guided Evidence Flow
• Adaptive Neural Dynamics for Robust Geometric LiDAR-Inertial State Estimation on UAVs
• A Benchmark and Multi-Agent System for Instruction-driven Cinematic Video Compilation
• Learning with Bilevel-Minimax Optimization for Efficient and Reliable Transfer Attacks
• MArFE: Multi-Contrast MRI Arbitrary Scale Super-Resolution with Fourier Enhancement
• Multi-modal Knowledge Preserving Adapter for Embedding Backward Compatibility
• STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding
• ActionPlan: Future-Aware Streaming Motion Synthesis via Frame-Level Action Planning
• StoryTeller: Training-Free Narrative Grounding for Long-Form Audio Description
• Conditional Flow Matching for Visually-Guided Acoustic Highlighting
• SENTRY: SAM2-Enhanced Neighbor-Aware and Temporally Reasoned Memory for Visual Tracking
• Guardrail-Agnostic Societal Bias Evaluation in Large Vision-Language Models
• CCFM: Collision-Constrained Flow Matching for Safety-Critical Scenario Generation
• Structured Hyperedge Adaptation for Parameter-Efficient Fine-Tuning of Vision Transformers
• SIMSplat: Language-Aligned 4D Gaussian Splatting for Driving Scenario Generation
• Pro-Pose: Unpaired Full-Body Portrait Synthesis via Canonical UV Maps
• MotionAnymesh: Physics-Grounded Articulation for Simulation-Ready Digital Twins
• Prosthesis-Aware 3D Human Pose Estimation: A Dataset and Benchmark for RSP Users
• UniDynamics: Event-RGB Fusion for Unified Future 4D Dynamic Scene Generation
• Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations
• Lost in the Tail: Addressing Geographic Imbalance in Urban Visual Place Recognition
• AHOY! Animatable Humans under Occlusion from YouTube Videos with Gaussian Splatting and Video Diffusion Priors
• UrbanAlign: Post-hoc Semantic Calibration for VLM-Human Preference Alignment
• A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models
• DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models
• 360Anything: Geometry-Free Lifting of Images and Videos to 360°
• STANCE: Controllable Video Generation for Structured Dynamics via Sparse-To-dense ANChored Encoding
• PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models
• LibraGen: Playing a Balance Game in Subject-Driven Video Generation
• FlexiAvatar: Unified 3D Gaussian Human Avatars Under Arbitrary Body Visibility
• HOIMask: Towards Generative Masked Modeling for Human Object Interaction Generation
• RegHead: Non-Humanoid Head Blendshapes via Feed-Forward Registration
• InfiniteDance: Scalable 3D Dance Generation Towards in-the-wild Generalization
• ReinDriveGen: Reinforcement Post-Training for Out-of-Distribution Driving Scene Generation
• TaskTok: Delving into Task Tokens for Task-driven Image Restoration
• Roam2Room: A Unified Floorplan-to-Furnished Framework for Controllable Indoor Scene Generation
• Learning to Generate Rigid Body Interactions with Video Diffusion Models
• CS-TTA: Preserving Concept Sensitivity in Test-Time Adaptation
• Rethinking Detection Calibration: A Coordinate Perspective
• EgoExoMoCap: Distributed Human Motion Capture via Ego- and Exocentric Body Tracking from Head-Mounted Devices
• Self-supervised Garment Dynamics with Persistent Wrinkles
• Recognizing Co-Speech Gestures in-the-Wild
• SemGAN: A Semantic and Hierarchical Adversarial Network for 3D Human Pose Estimation
• Make Geometry Matter for Spatial Reasoning
• Composing Driving Worlds through Disentangled Control for Adversarial Scenario Generation
• SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence
• OVGGT: O(1) Constant-Cost Streaming Visual Geometry Transformer
• ControlHair: Synergizing Physics Simulator and Video Diffusion for Controllable Dynamic Hair Rendering
• Axolotl3D: a Unified Framework for Faithful 3D Shape Completion
• HiChor: Hierarchical Choreography Generation from Pop Music with Choreographic Primitives
• OpenCVL: An Open, Diverse, and Large-Scale Dataset for Fine-Grained Cross-View Localization
• HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding
• Rolling Shutter Relative Pose Estimation Made Practical
• Training-free Controllable Motion Generation under Heterogeneous Constraints
• PolyLayout: Multi-room Manhattan Layout Estimation
• LaVPR: Benchmarking Language and Vision for Place Recognition
• GimbalDiffusion: Gravity-Aware Camera Control for Video Generation
• Egocentric World Model for Photorealistic Hand Object Interaction Synthesis
• Attention is Case-Sensitive
• Honey, I Shrunk the Arc de Triomphe!
• ClusterStyle: Modeling Intra-Style Diversity with Prototypical Clustering for Stylized Motion Generation
• EMOTE: Expressive Motion and Shape Disentanglement for Human Animation
• Following Motion for Sequential Modeling in Video Frame Interpolation
• Estimating Velocity and Spin of Spherical Objects from Rolling-Shutter Image(s)
• Odoriko: A Shape-Aware Multimodal Diffusion Framework for Human Motion
• OmniColor: A Unified Framework for Multi-modal Lineart Colorization
• Towards Robust Driving Perception: A Flexible Scale-Driven Family for Self-Supervised Monocular Depth Estimation
• 4D-VGGT: A SpatioTemporal Foundation Model for Dynamic Scene Geometry Estimation
• From Drop-off to Recovery: A Mechanistic Analysis of Segmentation in MLLMs
• Moiré Video Authentication: A Physical Signature Against AI Video Generation
• Semantic-Aware, Physics-Informed, Geometry-Grounded Weather Synthesis
• Tuning-free Visual Effect Transfer across Videos
• MotionDreamer: Universal Skeletal Motion Generation for 3D Rigged Shapes
• Vision-TTT: Efficient and Expressive Visual Representation Learning with Test-Time Training
• PhysPO: Physics-Aware Local Preference Optimization for Physically Consistent Video Diffusion
• InterPet4D: A Multimodal 4D Human-Pet Interaction Dataset for Pet Motion Generation
• MoBa-GS: Learning a Spatially-Varying Motion Basis over a Dynamic Canonical Space for 4D Reconstruction
• Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting
• Music-to-Dance Generation via Atomic Movements
• Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning
• HairWeaver: Few-Shot Photorealistic Hair Motion Synthesis with Sim-to-Real Guided Video Diffusion
• Look Less, Think Faster: Joint Token-Compute Adaptation for Multimodal LLMs
• ID-PreFeR: ID-Preserving Face Restoration with Mixed Data Quality
• Syn4D: A Multiview Synthetic 4D Dataset
• AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labels
• ARGENT: Adaptive Hierarchical Image-Text Representations
• OmniPoser: Flexible Human Motion Recovery in the Wild with Masked Flow Matching
• 3D FaceShell: Attribute Transfer in 3D Face Avatars as a VLM Defense Mechanism
• Unwarping the Lens: A Physics-Grounded Approach to Video Glasses Removal
• Reconstructing Humans and Objects in Interaction using Large Reconstruction Models
• DnA: Denoising Attention for Visual Tasks
• BLOB-Q: Boosting Low Bit ViT Quantization via Global Optimization on Model Distortion
• RADmesh: Remesh-Aware Mesh Deformation
• Target-Bench: Can Video World Models Achieve Mapless Path Planning with Semantic Targets?
• Seeing Fast and Slow: Learning the Flow of Time in Videos
• ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos
• PhysConvex: Physics-Informed Dynamic Convex Fields for Reconstruction and Simulation
• Unsupervised Semantic Segmentation Facilitates Model Understanding
• SKEL-CF: Coarse-to-Fine Biomechanical Skeleton and Surface Mesh Recovery
• AnyMatch: Supercharging Universal Multi-Modal Image Matching with Large-Scale Single-View Images
• General Self-Calibration with Varying Intrinsics
• StreetForward: Perceiving Dynamic Street with Feedforward Causal Dynamics
• Pointer-CAD v2: Plan-Then-Construct CAD Generation with Dimension-Aware Parametric Precision
• Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flow
• GO-Renderer: Generative Object Rendering with 3D-aware Controllable Video Diffusion Models
• Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective
• Inductive Visual Logic for Few-Shot Out-Of-Distribution Adaptation in VLMs
• Enlightening Photographic Style Transfer with a Self-Supervised Photographic Embedding
• Beyond Inpainting: Unleash 3D Understanding for Stable Camera-Controlled Video Re-rendering
• UniFlow: Zero-Shot LiDAR Scene Flow for Autonomous Driving
• OmniFall: From Staged Through Synthetic to Wild, A Unified Multi-Domain Dataset for Robust Fall Detection
• MLVC: A Multi-platform Learned Video Codec for Real-World Deployment
• ARMS: Anchor–Relational Motion Streaming for Seamless Solo-Social Motion Transitions
• Kilometer-Vision: A New Frontier for Large-Scale Spatial Awareness in VLMs
• On the real-world generalisability of Optical Flow models
• GenLCA: 3D Diffusion for Full-Body Avatars from In-the-Wild Videos
• ConfCtrl: Enabling Precise Camera Control in Video Diffusion via Confidence-Aware Interpolation
• Trajectory-aware Cross-view Geo-Localization with Sequential Observations
• Verifying Cancer Segmentation in Vision Transformers via Internal Concepts
• Mitigating Radar-Inertial Calibration Ambiguities via SO(3) Manifold Steering
• REON-NVS: Real-Time Online Novel-View Synthesis from Sparse-View Videos
• Variational Patch Gating for Training-Free Few-Shot Classification
• PoseImageNet: Pose Estimation for Extensive Classes Based on Rich Structure Prototypes
• Hyperbolic Hierarchical Clustering for Visual Representation Learning
• CameraAnything: Refilming Videos with Arbitrary Camera Control
• ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video
• Delaunay Canopy: Building Wireframe Reconstruction from Airborne LiDAR Point Clouds via Delaunay Graph
• Ray-Path-Aware Virtual Point Removal on 2D Layer-Wise Nearest Point Map
• GRE-Diff: Gaussian Room Embeddings for Structured Layout Diffusion
• TAQ: Static-Deployable Temporal-Aware Quantization for Real-World Video Super-Resolution
• MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control
• RoMa v2: Harder Better Faster Denser Feature Matching
• Social-Mamba: Socially-Aware Trajectory Forecasting with State-Space Models
• Detect by Track: Making Detector-Free Matcher Trackable
• FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model
• E-MOTION: A Dataset for Event-Based Scene Flow Estimation with Independent Moving Objects
• FlowPainter: Inpainting Optical Flow via Confidence-Guided Completion
• GARDEN: Gravity-Aligned Reconstruction of Disentangled ENvironments from RGB images
• FreeFlow: A Bias-free Hierarchical Transformer for Optical Flow Estimation
• Invisible Shortcuts: Why Vision Encoders Know Your Camera
• PhyMAGIC: Physical Motion-Aware Generative Inference with Confidence-guided VLM
• WiFi-JEPA: Self-supervised Learning for WiFi-CSI 3D Human Pose Estimation
• SynFlow: Scaling Up LiDAR Scene Flow Estimation with Synthetic Data
• Mechanistic interventions for explainable digital pathology uncovers adversarial vulnerabilities
• OrthoTrack: Continuous 6-DoF UAV Trajectory Estimation Anchored in Public Orthophotos
• CustomX: Unified Character, Action, and Scene Customization in Video World Models
• DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxies
• TriMotion: Modality-Agnostic Camera Control for Video Generation
• Human-like Object Grouping in Self-supervised Vision Transformers
• Versatile Editing of Video Content, Actions, and Dynamics without Training
• IC-World: In-Context Generation for Shared World Modeling
• Quick ViTs: Speeding up Vision Transformers through Equivariance
• TIDES: Time-Derivative Event Simulation via Deformable Reconstruction
• DisentangledTMR: Privacy-Preserving Skeleton Motion Retargeting via Factorized Transformers
• StoryBlender: Inter-Shot Consistent and Editable 3D Storyboard with Spatial-temporal Dynamics
• SPARC: Scalable Path-Specific Counterfactual Fairness via Causal Conditional Independence
• Physics Question Scene Graph: Fine-grained Evaluation of Physical Plausibility in Text-to-Video Generation
• TETO: Tracking Events with Teacher Observation for Motion Estimation and Frame Interpolation
• Holo360D: A Large-Scale Real-World Dataset with Continuous Trajectories for Advancing Panoramic 3D Reconstruction and Beyond
• SplatCtrlA: Generalizable Single Image to Fully Controllable 3D Avatar
• PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation
• OmniDS: Dual-Stream Context Fusion for Omnidirectional Depth from Fisheye Cameras
• GeCo: Evaluating Geometric Consistency for Video Generation via Motion and Structure
• MASS: Motion-Aligned Selective Scan for Flow-Based Video Frame Interpolation
• LoMa: Local Feature Matching Revisited
• IRIS: A Real-World Benchmark for Inverse Recovery and Identification of Physical Dynamic Systems from Monocular Video
• EgoMAN: Interaction-Structured Reasoning for Egocentric 3D Hand Trajectory Prediction
• Category-Level 3D Correspondence in Camera Space via Morphable Object Priors
• Unveiling Transferability in Trajectory Prediction via Latent Scene Embeddings
• Blind to Position, Biased in Language: Probing Mid-Layer Representational Bias in Vision-Language Encoders for Zero-Shot Language-Grounded Spatial Understanding
• Fast Sam 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recovery
• ObjectForesight: Predicting 3D Object Trajectories from Human Videos
• Leaving the City: A Large-Scale Aerial Dataset for Cross-Season Localization in Unstructured Environments
• Sparsity-Inducing Divergence Losses for Biometric Verification
• ETCH-X: Robustify Expressive Body Fitting to Clothed Humans with Composable Synthetic Data
• Ego-Human Motion Prediction with 3D-Aware LLM
• Sequential Visual Place Recognition: Exploiting Trajectory Priors for Robust Localization
• Circuit-MLLM: Topological Logic-Guided Latent-Space Visual Reasoning for Circuit Schematic Understanding
• VideoSfM: Exploiting Temporal Structure for Video-Based Structure-from-Motion
• Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars
• MotionSplicer: Part-Based Motion Editing for 4D Volumetric Videos
• MMEarth-Bench: Global Model Adaptation via Multimodal Test-Time Training
• Towards Reconfigurable Visual Feature Compression
• Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification
• Audio-Visual Camera Pose Estimation with Passive Scene Sounds and In-the-Wild Video
• NEOMAP: Novel-View Synthesis via Noise Initialization by Manifold Alternating Projection
• Global Graph-Validated Optimization for VLM-based 3D Indoor Scene Generation
• In-Context Sync-LoRA for Portrait Video Editing
• MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction
• CLIMP: Contrastive Language-Image Mamba Pretraining
• InSpace: Structure-Aware 3D Indoor Scene Generation from a Single 360° Image
• InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars
• EmbodiedHead: Real-Time Listening and Speaking Avatar for Conversational Agents
• BeyondMasks: Evaluating Causal and Physical Consistency in Video Object Removal
• Human Mesh Modeling for Anny Body
• Activation Quantization of Vision Encoders Needs Prefixing Registers
• TimeWalker: Personalized Neural Space for Lifelong Head Avatars
• SynHMR: Synergistic Joint-Mesh Modeling for LiDAR-based Human Mesh Reconstruction
• Learning Manifolds in High-D Point Embedding for Anisotropic Surface Approximation from Unstructured Point Clouds
• Mind-to-Face: Neural-Driven Photorealistic Avatar Synthesis via EEG Decoding
• JacobianAvatar: Temporally Consistent Semi-rigid Avatar Reconstruction from a Monocular Video
• PhysRAG: Enhancing Physics-Awareness in Video Generation via Retrieval-Augmented Generation
• PASDiff: Physics-Aware Semantic Guidance for Joint Real-world Low-Light Face Enhancement and Restoration
• On Locality and Length-Generalization in Visual Reasoning
• PLOT: Pseudo-Labeling via Object Tracking for Monocular 3D Object Detection
• SyncVL: Synchronizing Vision ⟷ Language Using Unsupervised Adaptation
• RASA: Disentangled Spatial-Motional Priors for Cross-Identity Character Animation
• EgoGVAE: Ego-body Mesh Reconstruction via Guided Variational Autoencoder
• EgoSim: Egocentric World Simulator for Embodiment Interaction Generation
• CAST3D: Customizing Arbitrary 2D Assets into 3D World
• AutoPhyX: Automatic Text-Condition Physics Property Generation
• Understanding Geometric Representations in Self-Supervised Vision Transformers via Subspace Intervention
• LivingWorld: Interactive 4D World Generation with Environmental Dynamics
• Visible Yet Unrecognizable: Frequency-Selective Facial Privacy via Attention
• Lightweight Online Reinforcement Learning for Block Decomposition of CAD Models
• OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control
• WristMimic: Full-Body Humanoid Control with Wrist-Guided Manipulation
• Last-Layer-Centric Feature Recombination: Unleashing 3D Geometric Knowledge in DINOv3 for Monocular Depth Estimation
• Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image
• Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
• Long-term Traffic Simulation via Structured Autoregressive Modeling
• Text Dictates, Music Decorates: Energy-based Attention for Editable Dance Generation
• Progressive Pose-Guided 4D Animal Reconstruction from Monocular Video
• Learning Zero-Shot Subject-Driven Video Generation Using 1% Compute
• Geometry-Preserving Image Generation for 6D Object Pose Estimation
• EchoStyle: Unlocking High-Fidelity Video Stylization with Reverse Data Synthesis
• EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal
• BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing
• PHOSA: Photorealistic 3D Sign Avatar Modeling and Benchmark
• Face Anything: 4D Face Reconstruction from Any Image Sequence
• Revisiting the Volumetric Data of 4DME: Compression, Extension and Benchmarking for Micro-Expression Analysis
• Gravity-aware partially calibrated absolute pose estimation from affine- or rotation-covariant features
• Dense Dynamic Scene Reconstruction and Camera Pose Estimation from Multi-View Videos
• MorphGS: Morphology-Adaptive Articulated Motion Transfer from Videos
• Disentangling Hallucinations: Orthogonal Semantic Projection for Robust Interpretability
• EmoteGPT: 3D Human Facial Expression from Natural Language Descriptions
• SGMatch: Semantic-Guided Non-Rigid Shape Matching with Flow Regularization
• MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources
• LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing
• ProGVC: Progressive-based Generative Video Compression via Auto-Regressive Context Modeling
• Probing the 3D Object-Level Understanding of Pre-Trained Detection Transformers
• SemCityLoc: Aerial 6DoF Localization Using Semantic 3D City Models
• ICLAgent: Integrated Circuit Footprint Geometry Labeling via LMM-empowered Multi-Agent Framework
• MotionEditGS: Editing Motion and Appearance of 4D Scenes from Monocular Video via Semantically Anchored Gaussians
• DeforM: Reasoning-Guided Physics-Aware Video Generation via Spatial-Temporal Masking
• Predictive Structure Improves Video Diffusion Dynamics
• Tesselating The Earth
• PRISM3D: Probabilistic Refinement and Robust Initialization for Physically Consistent Scene Modeling under Extreme Motion Blur
• SA-V2V: Training-Free Subject-Aware Video-to-Video Personalization
• Infinite Gaze Generation for Videos with Autoregressive Diffusion
• Sim, Yet Same: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds
• FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Arbitrary Images
• MuSViT: A Foundation Vision Model for Sheet Music Representation
• SignSparK: Efficient Multilingual Sign Language Production via Sparse Keyframe Learning
• Retrieving and Refining Winning Noise Tickets for Diffusion-Based Motion Generation
• PIAvatar: Physically Interactive Avatars via Deformation Gradient Decoupling
• Boosting 3D Foundation Models with Featureless Pose Optimization
• Frozen CLIP Priors for Robust Self-Supervised Poisson Inverse Problems
• JointHOI: Jointly Generating Contact Maps Enhances Hand Object Interaction Generation
• InsertAnywhere: Geometrically Grounded and Optics-Aware Video Object Insertion
• 3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement
• 4DGS360: 360° Gaussian Reconstruction of Dynamic Objects from a Single Video
• UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priors
• From One-to-One to Many-to-Many: Dynamic Cross-Layer Injection for Deep Vision-Language Fusion
• Discovering Geometric Biases in 3D Face Reconstruction: A Curvature-Aware Spectral Framework for Fairness Evaluation
• Auto3R: Automated 3D Reconstruction and Scanning via Data-driven Uncertainty Quantification
• HAT-4D: Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration
• Boosting Correspondence Learning with Structure-Aware Estimator
• ActionParty: Multi-Subject Action Binding in Generative Video Games
• VERTIGO: Visual Preference Optimization for Cinematic Camera Generation
• What VGGT Knows About Overlap: Probing Geometric Foundation Models for Co-Visibility
• VKSR: Scalable Kernel Surface Reconstruction Using Vecchia's Approximation
• Moving Beyond More Views: Redundancy-Aware Ego–Exo Fusion for Proficiency Estimation
• Interaction-Aware 4D Gaussian Splatting for Dynamic Hand-Object Interaction Reconstruction
• WorldCache: Content-Aware Caching for Accelerated Video World Models
• Multi-Modal Controlled Coherent Motion Generation
• Out of Sight, Out of Mind? Evaluating State Evolution in Video World Models
• IoUCert: Robustness Verification for Anchor-based Object Detectors
• MMDiff: Extending Diffusion Transformers for Multi-Modal Generation
• ComplexMimic: Human–Scene Interaction Imitation in Complex 3D Environments
• DynEval: Holistic Evaluations of T2I Generative Models in the Wild
• SignRefine: Adapting Foundational Video Models for Sign Language Generation
• CoSyncDiT: Cognitive Synchronous Diffusion Transformer for Movie Dubbing
• GraphVid: Interactive Graph-Controllable Video Generation
• Plug-and-Play Attention Linearization for Pretrained Transformers
• Towards Real-World Wearable Motion Reconstruction
• D-Rex : Diffusion Rendering for Relightable Expressive Avatars
• What CLIP Knows but Cannot Say: Recovering Negation from Frozen Intermediate Features
• VOID: Video Object and Interaction Deletion
• SICAGE: Speaker-Independent Culture-Aware Gesture Generation using TED4C-L Dataset
• Rolling Shutter Camera Self-Calibration
• A Dual-Transformer Architecture with Cross-Attention for Multi-Camera View Recommendation
• Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos
• Match-Any-Events: Zero-Shot Motion-Robust Feature Matching Across Wide Baselines for Event Cameras
• Grounding World Simulation Models in a Real-World Metropolis
• Monocular Models are Strong Learners for Multi-View Human Mesh Recovery
• Analytic Bayesian Uncertainty for LiDAR Segmentation: A Single-pass Generative Approach
• SpEmoC: A Balanced Speaker-Segment Multimodal Emotion Benchmark
• XSurfer: Reconstructing surface meshes of cerebral and cerebellar cortex from diverse MRI data using untrained neural networks
• ReconPhys: Reconstruct Appearance and Physical Attributes from Single Video
• Towards Flexible, Natural, Efficient Interaction for Conversational Talking Face Generation
• World Knowledge in the Weights: Reading Concept Circuits of Vision Transformers
• StreamGVE: Training-Free Video Editing via Few-Step Streaming Video Generation
• Multi-THuMBS: Multi-person Tracking of 3D Human Meshes Beyond Video Shots
• Infinite-Homography as Robust Conditioning for Camera-Controlled Video Generation
• Task Alignment: A simple and effective proxy for model merging in computer vision
• AirZoo: A Unified Large-Scale Dataset for Grounding Aerial Geometric 3D Vision
• What Moves? Localized Motion Representations for Compositional Scene Control
• LoCA: Spatially-Aware Low-Rank Convolutional Adaptation of Vision Foundation Models
• HO-Flow: Generalizable Hand-Object Interaction Generation with Latent Flow Matching
• Articulat3D: Reconstructing Articulated Digital Twins From Monocular Videos with Geometric and Motion Constraints
• VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward
• Video Generation Models are General-Purpose Vision Learners
• ECHO: Ego-centric Modeling of Human-Object Interactions
• InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics
• MuCHeR: Multi-Person Camera-Centric Human Detection, Mesh Recovery and Tracking
• DriftScope: Measuring The Hidden Effects of Diffusion Model Fine-Tuning
• Equivariant Symmetry-Aware Head Pose Estimation for Fetal MRI
• Multi-Head Normalization for Wide Vision Transformers
• BrepLLM: Enabling Large Language Models to Understand Boundary Representations
• Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models
• Event-driven Motion Deblurring via Trajectory-based Kernel Reconstruction
• SPARC: Single-Pass Scaling for Motion Forecasting with Conformal Bayesian Last Layers
• StyleFusion360: View-Consistent Head Stylization via Adaptive Style Modulation
• PrimitiveUDF: Primitive-Based Unsigned Distance Fields for Surface Reconstruction from Point Clouds
• Video2Reaction: Mapping Video to Audience Reaction Distribution in the Wild
• Diffusion-Based Immersive Visual Reasoning
• LOOM: Weaving Geometry-Consistent Human-Object Interaction Videos via Progressive Curriculum Learning
• SignNet-1M: Large-Scale Multilingual Sign Language Video Dataset with Downstream Benchmarks
• ReflectCAP: Detailed Image Captioning with Reflective Memory
• StreamTalk: Streaming Co-Speech Gesture Generation with Key-Pose Anchoring
• Articulated Object Reconstruction from Rest-State Observation
• Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints
• Head Avatars with Dynamic Explicit Hair
• Learning Generatable Mutual Distance for Scene-Aware Human Motion Generation
• Schroedinger’s Cat: Probabilistic Representation and Prediction of Potential Scene Kinematics
• DCARL: A Divide-and-Conquer Framework for Autoregressive Long-Trajectory Video Generation
• Motion Style Slider: Endpoint-Supervised Continuous Style Control for Human Motion Diffusion
• Measuring 3D Spatial Geometric Consistency in Dynamic Video Generation
• When Token Compression Breaks: Structural Pruning vs. Token Reduction for Robust ViT Segmentation under High Compression
• YeTI: You Only Need Two Noisy Images for Real-World sRGB Noise Generation
• VisTa3D: A Dataset and Benchmark for Vision, Tactile, and 3D Point Clouds-based Thin Object Reconstruction
• SafeSAE-VLA: Interpreting OpenVLA Progress Dynamics with Sparse Feature Analysis
• Unified and Efficient Point-Line Local Features
• TACO-Net: Topological Signatures Triumph in 3D Object Classification
• One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Control
• Generative Relightable Avatars
• CL4D: Contrastive Language–4D Pretraining for Vision-Language Reasoning in Dynamic Scenes
• WildProp: Visual Estimation of Wildlife Body Proportions at Scale
• Narrative-Driven Paper-to-Slide Generation via ArcDeck
• GrowFields: Compositional 4D Neural Fields for Topology-Changing Plant Growth
• MemoBench: Benchmarking World Modeling in Dynamically Changing Environments
• VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations
• Test-Time Noise Guided Adaptation for Realistic Autoregressive Video Generation
• One Video, One World: Turning Monocular Video into Physical 4D Scenes
• Meric: A Unified Framework for Multimodal Music Generation and Retrieval via Representation Space Anchoring
• Test-Time Registers as Global Priors for Tokenized Image Generation
• VectorReLoc: Reliable Vectorized SD Map Visual Re-localization with Contrastive Feature Alignment
• Fabric Image Demoiréing Benchmark from Synthesis to Restoration
• MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens
• Controlling Motion Transfer in Diffusion Transformers via Attention Heads
• Coordinate Singularities Break Conformal Coverage for Gaze and Head Pose
• AFFMAE: Scalable Vision Pre-Training for High-Resolution Microscopy Segmentation on Desktop Hardware
• SparseCtrl-HOI: Sparse Temporal Control for Human-Object Interaction Video Generation
• CAR-MIL: Counterfactual Attention Regularization for Multiple Instance Learning
• InnoText: A Unified Model for Visual Text Generation and Editing
• M4-SAR: A Multi-Resolution, Multi-Polarization, Multi-Scene, Multi-Source Dataset and Benchmark for optical-SAR Object Detection
• Decoding Children’s Gait Behavior
• CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation
• InclusiveHuman-10K: Towards Inclusive Human Parsing Beyond the Intact-Limb Assumption
• PIPBench: A Profile-Inclusive Framework for Personalized Image Generation Evaluation
• Kinematics-Agnostic 3D Human Motion Prediction via Equivariant Latent Diffusion
• Layout-Conditioned Autoregressive Text-to-Image Generation via Structured Masking
• Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion
• EDM:Event-guided Diffusion Model for Video Shadow Detection in Complex Dynamic Scenes
• NumColor: Precise Numeric Color Control in Text-to-Image Generation
• Streaming Dense Voxel Representations for 3D Occupancy Prediction
• Learn Once, Edit Anywhere: Visual Direction Transfer for Diffusion Models
• VGEdit: Unlocking Video Generation Priors for Reasoning-Informed Image Editing
• MoScale: Autoregressive Next-Scale Prediction for Human Motion Generation and Editing
• Universal Image Immunization against Diffusion-based Image Editing via Semantic Injection
• Anchoring on Reality: Breaking the Pseudo-Target Ceiling in Makeup Transfer
• Region-Aware Multimodal Interleaving for Animal Re-Identification
• Aligning Human Sense: Calibrated Distributional Reward Learning for Video Generation
• Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning
• MANGO: Unleashing Image Generation Capability of Unified Multimodal Models
• SGQA: Semantic-Geometric Quality Alignment for Training-Free Few-Shot Instance Segmentation
• Anti-Prompt: Image Protection against Text-Guided Image-to-Video Generation
• Exclusivity-Guided Mask Learning for Semi-Supervised Crowd Instance Segmentation and Counting
• Complex-Valued 2D Gaussian Representation for Computer-Generated Holography
• Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipeline
• Fast Dynamic Prototypes for Unsupervised Anomaly Detection and Localization
• LISA: Locality-Informed Speculative Decoding for Accelerating Autoregressive Image Generation
• Free‑CD: Probabilistically Decoupled Training-Free Open-Vocabulary Change Detection with Resolution-Invariant Feature Inversion
• RiO-DETR: DETR for Real-time Oriented Object Detection
• QVAM: Query-guided View-aware Adaptive Modulation for Aerial-Ground Person Re-Identification
• Revisiting Avatar-As-Image: High-Fidelity Registration is All You Need
• Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling
• Diffusion-Based Material Regularization for Physics-Based Inverse Rendering
• UNet-Twice: A Simple Structured Reference-based Inpainting Framework
• SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video
• Query-Kontext: An Unified Multimodal Model for Image Generation and Editing
• MapDreamer: Aerial Imagery Conditioned Latent Diffusion For Lane Level Map Generation
• Divide and Align: Disentangled Vision-Language Learning for Text-Based Person Anomaly Search
• ReSWD: ReSTIR‘d, not shaken. Combining Reservoir Sampling and Sliced Wasserstein Distance for Variance Reduction.
• STEP: Score-Based Temporal Energy for Human Pose Video Anomaly Detection
• Rethinking Continual Anomaly Detection on the Edge: Benchmarking Under Realistic Industrial Conditions
• ShellMaker: Language-Guided Exterior Completion under Structural Constraints
• FoundYou: A Unified Model for Personalized Segmentation and Retrieval
• DiTailed: Ensuring Visual Object Consistency in Text-Image-to-Image Flow Matching Models
• LensStyle: Learning the Optical Aesthetics for Controllable Stylized Lens Effect Rendering
• TRaM-VSR: Importance-Aware Token Routing and Merging for One-Step Diffusion Video Super-Resolution
• Back-Tracking from Clarity: Self-Learning to See Text from Afar
• In-context Region-based Drag: Drag Any Region to Any Shape
• RePL: Pseudo-label Refinement for Semi-supervised LiDAR Semantic Segmentation
• AR-CoPO: Align Autoregressive Video Generation with Contrastive Policy Optimization
• DiffPro: Joint Timestep and Layer-Wise Precision Optimization for Efficient Diffusion Inference
• Text-Conditioned Background Generation for Editable Multi-Layer Documents
• EVAR: Edge Visual Autoregressive Models via Principled Pruning
• High-Throughput Event-Based Feature Detection and Tracking on an Embedded CPU
• MiNQVIS: Mitigating Noisy Queries for Robust Online Video Instance Segmentation
• Multi-dimensional Preference Alignment by Conditioning Reward Itself
• HolisticSemGes: Semantic Grounding of Holistic Co-Speech Gesture Generation with Contrastive Flow-Matching
• Heat Kernel Textures -- the Geodesic Gaussians That Do Not Splat
• PS-MOT: Cultivating Instance Awareness from Point Seeds for Multi-Object Tracking
• Granular Semantic Cognition for Visible-Infrared Person Re-Identification
• Bridging Online and Offline Handwriting via Differentiable Physical Rendering
• A Benchmark for Heterogeneous Stereo Deblurring with Physically- and Epipolar-constrained Cross Attention
• VSDiffusion: Taming Ill-Posed Shadow Generation via Visibility-Constrained Diffusion
• Bottom-up modeling of repeated elements via single image analysis-by-synthesis
• DRPO: Disentangling Demographic Bias from Rewards for Fair Diffusion Alignment
• Beyond Fixed Luminance: Towards Panchromatic and Orthochromatic Image Colorization
• EruDiff: Refactoring Knowledge in Diffusion Models for Advanced Text-to-Image Synthesis
• NoisEasier: Test-Time Noise Optimization for Text-to-Video Generation
• FPicker: Topology-Guided Evolution for Filament Tracing in Low-SNR Microscopy
• FontCopilot: Towards Generalist Multimodal Large Language Models for Holistic Chinese Font Engineering
• Uncertainty-aware tree height change regression
• Training-Free Multi-Concept Image Editing
• DARE to Mitigate Hallucination: Dual-path Auto-Regressive-aware Editing
• Q-REAL: Towards Naturalness and Distortion Evaluation for AI-Generated Content
• Entropy-Controlled Flow Matching
• Triangular Consistency as a Universal Constraint for Learning Optical Flow
• SceneDiff: A Benchmark and Method for Multiview Object Change Detection
• SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation
• RankT2I: A Submodular Framework for Discovering Interpretable and Diverse Semantics in Text-to-Image Models
• NUN: Nested Unfolding Network for Real-World Concealed Object Segmentation
• GenSP: Consistent Spherical Parameterization via Learning Shape Generative Models
• NoiseTilt: Noise-Tilted Reverse Kernels for Diffusion Reward Alignment
• HuCollisionField: Resolving Self-Collisions via Neural Fields for Human Prediction
• Silhouette-based Gait Foundation Model
• LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detection
• Robust Self-Supervised Cross-Modal Super-Resolution against Real-World Misaligned Observations
• ELHINN: Unifying Dense Crowd Simulation Across Scales via Eulerian–Lagrangian Hydrodynamics
• FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs
• Multi-View Foundation Models
• YesTrack: Referring Multi-Object Tracking via MLLM-based Yes/No Reasoning
• AV2T-Gen: Aerial Visible to Thermal Generation with Environment and Vehicle State Guidance
• ThermoGS: Decoupling Physical Surface Attributes for Spatio-Temporal Thermal Field Emulation via 4D Gaussian Splatting
• CountEx: Fine-Grained Counting via Exemplars and Exclusion
• RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards
• TripVVT: A Large-Scale Triplet Dataset and a Coarse-Mask Baseline for In-the-Wild Video Virtual Try-On
• SAEdit: Token-Level Control for Continuous Image Editing via Sparse Autoencoder
• Attribute Token Arithmetic: Disentangled and Continuous Semantic Control for Visual Autoregressive Models
• Sound-based Multi-Person 3D Pose Estimation
• PointSplat: Compact Gaussian Splatting via Human-Centric Prediction
• MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training
• Revisiting Autoregressive Models for Generative Image Classification
• Push–Pull Attentional Anchoring for Diffusion Concept Erasure
• Where and What: Long-Term Object Tracking in Egocentric Videos
• DiGS-Avatar: Single-Image Animatable 3D Human Reconstruction via UV-Space Diffusion
• FitControler: Toward Fit-Aware Virtual Try-On
• Efficient RGB-T Object Detection via Sparse Cross-Modality Fusion
• Controlling Embedding Spaces with Text-Conditioned Transformations
• LoGAN: Multilingual Font Localization with Generative Agents
• ARGOS: Who, Where, and When in Agentic Multi-Camera Person Search
• EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing
• Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models
• APT: Anchor-aligned Perturbations for Tamper Localization in Fully Regenerated Images
• RubricRL: Simple Generalizable Rewards for Text-to-Image Generation
• Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective
• Rethinking Garment Conditioning in Diffusion-based Virtual Try-On: Decouple, Don't Denoise
• Generating a Paracosm for Training-Free Zero-Shot Composed Image Retrieval
• GoStop: Reinforcement Learning for Adaptive Temporal Aggregation in Event-Based Feature Tracking
• UniTranslator: A Unified Multi-modal framework for End-to-end In-Image Machine Translation
• WebEyeTrack: Scalable Eye-Tracking for the Browser via On-Device Few-Shot Personalization
• DuoFlow: JVP-Free Finite-Difference Mean Flows for One-Step Image Generation
• EVEE: Event-Based Online Adaptation for Matching on Unknown Targets
• Layering Virtual Try-On
• TMI: Text-to-Image Meets Image-to-Image for Complementary Data Synthesis to Boost Long-Tailed Instance Segmentation
• PosterCopilot: Toward Layout Reasoning and Controllable Editing for Professional Graphic Design
• TopoFuse: Topology-Aware Tri-Planar Fusion for 3D Cryo-Electron Tomography Segmentation
• Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation
• RADIANCE: Relative Adaptive Denoising with IP-Adapter for Novel Concept Enhancement
• SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models
• Policy-Based Tuning of Autoregressive Image Models with Instance- and Distribution-Level Rewards
• Affordance-Guided Diffusion Prior for 3D Hand Reconstruction
• NURBS Splatting: A Unified Differentiable Rendering Framework for Vector Graphics
• Spanning the Visual Analogy Space with a Weight Basis of LoRAs
• Spanning Tree Autoregressive Visual Generation
• HRDiT: Training-Free High-Resolution Image Generation with Off-the-Shelf Diffusion Transformer Models
• POET: Preference Optimization for Enhanced Text-to-Image Generation
• Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing
• TOPA: Mitigating Concept Dominance in Diffusion Personalization via Target-Oriented Perturbation Augmentation
• Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration
• Beyond the Black Box: Identifiable Interpretation and Control in Generative Models via Causal Minimality
• Single-Query Person-Centric Bimanual Hand-Object Interaction Detection
• Reinforcement Learning for Multimodal Diffusion Language Models via Bidimensional Trajectory and Thought Optimization
• Direct Diffusion Score Preference Optimization via Stepwise Contrastive Policy-Pair Supervision
• Teaching an Agent to Sketch One Part at a Time
• DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing
• FusionTrack: Collaborative Multi-Object Tracking with Arbitrary Multi-UAVs
• Environmental Change Detection for Real-World Change Analysis
• Personalized Reward Modeling for Text-to-Image Generation
• SplitHDR: Saturation-Aware HDR Recovery and Denoising for Real-Time Detection
• Tiled Prompts: Overcoming Prompt Misguidance in Image and Video Super-Resolution
• Let's Reward Step-by-Step: Step-Aware Contrastive Alignment for Vision-Language Navigation in Continuous Environments
• Disentangling Rotation and Translation from SE(3)-Equivariant Features for Shape Assembly
• DOGE: Differentiable Bézier Graph Optimization for Road Network Extraction
• DeltaDeno: Zero-Shot Anomaly Generation via Delta-Denoising Attribution
• JanusMesh: Fast and Zero-Shot 3D Visual Illusion Generation via Cross-Space Denoising
• Geometric Foundation Model Distillation for Efficient Lunar 3D Reconstruction
• Unmasking-Time Visual Calibration for Hallucination Mitigation in Multimodal Discrete Diffusion Language Models
• Beyond Aesthetics: Quantifying Information Loss in Turbid Scenes
• DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models
• Pathryoshka: Compressing Pathology Foundation Models via Multi-Teacher Knowledge Distillation with Nested Embeddings
• REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion
• Unsupervised Source-Free Ranking of Biomedical Segmentation Models Under Distribution Shift
• MV-GEL: Language-Driven Multi-View Geometric Entity Localization on Meshes
• P3-SAM: Native 3D Part Segmentation
• Low-latency Event-based Object Detection with Spatially-Sparse Linear Attention
• LayerVerse: Finding the Sweet Spot for KV-Injection in Training-Free Image Editing
• TerraDiT-Ω: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive
• LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents
• Per‑Object IoU Forecasting for Deadline‑Aware Real‑Time Embedded Detection Control
• STAT: Soft Tail-dropping for Adaptive Visual Tokenization
• Compositional Non-Face Re-Identification Pressure under Cumulative Vision Releases
• FairSteer: Cross-Attention Steering Towards a Fairer Text-Guided Image Generation
• Posterior Augmented Flow Matching
• Unsafe by Reciprocity: How Generation–Understanding Coupling Undermines Safety in Unified Multimodal Models
• Unsupervised Pixel-Level Semantic Left-Right Understanding of In-the-Wild Images
• WearWow: Native 2K Multi-Garment Virtual Try-On via Adaptive Token Packing and Preference Alignment
• TiCRL: Textual Image Classification with Reinforcement Learning-Based Curriculum Learning
• TreeSRNF: Square-Root Normal Fields for Generative Modelling of the Geometric and Structural Variability in Tree-like 3D Objects
• Target-aware Image Editing via Cycle-consistent Constraints
• Temporally Stable Generative Illumination with a One-Step Diffusion Model
• FineEdit: Fine-Grained Image Edit with Bounding Box Guidance
• Slim-DETR: Real-Time Tiny Object Detection with Efficient Interaction and Gaussian Query
• Learning to Tessellate: Point Cloud Generation via Recursive Spectral Partitioning
• Learning Video Dynamics with Predictive Differentiable Rendering
• SpecV: Specification Verification for Robust Unified Multimodal Evaluation
• O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning
• CGCE: Classifier-Guided Concept Erasure in Generative Models
• PA-VAD: Diffusion-Based Pseudo-Only Video Anomaly Detection via Domain-Aligned Memory Updates
• DDStereo: Efficient Dual Decoder Transformers for Stereo 3D Road Anomaly Detection
• Accelerated Likelihood Maximization for Diffusion-based Versatile Content Generation
• Beyond Absolute Scores: Relative Edit-induced Difference for Generalizable Image Aesthetic Assessment
• DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space
• DeCoFlow: Structural Decomposition of Normalizing Flows for Continual Anomaly Detection
• CLUE-VAD: Structured Semantic Clues for Understanding Explainable Events in Video Anomaly Detection
• URHead: A Unified UV-Space Representation for Joint Mesh–3DGS Optimization in Head Avatars
• ODONet: Online Dynamic Offset Network for Visual Object Tracking
• Hybrid-LUT: Channel-Aware Hybrid Lookup Table and Filtering for Efficient Image Restoration
• BrainFIBRE: A Foundation Model via Information Decomposition for Brain Microstructure
• MCVL: Multi-Space Cross-View Learning for Aerial-Ground Person Re-Identification
• Scaling Multi-Reference Image Generation with Dynamic Reward Optimization
• Pretrained Video Models as Differentiable Physics Simulators for Urban Wind Flows
• UnderOneFacade: Worldwide Facade Semantic Segmentation Benchmark Dataset
• WorldMesh: Generating Navigable Multi-Room 3D Scenes via Mesh-Conditioned Image Diffusion
• Omni-RRM: Advancing Omni Reward Modeling via Automatic Rubric-Grounded Preference Synthesis
• OCTA-SOT: Online Cross-Modal Trajectory Adjustment for RGBT Anti-UAV Single Object Tracking under Spatio-Temporal Misalignment
• Event Stream-based Sign Language Translation: A High-Definition Benchmark Dataset and A Novel Baseline
• MATCH: Flow Matching for Multi-View Anomaly Detection
• Evidence Triangulation for Multimodal Fact-Checking in the Wild
• Reinforcing Video Reasoning with Focused Thinking
• Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting
• GH-ESD: Grounded Hypothesis-Driven Error Slice Discovery for Instance-Level Vision Tasks
• Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback
• Constrained Rotation Optimization: Revisiting Crop-Based Gaze Estimation
• DualCount: Structurally Consistent Density and Point Modeling for Zero-Shot Object Counting
• Obliviate: Erasing Concepts from Autoregressive Image Generation Models
• Not All Prediction Targets Keep Training-Free Diffusion Guidance on the Manifold
• Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off
• Proximity-CLIP: Text-Guided Semantic Proximity Learning for Zero-Shot Anomaly Detection
• SAM2Matting: Generalized Image and Video Matting
• Learning Geometry-Aware Embedding Fields for Intrinsic Riemannian Mappings
• Reflecting Process Expertise in Procedural Material Generation
• Real-Time Source-Free Object Detection
• DETRAM: End-to-end DEtection, Tracking and Recovery of HumAn Meshes
• Harnessing SSL for Segmentation in 3D Microscopy with Noisy Labels and Hard Patches
• DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising
• Anomaly Factory 3D: A Modular Framework for Diverse Pseudo-Anomaly Synthesis in Unsupervised 3D Anomaly Detection
• Seeing as Humans Do: Learning from Motion to Segment Anything Without Supervision
• LightFusion: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation
• PhyEditBench: A Real-World Multi-Stage Benchmark for Physics-Aware Image Editing
• Wavelet-Guided Semantic Signal Compensation for Inversion-Free Image Editing
• Correlation-Weighted Multi-Reward Optimization for Compositional Generation
• Rethinking Robust Adversarial Concept Erasure in Diffusion Models
• Text-based Tactile Graphics Generation for the Visually Impaired
• FuDU: A Fuzzy Dual-dimension Uncertainty Framework for Streaming Active Learning in Industrial Defect Detection
• InstanceControl: Controllable Complex Image Generation without Instance Labeling
• StereoEdit: A Diffusion-Based Framework for Stereo-Consistent Image Editing
• Online 3D Instance Segmentation at task-oriented granularity with Unposed Monocular Video
• AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
• Mode-Conditioned Residual Calibration for Multi-Object Tracking
• Domain Adaptive Object Detection via Dual-Stream Bilevel-Cycle Optimization
• HASSL: Hierarchy-Aware Self-Supervised Learning Framework for Single Cell Microscopy
• OSVE: One Step Video Editing with One Step Diffusion Models
• Benchmarking MLLMs on Mistake Recognition and Explanation in Single-Step Components of Cooking
• CoToGrasp: Contact-Topology-Conditioned Dexterous Grasp Synthesis via Canonical Workspace Learning
• Towards Video Anomaly Detection from Event Streams: A Baseline and Benchmark Datasets
• A Scalable Vector Graphics Latent Space
• TexTailor: Inference-Time Textual Guidance Tailoring for Multimodal Diffusion Transformers
• PhenoLeaf-TS: A Time-Series Benchmark for Leaf Instance Segmentation, Tracking, and Growth Stage Classification
• Repurposing Geometric Foundation Models for Multi-view Diffusion
• Local Spacing-Aware Hungarian Matching for Stable Point-Supervised Crowd Counting
• TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields
• A Comprehensive Analysis about Unsupervised Outlier Detection for Images
• Monocular Avatar Reconstruction via Cascaded Diffusion Priors and UV-Space Differentiable Shading
• On-Orbit Real-Time Wildfire Detection Under On-Board Constraints
• Zero-Shot Image Personalization from Personas
• A Simple Baseline with Placement Prior for Point-Supervised Oriented Object Detection
• Bridging the Geometry Mismatch: Frequency-Aware Anisotropic Serialization for Thin-Structure SSMs
• AVSR-Diff: Scale-Agnostic Diffusion Priors for Temporally Consistent Arbitrary-Scale Video Super-Resolution
• Optimization-Guided Diffusion for Interactive Scene Generation
• ISAC: Training-Free Instance-to-Semantic Attention Control for Multi-Instance Generation
• ReFP-AD: Rectified Flow Preconditioning for Energy-Based Anomaly Detection
• SelfMOTR: Revisiting MOTR with Self-Generating Detection Priors
• 3D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identification
• Through Van Gogh’s Eyes: Global Style Transfer with Diffusion Model
• HQ-DM: Single Hadamard Transformation-Based Quantization-Aware Training for Low-Bit Diffusion Models
• Robust Zero-shot Anomaly Detection under Limited Auxiliary Anomaly Priors
• h-Flow: Flexible Flow-based Image Editing via Doob's h-Transform
• Align and Segment: Unsupervised Learning for Building Segmentation From Misaligned Labels
• Reference-Free Quality Assessment for Virtual Try-On via Human Feedback
• COLA: Continual Orthogonal Low-Rank Adaptation for Class-Incremental Learning
• CellFluxRL: Biologically-Constrained Virtual Cell Modeling via Reinforcement Learning
• BAAF: Universal Transformation of One-Class Classifiers for Unsupervised Image Anomaly Detection
• NearID: Identity Representation Learning via Near-identity Distractors
• SCALE: Semantic-Calibrated Guidance Enhancement for Prompt-Faithful Diffusion
• Vector Scaffolding: Inter-Scale Orchestration for Differentiable Image Vectorization
• Generalization and Memorization in Rectified Flow
• Seeing to Ground: Visual Attention for Hallucination-Resilient MDLLMs
• ModTrack: Sensor-Agnostic Multi-View Tracking via Identity-Informed PHD Filtering with Covariance Propagation
• Two-Parameter Flow Map Learning for Continuous-Time Diffeomorphic Image Registration
• Intermediate Text Representation Guided Text-to-Image Generation for Enhancing One-and-Only Alignment
• V-HOLD: Stabilizing Flow Trajectories to Rethink the Edit–Preservation Trade-off
• When Rubrics Fail: Error Enumeration as Reward for Reference-Free RL Post-Training
• LumiTokens: 3D Relighting via Token-Space Lighting Transformation
• Q-BridgeNet: A Quantization Network for Cross-Lingual Sign Language Translation
• Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs
• Rapidly Deploying On-Device Eye Tracking by Distilling Visual Foundation Models
• CHARTSTYLE-100K: A Large-Scale Dataset for Structured Visualization Style Transfer
• Consistent Feature Transport for Image Relighting
• SPQR: A Multi-Dimensional Benchmark for Safety Alignment under Benign Model Adaptation
• Diagnosing Aerial-View Object Detectors with Foundational Image Generative Models
• SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation
• Improved Immiscible Diffusion: Accelerating Diffusion Training by Reducing Miscibility
• UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception
• Diffusion Integrated Gradients: Controllable Path Generation for Flexible Feature Attribution
• Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation
• Multi-History-Step SDE Inversion for Image Editing with Superior Regional Awareness
• PRISM: Latent Composition Consistency for Single-Image Reflection Removal
• DiffGI: Differentiable Geometry Images for High-Fidelity Thin-Shell 3D Generation
• CRD-Net: Frequency-Adaptive Feature Injection and Change Decoupling for Building Damage Assessment
• H-Adapter: Pose-Robust Hairstyle Transfer via Attention-Derived, Source-Aligned Hair Masks
• Don’t Starve the Boundaries: Boundary-Constrained Label Propagation for Weakly Supervised 3D Segmentation
• Self-Improving Diffusion Classifiers with Minority Preference Optimization
• EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders
• Segmenting, Fast and Slow: Real-Time Open-Vocabulary Video Instance Segmentation with Dual-Path Processing
• DARL: Efficient Document-to-Markup Generation via Look-Ahead Diffusion Trajectory Sampling
• Contextual Image Attack: How Visual Context Exposes Multimodal Safety Vulnerabilities
• Continuous Speculative Decoding for Autoregressive Image Generation
• SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation
• Following the Flow: Advection-Consistent Modeling for Event-based Small Object Detection
• WorldAgents: Can Foundation Image Models be Agents for 3D World Models?
• Editing Everything Everywhere All at Once
• Event-based Gaze Control Systems for Real-time Spin Estimation in Professional Ball Games
• K-Mask: Kinematic-Aware Masked Modeling for Controllable Text-to-Motion Synthesis
• OBBSeg: Irregular Lesion Segmentation under Oriented Bounding Box Annotations
• ET-SAM: Efficient Point Prompt Prediction in SAM for Unified Scene Text Detection and Layout Analysis
• Robust 3DGS-based SLAM via Adaptive Kernel Smoothing
• Semantically Aligned Gradient-Driven Context-Preserving Image Editing
• IACD: Iterative Adversarial Collaborative Detection via Dual-Perspective Blind Spot Discovery
• VIGA: View-Conditioned and Identity-Guided Adaptation for Aerial-Ground Person Re-Identification
• Stitched Embeddings: A Unified Latent Space for 3D Garments and 2D Patterns
• Point2Pose: Occlusion-Recovering 6D Pose Tracking and 3D Reconstruction for Multiple Unknown Objects Via 2D Point Trackers
• TiltDiff: Tilted Weight-Space Diffusion for Neural Network Generation
• RCEdit-500K: Reference Completion for Image-Conditioned Image Editing
• VLTR: Vision-Language Tool Reasoning for Instruction-Guided Image Editing
• ProtoFair: Fair Self-Supervised Contrastive Learning via Pseudo-Counterfactual Pairs
• Why Linear Probing Works: Non-Vacuous Generalization Bounds via Effective Dimension
• CMuon: Accelerating and Stabilizing Diffusion Transformer Training via Chunked Momentum Orthogonalization
• NeuralGarSim: Geometry-agnostic Garment Simulation with Neural Fields
• To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion
• The Map Is Not the Territory: Embedding-Coverage Blacklists for Safe Diffusion Steering
• Segmentation-Guided Homography Estimation for Long-Term Planar Tracking
• ExPLoRe: Expert Patch-Level Loss Routing for Multi-Objective Masked Image Modeling
• DETRPose: Real-Time End-to-End Multi-Person Pose Estimation via Modified Transformer Decoder and Novel Denoising Keypoints
• Rank-Aware Hyperbolic Alignment for Vision–Language Dataset Distillation
• Prototype Normalization: Optimizing Prototype Separation for Heterogeneous Federated Learning
• CloSeR: Unified Relational Distillation from Closed-Set Teachers for Category Discovery
• CaRe: Critical Parameter Rectification for Efficient Visual Modeling
• AccelAes: Accelerating Diffusion Transformers for Training-Free Aesthetic-Enhanced Image Generation
• HER-Count: Learning Hyper-Exemplar Representation for Generalized Zero-Shot Object Counting
• ProSR: Semantic-Prototype-Guided Discrete Modeling for Physically Consistent SAR Super-Resolution
• FST-SAM3: Taming SAM~3 with Frequency-Spatio-Temporal Refinement for Video Polyp Segmentation
• R2M: Real-Aware Residual Model Merging for Robust and Generalizable Deepfake Detection
• Straight-Path Flow Matching for Incomplete Multi-View Clustering
• An Inverse-Adversarial and Difficulty-Adaptive Robust Vision-Language Model
• Rethinking Prototype-based Similarity Learning for Few-Shot Object Detection
• D2PO: Optimizing Diffusion Samplers via Dynamic Preference
• Be Tangential to Manifold: Discovering Riemannian Metric for Diffusion Models
• SFM: Taming State Space Models for Text-to-Motion via Spatial-Frequency Modeling
• BATQuant: Outlier-Resilient MXFP4 Quantization via Learnable Block-wise Optimization
• AC3S: Adaptive Conditioning for 3D-Aware Synthetic Data Generation
• ColorFM: An Optimization-to-Learning Framework for Color Transfer via Flow Matching
• Spectral Prior for Reducing Exposure Bias in Diffusion Models
• MixTTA: Low-Rank Cross-Channel Mixing for Reliable Test-Time Adaptation
• FSDC-DETR: A Frequency-Spatial Domain Collaborative DETR for Small-Object Detection
• Revisiting Deepfake Detection: BCNet for Robust Generalization Beyond Semantic Dependence
• BioMedVR: Confusion-Aware Mixture-of-Prompt Experts for Biomedical Visual Reprogramming
• D3F-IR: Dual-Domain Deterministic Flow Matching for Visible-to-Infrared Translation
• REAL-OW: Rehearsal-free Open World Object Detection with Low-Rank Adaptation and Dual-Stage Objectness Modeling
• Virtual Category-Guided Continual Generalized Category Discovery
• Contrastive Conditional–Unconditional Alignment for Long-tailed Diffusion Model
• CaPCL: Caption-Preserved Continual Learning for Text-to-Image Retrieval
• BEVOpen3D: Towards Open-World 3D Object Detection in Bird's-Eye-View
• Label-Free Text Prototype Adaptation for Open Vocabulary Segmentation
• Solving Diffusion Inverse Problems with Restart Posterior Sampling
• Unified Multi-plane Autoregressive Diffusion for 3D Multi-Contrast MRI Synthesis
• Dual-Margin Embedding for Fine-Grained Long-Tailed Plant Taxonomy
• Y-diff: Structure-Texture Decoupled Diffusion Distillation for H&E-to-pCLE Translation
• DA-MergeLoRA: Hypernetwork-Based LoRA Merging for Few-Shot Test-Time Domain Adaptation
• Zero-Shot Quantization for Object Detectors using Off-the-Shelf Generative Models
• Rethinking Cross-Spectral Image Generation via Shared-Specific Representation
• Source-Agnostic Image Translation Based on Latent Aware Adaptive Masking
• SCoT: Similarity-guided Conflict-aware Task Consolidation for Continual VQA
• HEM: a margin-based loss for visual categorisation tasks
• SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization
• CMDer: Controllable Mode Decomposition-Based Single Motion Synthesis with Diffusion
• COVERT: Privacy-Preserving Covariant Obfuscation for VLMaaS via Exact Reparameterization and Tailored Tuning
• DiffRGD: An Inference-Time Diffusion Guidance Through Riemannian Gradient Descent
• Comprehensive Robustness Analysis of LiDAR-based 3D Object Detection in Autonomous Driving
• CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation
• Fisher-Routed Mixture of Experts for Federated Class-Incremental Learning
• Mask-guided Semantic Alignment: Robust Learning with Noisy Labels via Temporal Attention Stability
• Reconstruction-Anchored Diffusion Model for Text-to-Motion Generation
• Open-Weather Robust 3D Detection via Dual-Critic Diffusion Alignment
• Aligning Anything: Hierarchical Motion Estimation for Video Frame Interpolation
• Degradation-Robust and Temporally Consistent Infrared–Visible Video Fusion via One-step Diffusion Framework
• KATANA: Knowledge-Aligned Topology-Aware Neural Agents for RL-Driven Vision-Language Model Compression
• Semantic Browsing: Controllable Diversity for Image Generation
• Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts
• Breaking Rigidity in Adversarial Patch Attacks
• Recolour What Matters: Region-Aware Colour Editing via Token-Level Diffusion
• Symbiotic-MoE: Unlocking the Synergy between Generation and Understanding
• Cross-Resolution Distribution Matching for Diffusion Distillation
• ScanFocus: A Coarse-to-Fine Framework for Spatio-Temporal Video Grounding
• SIMPLER: Efficient Foundation Model Adaptation via Similarity-Guided Layer Pruning for Earth Observation
• Modality-Aware Out-of-Distribution Detection for Multi-Modal Action Recognition
• RhymeFlow: Training Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling
• VD-LoRA: Adaptive Reuse of Low-Rank Directions for Continual Learning
• Disentangling and Reusing Interaction Cues for Zero-Shot HOI Detection
• SLAIR: Structured Latent Flow Matching for All-in-One Image Restoration
• Why Feature Magnitude Deceives OOD Detectors: An Angular Separation Perspective
• Learning Structured Visual Compositional Representations for Weakly Supervised Referring Expression Comprehension
• DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM Agents
• FeDepth: Federated Learning for Depth Estimation under Robot Heterogeneity
• MAVFusion: Efficient Infrared and Visible Video Fusion via Motion-Aware Sparse Interaction
• Towards Sparsely Annotated Open World Object Detection
• SUM: Unified Geometric Surgery on Spatio-Temporal Adaptation Vectors for Federated Class Incremental Learning
• Flow Straight to Reality: Perceptually Consistent Flow Matching for Efficient Image Restoration
• SegPAR: Class-Centric Decision-Based Sparse Attack for Semantic Segmentation
• Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging
• ReTarget: Representation Transformation via Adversarial Regularization for Geometric Misalignment
• Training-Free Task Classification for Multi-Task Model Merging
• FMA-Net++: Motion- and Exposure-Aware Joint Video Super-Resolution and Deblurring
• MED-LCDS: Multi-Expert-Domain CLIP Classification via Logit Calibration
• MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation
• FaceMoE: Mixture of Experts for Low-Resolution Face Recognition
• LANCE: Low Rank Activation Compression for Efficient On-Device Continual Learning
• The Label Imitation Game: Turing Test Network for Zero-Shot Pseudo-Label Pruning
• Segmenting Visuals With Querying Words: Language Anchors For Semi-Supervised Image Segmentation
• TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction
• OP3DSG: Open-vocabulary Part-aware 3D Scene Graph Generation for Real-world Environments
• DiverseVAR: Balancing Diversity and Quality of Next-Scale Visual Autoregressive Models
• From Local Geometry to Global Pseudo-Labeling for Robust Positive–Unlabeled Learning under Covariate Shift
• Prevention over Correction: Learning Aligned Representations in One-shot Federated Learning
• AnchorGUI: Asymmetric Memory for Dual-Scale Learning in GUI Navigation
• NegROI: Click-Centric Uncertainty-Guided Refinement with Scene-Conditioned Negative Prompts for Robust Interactive 3D Segmentation
• FedMental: Topology-Aware Federated Prototype Learning for Polymorphic Multimodal Psychiatry
• Path-JEPA: Path Signature Based Predictive Learning for Skeleton Action Recognition
• Selective Synergistic Learning for Video Object-Centric Learning
• PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation
• Saber: Anchoring Semantics to Scale-Aware Kinetic Salience for Zero-Shot Skeleton Action Recognition
• Beyond Alignment: A Generative Matching Paradigm via Flow Matching for Zero-Shot Skeleton-Based Action Recognition
• Exposure Bias Can Alleviate Itself via Directional and Frequency Rectification in Flow Matching
• Boosting Text-Driven Video Segmentation via Geometry-Aware Distillation
• Robust onion: Peeling Open Vocab Object Detectors Under Noise
• CLIP-AUTT: Test-Time Personalization with Action Unit Prompting for Fine-Grained Video Emotion Recognition
• Domain Adaptation with Adaptive Imagination for Visual Reinforcement Learning under Limited Target Data
• Task-Agnostic Incremental Vision-Language Object Detection via Prompt Augmentation and Distribution-Aware Fusion
• Low-Rank Ternary Adaptation for Fine-Tuning Transformers
• Foundation Model Selection for Remote Sensing via a Constraint-Aware Agent
• Learning 1-Bit LiDAR-based Localization with Auxiliary Objective
• EMAG: Self-Rectifying Diffusion Sampling with Exponential Moving Average Guidance
• VisNec: Measuring and Leveraging Visual Necessity for Multimodal Instruction Tuning
• Diffusion-based dual-view reflection removal
• ModuSeg: Decoupling Object Discovery and Semantic Retrieval for Training-Free Weakly Supervised Segmentation
• Preserving Knowledge across Space and Time for Continual Video Deepfake Detection
• Beyond the Boundary: RL-Driven Solution Space Exploration for Blind Face Restoration
• Geometric Regularization for Long-Tailed Semi-Supervised Learning via Gaussian Feature Bridges
• BIP: Bi-level Information Transfer and Completion Prompting for Visual Recognition with Missing Modalities
• BiSLW: Bi-Spectral Latent Watermarking for Generative Diffusion Models
• Decoupling Complexity from Scale in Latent Diffusion Model
• Wavelet-Driven Cross-Domain Consistency for Mixed-Supervised 3D Tumor Segmentation
• PriSM: Parsing and Style-Mixed Consistency for Unsupervised Domain Adaptation in Facial Landmark Detection
• Co-evolving Representations in Joint Image-Feature Diffusion
• DSeq-JEPA: Discriminative Sequential Joint-Embedding Predictive Architecture
• Neural Collapse-Inspired Multi-Label Federated Learning under Label-Distribution Skew
• Region-Aware Test-Time Scaling for Compositional Image Generation
• TooBad: Backdoor Diffusion Models with Ultra-Low Poison Rate and Imperceptible Trigger
• RT-DETRv4: Painlessly Furthering Real-Time Object Detection with Vision Foundation Models
• Training-free Discriminative Patch Mining for Robust Few-Shot Recognition with CLIP
• SD3.5-Flash: Distribution-Guided Distillation of Generative Flows
• Rethinking Adversary in Semantic Segmentation: An Out-of-Distribution Perspective
• VCP-DCN: Beyond Visual Concealed Property via Depth Collaborative Network for Camouflaged Object Detection
• Stealthy Multi-task Adversarial Attacks
• Spectral Consistent Flow for One-step 3D Medical Image Translation
• SCDL: Synergistic Confidence-Dispersion Learning for Semi-Supervised Video Polyp Segmentation
• PASR: Pattern-Aware Scene-Conditioned Reasoning for Camouflaged Object Detection
• Towards Scalable Pre-training of Visual Tokenizers for Generation
• μFlow: Leveraging Average Images for Improving Generalisation of Deepfake Faces Detectors
• Momentum Guidance: Plug-and-Play Guidance for Flow Models
• When W4A4 Breaks Camouflaged Object Detection: Token-Group Dual-Constraint Activation Quantization
• Discrete Diffusion Bridges for Spatiotemporally Aligned Image Translation and Generation
• Which Layer Causes Distribution Deviation? Entropy-Guided Adaptive Pruning for Diffusion and Flow Models
• Open-Vocabulary 3D Object Detection with Co-Distillation Discovery and Dual Guidance Robust Training
• MoMCE: Mixture of Modality and Cue Experts for Multimodal Deception Detection
• Discrete Diffusion Models with MLLMs for Unified Medical Multimodal Generation
• SAMPLe: A Sharpness Aware Minimization based Optimizer for Prompt Learning in Vision-Language Models
• Holistic Optimal Label Selection for Robust Prompt Learning under Partial Labels
• CoT-PL: Chain-of-Thought Pseudo-Labeling for Open-Vocabulary Object Detection
• RA-SOD: Reliability-Aware RGB-T Salient Object Detection under Modality Degradation
• Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning
• Towards Purified Multi-Label Test-Time Adaptation of Vision-Language Models
• Fragmented Text Is Insufficient for Image Representation: Fine-Grained Correspondence in Multimodal Dataset Distillation
• DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection
• InfraNet: Quality-Aware RGB Guidance for Infrared Object Detection
• Multi-modality Image Fusion under Adverse Weather: Mask-Guided Feature Restoration and Interaction
• Learning Accurate Segmentation Purely from Self-Supervision
• DAPS++: Rethinking Diffusion Inverse Problems with Decoupled Posterior Annealing
• Bayesian Uncertainty Attribution-Guided Fine-Tuning for Open-Set Action Recognition
• VLOD-TTA: Test-Time Adaptation of Vision-Language Object Detectors
• LDC-MTL: Balancing Multi-Task Learning through Scalable Loss Discrepancy Control
• Enhancing prompt-image alignment evaluations via cyclic mutual information maximization
• Benchmarking Federated Learning & Knowledge Distillation for Point Cloud Classification
• When Specialists Meet Generalists: Segmenter-Coordinated Asymmetric Learning for Label-Deficient Concealed Object Segmentation
• Unleashing Multimodal Large Language Models for Training-free HOI Detection in the Wild
• Mitigating Pose–Scale Discrepancy Bias and Reforming Multi-Support Reasoning for Few-Shot Semantic Segmentation
• Can Vision Models Truly Forget? Mirage: Representation-Level Certification of Visual Unlearning
• Locality-Aware Continual Unlearning for Diffusion Models
• ECTraj: Enhanced Consistency Training for Multi-Agent Trajectory Prediction
• Multi-scale Object-Aware Gaze Estimation via Geometric Reasoning
• Online Versatile Incremental Learning: Towards Class and Domain-Agnostic Adaptation at Any Time
• Detecting Backdoors in Object Detection via Pre-NMS Prediction Distribution Shift
• DecepGPT: Schema-Driven Deception Detection with Multicultural Datasets and Robust Multimodal Learning
• Safe Generalization: Mitigating Catastrophic Forgetting in Single-Source Multi-Organ Segmentation via Collaborative Causal Learning
• Short-to-Long Functional Connectivity Transfer via Structure-Aware Latent Diffusion
• RefAlign: Representation Alignment for Reference-to-Video Generation
• From Predictions to Embeddings: Dual Knowledge Distillation for Instance-Dependent Partial Label Learning
• ReynoldsFlow: Physics-Inspired Spatiotemporal Flow Representation for Video Understanding
• Physics Meets Perception: A Reinforcement Learning Framework for Unpaired Real-World Image Dehazing
• CRISP: Calibration-Aware Visual State Space Duality for Remote Sensing Image Segmentation
• RefDiT: Local Attribute Guidance in Reference-Based Image Generation
• Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorations
• Exploiting Local Flatness for Efficient Out-of-Distribution Detection
• Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation
• Learning to Corrupt for Better Restoration
• FedDO: Dynamic Client Optimization for Adaptive Federated Learning
• DINOde: Continuous Vision-Text Alignment for Open-Vocabulary Semantic Segmentation
• LACON: Training Text-to-Image Model from Uncurated Data
• Indelible Backdoors: On the Limits of Post-Training Defenses
• FD²: A Dedicated Framework for Fine-Grained Dataset Distillation
• XSemanticFlow: Cross Object Semantic Alignment for Zero-shot Manipulation
• Unified Multi-Layer Subspace Modeling for Cross-Domain OOD Detection
• LUCE: Constrained Curve-Domain Guidance for Training-Free Low-Light Enhancement with Hue-Preserving Decoupling
• Improving Image-to-Image Translation via a Rectified Flow Reformulation
• From smooth to sharp: Frequency-Decoupled Latent Optimization for Realistic Image Generation
• Towards Unsupervised Multi-modal Semantic Segmentation
• MoE-KD: Your Teacher Model is Worth Mixture-of-Experts for Knowledge Distillation
• ELT: Elastic Looped Transformers for Visual Generation
• Intra-Class Consistency Guided Class-Agnostic Event Segmentation
• DA-F2F: Domain-Adaptive Object Detection with Feature-to-Feature Modulation and Alignment
• SPLIT: Training-Free AI-Generated and Partially Edited Video Detection via Spatial Patch‑Level Incoherence and Temporal Roughness
• OpenPanoD: Aligning Multimodal Prompts and Spherical Representations for Open-Vocabulary Panoramic Detection
• On the Vulnerability of Parameter-Level Defenses to Model Merging
• Residual-Guided Expert Specialization for Incomplete Multimodal Learning
• QualiTeacher: Quality-Conditioned Pseudo-Labeling for Real-World Image Restoration
• Don’t Settle at the Mode! Mitigating Diversity Collapse in Pretrained Flow Models via Feature Self-Guidance
• Data-Free Client Contribution Estimation via Logit Maximization for Federated Learning
• Breaking the Model Forgetting Cycle in Long-Incremental 3D Object Detection
• Beyond Disjoint Tasks: Towards More Natural Continual Learning for Vision-Language Models
• HNDiff: Haze-Noise Diffusion for Image Dehazing
• UniStitch: Unifying Semantic and Geometric Features for Image Stitching
• PhysFlowNet: Learning Canonical Latent Manifolds via Spatio-Spectral Physics Priors for Underwater Object Detection
• When Distillation Breaks Motion Control: Restoring Generative Trajectories for Fast Video Generators
• Generative Refinement Network for Visual Synthesis
• Rethinking Token Reduction for Diffusion Models via Output-Similarity-Awareness
• CMDS-AD: Cross-Modal Dual-Stream Decoupling for Few-Shot Anomaly Detection
• FSD-Net: Foundation-Guided Spatiotemporal Distillation for Video Polyp Segmentation
• Learning to Recover Task Experts from a Multi-Task Merged Model
• DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognition
• Training-Free Refinement of Flow Matching with Divergence-based Sampling
• Attention-Logit Steering to Compositional Generalization for Continual VQA
• Beyond Prompts: Unconditional 3D Inversion for Out-of-Distribution Shapes
• TerrainGraphNet: Terrain-Constrained Graph Reasoning for Landslide Segmentation
• Incentive Noise and Structural Prior Infusion for Multi-Modal Object Re-Identification
• LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion
• Fourier Self-Supervision for Fine-Grained Generalized Category Discovery
• Distribution-Aware Feature Selection for Post-hoc Out-of-Distribution Detection
• TORA: Topological Representation Alignment for 3D Shape Assembly
• GhostPoint: Self-Supervised Representation Learning by Hallucinating Occluded LiDAR Structure
• H-SFP: Hierarchical Federated Learning with Decoupled Split-Model Prototyping
• What Images Cannot Say: Language-Guided Olfactory Representation Learning
• SK-Adapter: Skeleton-Based Structural Control for Native 3D Generation
• OPAL: Orthonormal Prototype Alignment Learning for Interpretable Image Classification
• Vitality-Aware Compression for Efficient Image-to-Shape Diffusion Transformers
• SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing
• MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding
• Stabilizing Ultra-Low-Bit Quantization of Multimodal LLMs via Global Bit Allocation
• Path-level Hindsight Instructions for Semantic Exploration in Vision-Language Navigation
• MixCompress: Mixture of Experts for Variable Rate Learned Image Compression
• Capacity Overflow: A Blind Spot for Backdoor Attacks in Vision MoE
• Improving Adversarial Robustness via Activation Amplification and Attenuation
• Inference-Time Scaling of Diffusion Models via Progressive Seed Pruning
• Defect-aware Hybrid Prompt Optimization for Zero-Shot Multi-type Anomaly Detection and Segmentation
• UltraGen: Efficient Ultra-High-Resolution Image Generation with Hierarchical Local Attention
• Generative Manifold Distillation: Aligning Restoration Trajectories with the Natural Image Prior
• Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectories
• Early Estimation of Language to Latent Alignment in Diffusion Models
• T-REN: Learning Text-Aligned Region Tokens Improves Dense Vision-Language Alignment and Scalability
• TanGO: Training-Free 3D Editing via Tangent-Space Guidance and Optimization
• Shared LoRA Subspaces for almost Strict Continual Learning
• NaP-Control: Navigating Diffusion Prior for Versatile and Fast Character Control
• Learning Structurally Consistent Representations for Multi-View Radar Semantic Segmentation
• FAIR: Feature-Augmented Implicit Regularization for AI-generated Fake Image Detection
• Unified Backbone Refinement for Diffusion Models via Internal-Latent Analysis
• FedNASP: Federated Vision-Language Navigation with Adaptive Step-wise Personalization
• SAM+D: Parameter-Efficient Dimensional Lifting of SAM-Family Models via Depth-Routed LoRA and Depth Shifting
• S2-FracMix: Self-Saliency Fractal Mixup
• Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition
• Prompt2Effect: Training-Free LoRA Synthesis for Controllable Video Effects
• Linear Fusion MultiDiffusion for Fast Training-Free Spherical Panorama Generation
• MOCHA: Multi-modal Objects-aware Cross-arcHitecture Alignment
• Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models
• Diffusion Image Generation with Explicitly Modeling of Data Manifold Geometry
• Token-level Response-visual Attention Guidance for Multimodal LLMs Knowledge Distillation
• FreqOrtho-SR: Frequency-Guided Orthogonal Expert Learning for Real-World Image Super-Resolution
• Liquid Fusion of Heterogeneous Representations Towards General Salient Object Detection
• Prune Once: Retraining-Free Task-Agnostic Pruning for Vision-Language Models
• WaterGen: Decoupling Scene and Medium in Underwater Image Generation
• HVGCD:Rethinking Generalized Category Discovery through Hypothesis–Verification
• Learning to Compose: Revisiting Proxy Task Design for Zero-Shot Composed Image Retrieval
• MaterialFlow: Attribute-Disentangled Material Transfer via Trajectory-Aware Velocity Modulation
• Rethinking Real-World MRI Denoising: Learning from Physical Noise
• HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-training
• Learning to Attract and Repel: Dual Quality Margin Learning for Face Recognition (DQM-Face)
• TextDS: Parameter-Efficient Representation Alignment for Scene Text Detection under Distribution Shifts
• Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptation
• AnyStyle: A Single LoRA is Sufficient for Image-Guided Style Transfer
• RAG-3DSG: Enhancing 3D Scene Graphs with Re-Shot Guided Retrieval-Augmented Generation
• Unified Prediction and Planning via Conflict-Aware Disjoint Parameter Training
• Jumping the Landing Phase: Noise Variance Matching Enables Accurate Few-Step Inversion
• QASA: Quality-Guided K-Adaptive Slot Attention for Unsupervised Object-Centric Learning
• SAND: Stage-Aware Noise Decomposition for Training-Free Diffusion Guidance
• Diffusion to Obfuscation: Time-Adaptive Synthesized Generation Against Gradient Leakage Attacks in Federated Learning
• Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers
• Neutralizing Token Aggregation via Information Augmentation for Efficient Test-Time Adaptation
• TSEmbed: Unlocking Task Scaling in Universal Multimodal Embeddings
• ReliefSAM: A Geometry-Augmented Multi-Prior Adapter for Bas-Relief Segmentation
• DiscoVL: Unveiling Disentangled Cross-Modal Representation Learning via Orthogonal Adversarial Regularization for Vision-Language Models
• Graph Coloring for Multi-Task Learning
• Reflection-Aware Reasoning for Non-Line-of-Sight Pedestrian Localization
• Orthogonal Knowledge Refreshing for Domain-Incremental Object Detection
• Group3D: MLLM-Guided Semantic Grouping for Open-Vocabulary 3D Object Detection
• Hierarchical Prompt Injector for Domain Generalization Segmentation
• Rethinking Pseudo-Labels: Multi-Granularity Supervision for Domain Adaptive Object Detection
• DroneFINE: Domain-Aware Parameter-Efficient Fine-Tuning of Vision-Language Detectors for Drone Images
• Representation Alignment for Just Image Transformers is not Easier than You Think
• SARA: Structure-Aware Riemannian-Guided Alignment for Drone Image-Text Retrieval
• High-Resolution Artwork Outpainting with Global Blueprint Guidance and Layout Control
• One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policies
• GenHOI: Generalized Hand-Object Pose Estimation with Occlusion Awareness
• Warp-free Cross-view Geo-localization via Feature-space Consensus Mining
• OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolution
• Accurate Zero-shot Quantization via Hierarchical Teacher-Assistant Distillation
• What is the Right Embedding Space for Contrastive Learning in Referring Expression Counting?
• Flash-DD: An Ultra Parameter-Efficient Approach to Dataset Distillation
• TIR-Agent: Training an Explorative and Efficient Agent for Image Restoration
• GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models
• Iterative Refinement of Semantic and Spatial Representations for Open-Vocabulary Camouflaged Object Segmentation
• Zero-Shot Inference-Time Rectification for Real-World Arbitrary-Scale Super-Resolution
• Image Warping for Image-to-Image Translation
• UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation
• MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning
• Visual Spatial Tuning
• UniBYD: A Unified Framework for Learning Robotic Manipulation Across Embodiments Beyond Imitation of Human Demonstrations
• Unsupervised Point Cloud Registration via Training-Time Semantic Guidance
• OmniNWM: Unifying the State-Action-Reward Triad for Closed-Loop Panoramic Driving Navigation World Models
• Memory Tree Guided Key Frame Querying for Efficient 3D Question Answering
• MolmoWeb: Open Visual Web Agent and Open Data for the Open Web
• EGVLR: Evidence-Grounded Vision–Language Reinforcement for Anomaly Reasoning
• VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning
• Multi-scale Mixture of World Models for Embodied Agents in Evolving Environments
• VERDICT: Training-Free Step-Wise Verification of Multimodal Reasoning via Disagreement-Aware Consensus
• GameWorlds: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents
• BaFCo: A Document Understanding Benchmark for Complex Bangla Form Comprehension
• Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction
• HERO: Heterogeneous Evidential Robust Object-Level Collaborative Perception
• Markov-Renewal Single-Photon LiDAR Simulator
• Pixel-wise Geo-registration of Drone and Satellite Images
• Thinking from the Robot’s View: The CoT-HRC Benchmark for Human Intent Reasoning in Embodied Collaboration
• Sen-Cap: Sensor-Flexible and Noise-Resilient Human Motion Capture via LiDAR-Camera Integration
• Iterative Perceptual Alignment for VLMs via Deterministic Reconstruction Feedback
• RECO: Region-Aware Compensation for Extrinsic Perturbations in Roadside 3D Detection
• ViTAL‑X: Video-Text Alignment with Cross‑Modal Temporal Edits
• DiverseAD: A Large-Scale Driving Dataset with Diverse Atmospheric Conditions
• RegVGGT: Sustainable Visual Geometry Grounding for Streaming via Regulated Memory
• Toward Interpretable Analysis of Whole-slide Pathology Images via Large Language Model-based Agentic Reasoning
• ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance
• AdaDexGrasp: Adaptive Dexterous Grasping via 3D Visuo-Tactile Representation Fusion
• White Aggregation and Restoration for Few-shot 3D Point Cloud Semantic Segmentation
• E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenes
• BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Models
• RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures
• ForeSea: AI Forensic Search with Multi-modal Queries for Video Surveillance
• Tac2Real: Reliable and GPU Visuotactile Simulation for Online Reinforcement Learning and Zero-shot Real-World Deployment
• Personalizing MLLMs via Reinforced Multimodal Reference Game
• MV2GF: Multi-view Pedestrian Detection with a Visual Geometric Foundation Model
• LangLoc: “Tell Me What You See”
• HumanOmni-Speaker: Identifying Who said What and When
• OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning
• Persistent Robot World Models: Stabilizing Multi-Step Rollouts via Reinforcement Learning
• StrucTab: A Structured Optimization Framework for Table Parsing
• Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation
• Counting Trees from Satellite Imagery with Noisy Supervision
• Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing
• S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresight
• RayMap3R: Inference-Time RayMap for Dynamic 3D Reconstruction
• Geometric Context Transformer for Streaming 3D Reconstruction
• Bridging Vision and Language Concepts through Optimal Transport Semantic Flow
• VVSim: A Large-Scale Aerial-Ground Dataset and Benchmark for Cooperative Perception
• SceneOrchestra: Efficient Agentic 3D Scene Synthesis via Full Tool-Call Trajectory Generation
• UECP: Uncertainty-Enhanced Collaborative Perception
• CoReLIN: Constraint-based Reasoning for Zero-shot Lifelong Interactive Navigation
• Bootstrapping Articulated 3D Reconstruction from 2D Image Collections
• Caption Bottleneck Models
• Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation
• Grasp-Oriented Non-Prehensile Manipulation via Learning a Graspability Field
• 360CityArena: A Realistic Virtual Urban Navigation Benchmark for Embodied Agents
• VIPS: Vehicle-Infrastructure Cooperative Planning Benchmark via Pseudo-Simulation
• CooperScene: Multi-Modal Cooperative Autonomy Benchmark with C-V2X Communication Characterization
• WorldFlow3D: Flowing Through 3D Distributions for Unbounded World Generation
• ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs
• RESOLVE: A Multi-Resolution and Multi-Modal Dataset for Roadside Cooperative Perception
• Towards Metric-Agnostic Trajectory Forecasting
• How to Teach Large Multimodal Models New Skills
• AMCoNav: Asynchronous Multi-module Collaborative Framework for Embodied Visual Navigation
• MultiHaystack: Benchmarking Multimodal Retrieval and Reasoning over 40K Images, Videos, and Documents
• TraversRL: Traversable Pedestrian Pathway Generation With Reinforcement Learning
• Seeing Through the Weights: Privacy Leakage in Scene Coordinate Regression
• DH-VLM: Dual-Horizon Cooperative Latent Reasoning for Autonomous Driving
• Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs
• Seen2Scene: Completing Realistic 3D Scenes with Visibility-Guided Flow
• SEM-ROVER: Semantic Voxel-Guided Diffusion for Large-Scale Driving Scene Generation
• Tactile Modality Fusion for Vision-Language-Action Models
• Global-Local Dual Perception for MLLMs in High-Resolution Text-Rich Image Translation
• LESV:Language Embedded Sparse Voxel Fusion for Open-Vocabulary 3D Scene Understanding
• ReconDreamer-RL: Enhancing Reinforcement Learning via Diffusion-based Reconstruction
• Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout
• EgoTraj: Real-World Egocentric Human Trajectory
• GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation
• World Models for Learning Dexterous Hand-Object Interactions from Human Videos
• RAGrasp: A Retrieval-Augmented Framework with Diversity-Aware Modeling for Dexterous Grasp Generation
• ORION: Ordinal Neural Collapse as a Representation Prior for Visual Navigation
• What if? Emulative Simulation with World Models for Situated Reasoning
• PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation
• CoverPrune: Coverage-Driven Token Pruning for 3D VLMs via Optimal Transport
• A First Exploration of Neuromorphic OT-CFM for Multi-Speaker VSR
• MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos
• Self-Evolving Just-In-Time Memory for Proactive Embodied Safety
• Learning Active Perception for Pixel-Space Reasoning via Visual-Intent Stratified GRPO
• Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding
• Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresight
• EatVid-Bench: A Multimodal Fine-Grained Eating Behavior Video Dataset
• GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models
• Experts-Guided Unbalanced Optimal Transport for ISP Learning from Unpaired and/or Paired Data
• Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising
• Paying More Attention to Visual Tokens in Self-Evolving Large Multimodal Models
• E-M3RF: An Equivariant Multimodal 3D Re-assembly Framework
• Think While You Map: Asynchronous Vision-Language Agents for Incremental 3D Scene Graphs
• Walk through Paintings : Ego-centric World models from Internet Priors
• Cooking beyond Frames: A Stereo Event Camera Dataset in the Kitchen
• SNOW: Spatio-Temporal Scene Understanding with World Knowledge for Open-World Embodied Reasoning
• Mixture of Specialized Vision Experts: Unlocking Complementary Visual Insights for Faithful MLLM Reasoning
• RAE-NWM: Navigation World Model in Dense Visual Representation Space
• ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning
• GridFlow: Structured Latent Flow for Seamless City-Scale 3D Point Cloud Generation
• PriorEye: Geospatial Visual Priors for End-to-End Autonomous Driving
• FlowCIR: Semantic Transport via Flow Matching for Zero-Shot Composed Image Retrieval
• Geometry-Aware Spatio-Temporal Context Modeling for 4D Occupancy Forecasting
• SyntheticDoc: A Large Synthetic Dataset for Document Unwarping and Illumination Correction
• SuperFlex: Deformable Superquadrics for Point Cloud Decomposition
• Map2World: Segment Map Conditioned Text to 3D World Generation
• SP-TransientBench: A Real-Captured Single Photon Perception Benchmark
• DriveVA: Video Action Models are Zero-Shot Drivers
• NeSy-Route: A Neural-Symbolic Benchmark for Constrained Route Planning in Remote Sensing
• G2P: Gaussian-to-Point Attribute Alignment for Boundary-Aware 3D Segmentation
• TouchAnything: Diffusion-Guided 3D Reconstruction from Sparse Robot Touches
• Towards Practical Lossless Neural Compression for LiDAR Point Clouds
• VLZip: Unified Visual and Textual Compression for Interleaved Long-Context Modeling
• Identifying and Resolving Pitfalls of Knowledge-Based VQA Benchmarks: Auditing, Repairing, and Augmenting
• ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving
• Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding
• BitRIC: Efficient Neural Compression of LiDAR Range Images via Hierarchical Bitplanes
• TabletopGen: Tabletop Scene Generation and Interactive Simulation for Robotic Manipulation
• Hierarchical 3D Scene Graph Construction and Belief-based Planning for Semantic Navigation
• SegFly: A 2D-3D-2D Paradigm for Aerial RGB-Thermal Semantic Segmentation at Scale
• HitMem: Hierarchical Temporal 3D Memory with Multi-Modal Context-Aware Retrieval for Dynamic Environments
• From Hallucination to Grounding: Diagnosing Visual Spatial Intelligence via CRISP
• UBone3D: Physics-Rectified Conditional Flow Matching for Anatomical 3D Shape Completion from Ultrasound
• HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving
• Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs
• ASSCG: Just-Right Gating over Chattering for Fast–Slow LLM Planning in Autonomous Driving
• TriO: Tri-Modal Unsupervised Occupancy World Model for Anything Perception
• Boba: Batched Simulation for Physics-Based Gaussian Digital Twins
• Describe-Then-Act: Proactive Agent Steering via Distilled Language-Action World Models
• CMDR: Contextual Multimodal Document Retrieval
• CogniCred: A Dataset and Benchmark for Cognitive Credential Forgery Detection
• ContextFlow: In-Context Flow Matching for Robot Manipulation
• DoCoG: Mask-based Multi-Type Grounded Chain-of-Thought for Document QA
• When Sinks Help or Hurt: Unified Framework for Attention Sink in MLLMs
• OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents
• Masked Depth Modeling for Spatial Perception
• Twin-DAgger: Synergizing Digital Twins and Human Corrections for Efficient Robot Manipulation
• Revisiting Scene Graph Generation from the Perspective of Detector-Conditioned Reachability
• What You Ask is What You Ground: Bridging Question Intent to Temporal Evidence for Grounded VideoQA
• Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs
• See & Sniff: Learning Visuo-Olfactory Representations
• Improving Reasoning in Vision-Language Models via Perception Verified Self-Training
• OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams
• VisCritic: Visual State Comparison as Process Reward for GUI Agents
• Two-Way Street: Efficient VSLAM using Collaborative In-Sensor and Off-Sensor processing
• Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models
• C2E: Boosting Ego-Only 3D Object Detection via Multi-Teacher Contrastive Knowledge Distillation
• Lifting Ego World Models for Planning and Control
• Event-Driven Video Generation
• RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios
• Pano3D: Unified 3D Reconstruction and Panoptic Segmentation
• Learning Transferable Dynamics Priors from Action to World Modeling
• HighlightBench: Benchmarking and Diagnosing Markup-Driven Table Reasoning in Scientific Documents
• Learning Spectral and Polarimetric Clues for One-to-Multimodal Novel View Synthesis
• Structured Redundancy Modeling for Efficient Visual Token Pruning in High-Resolution MLLMs
• ESTANet: Efficient Online Error Detection in Procedural Videos via Prediction Inconsistency
• Error-Driven Scene Editing for 3D Grounding in Large Language Models
• SafeGuard: A Multi-Agent Perception-Reasoning Framework for Social-Risk AI-Generated Video Detection
• Beyond Description: Cognitively Benchmarking Fine-Grained Action for Embodied Agents
• The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models
• WALL-EVE: World Alignment with Rule Learning in Visual Environments
• Sentinel: Embodied Cooperative Spatial Reasoning and Planning
• HiPolicy: Hierarchical Multi-Frequency Action Chunking for Policy Learning
• The Telephone Game: Evaluating Semantic Drift in Unified Models
• MessyKitchens: Contact-rich object-level 3D scene reconstruction
• OmniSch: A Multimodal PCB Schematic Benchmark For Structured Diagram Visual Reasoning
• Spotlight: Identifying and Localizing Video Generation Errors Using VLMs
• UniDriveDreamer: A Single-Stage Multimodal World Model for Autonomous Driving
• MotionChain: Fine-Grained Video Motion Understanding via Structured Decomposition
• COMPASS: Grounding Composition-Intent Guidance in Unified Multimodal Models
• SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation
• Learning Sample-wise Rank-Aware Interpolation Weights for Composed Visual Data Retrieval
• Incentivizing Vision Language Models to Search for Long Video Question Answering
• Spatial Amsan: A Benchmark for Perception-Grounded Spatial Reasoning and Action Evaluation in Egocentric Manipulation
• The Language of Visual Attention: Modeling Scanpaths via Autoregressive Token Prediction
• PUF: Plug-and-Play Uncertainty-Aware Fusion for Online 3D Scene Graph Generation
• Unbalanced Optimal Transport for Efficient Visual Document Retrieval
• Beyond Final Answers: CRYSTAL Benchmark for Transparent Multimodal Reasoning Evaluation
• Wavelet-based Intra-video Counterfactual Reasoning for Video Question Grounding
• MarineEVT: Advancing Event-Centric Marine Video Understanding via Visual Tool Reasoning
• MARché: Fast Masked Autoregressive Image Generation with Cache-Aware Attention
• Pose Anything Anywhere: Model-free Object Poses from Arbitrary References
• UniQueR: Unified Query-based Feedforward 3D Reconstruction
• Multiple Images Distract Large Multimodal Models via Attention Fragmentation
• WildCity: A Real-World Dataset for City-Scale Rendering and Beyond
• Vulnerability of Privacy-Preserving Visual Localization against Diffusion-based Attacks
• Knowledge-Centric Agents for Workflow Generation in ComfyUI
• Video-Text Alignment Model for Sign Language Translation
• Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training
• WildWorld: A Large-Scale Dataset for Action-Conditioned World Modeling with Explicit State Annotations
• Ground3D-LMM: Fine-Grained 3D Point Grounding and Spatial Reasoning with LMM
• 3DWay: Generalizing Robot Manipulation via 3D Consistent Waypoints
• Predicting Consequences and Reinforcing Navigation Policies with Latent World Models
• SE-DETR: Explicit Semantic Exploration for Generalizability and Distinguishability in Video Temporal Grounding
• Hierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spaces
• CausalVAE as a Plug-in for World Models: Towards Reliable Counterfactual Dynamics
• OCA: ODE-Driven Cross-Attention for Image-to-Point-Cloud Registration
• When Thinking Hurts: Mitigating Visual Forgetting in Video Reasoning via Frame Repetition
• Multi-label Instance-level Generalised Visual Grounding in Agriculture
• EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models
• Robobench: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models as Embodied Brain
• Falcon: Functional Assembly and Language for Compositional Reasoning in X-ray
• Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs
• Spectral Evolution-Guided Token Pruning in Large Multimodal Models
• RadarGen: Automotive Radar Point Cloud Generation from Cameras
• On the Faithfulness of Post-Hoc Concept Bottleneck Models
• FlashVLM: Text-Guided Visual Token Selection for Large Multimodal Models
• Beyond Dense Futures: World Models as Structured Planners for Robotic Manipulation
• MV-STRIDE: Enabling MLLMs to Master Multi-View Spatial Reasoning via Hierarchical Capability Modeling
• PrintAnything: Learning Geometric Plan Map for 3D Printing G-code Generation from Unoriented Point Clouds
• AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution
• InstrAct: Towards Action-Centric Understanding in Instructional Videos
• AnchorPrune: Relevance-Anchored Contextual Expansion for Visual Token Pruning
• CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates
• SIGMA-Lane: Scale-pyramId Gated MAmba for Temporally Consistent Video Lane Detection
• Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning
• RAF: Reliability-Aware Fusion of Camera, LiDAR, and 4D RADAR for Robust 3D Object Detection in Adverse Weather
• TASE: Truncation-Aware Semantic Embeddings for 3D Scene Understanding and Editing
• Driving like yourself: A Benchmark for Closed-Loop Personalized End-to-End Autonomous Driving
• FUSE: A Flow-based Mapping Between Shapes
• ZTRS: Zero-Human Demonstration End-to-end Autonomous Driving with Trajectory Scorer
• Physically Grounded 3D Generative Reconstruction under Hand Occlusion using Proprioception and Multi-Contact Touch
• Ex-Sim(3)-Reg: 2D-3D Correspondence Pruning via Extended Sim(3) Registration
• 360° Image Perception with MLLMs: A Comprehensive Benchmark and a Training-Free Method
• LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows
• SEAR: Simple and Efficient Adaptation of Visual Geometric Transformers for RGB+Thermal 3D Reconstruction
• Co-Steer: Cross-Modal Collaborative Steering for Jailbreaking MLLMs
• BEVLM: Distilling Semantic Knowledge from LLMs into Bird's-Eye View Representations
• SparseDriveV2: Scoring is All You Need for End-to-End Autonomous Driving
• CoMind: Understanding Collaborative Human Activity from Multiple Minds and Views
• Fast and Scalable LiDAR Data Generation for Autonomous Driving Simulation without Raycasting
• Towards High-Resolution Visual Perception via Hierarchical Entity Exploration
• One Demonstration Is Enough for Real-World Robotic Reinforcement Learning
• MobileOcc: A Human-Aware Semantic Occupancy Dataset for Mobile Robots
• YouTube-Occ: Learning Indoor 3D Semantic Occupancy Prediction from YouTube Videos
• Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformer
• GroundSet: A Cadastral-Grounded Dataset for Spatial Understanding with Vector Data
• SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers
• SwiftWA: An Efficient Action-Centered World-Action Model
• When the City Teaches the Car: Label-Free 3D Perception from Infrastructure
• CabinSI: Omni-Cabin Spatial Reasoning through Explicit Visual Cognitive Maps
• VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model
• Zero-Shot Novel Depth Synthesis Using Foundation Models Scene Representations
• NarrativeTrack: Evaluating Entity-Centric Reasoning for Narrative Understanding
• Geo-DPO: Aligning Semantic Intent with Geometry for 3D Affordance Segmentation
• DRS-VPT: Directly Re-localizing in Scenes using a Vision and Point Transformer
• Event-LiDAR: 3D Eventification for Efficient Point Cloud Processing
• Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces
• DVG-WM: Disentangled Video Generation Enables Efficient Embodied World Model for Robotic Manipulation
• LiFlow: Flow Matching for 3D LiDAR Scene Completion
• Agentic Collaborative Cognition for Zero-Shot 3D Understanding
• SkillSpotter: Pose-Aware Multi-View Skilled Action Detection and Grading in Ego-Exo Videos
• Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching
• MobileManiBench: Simplifying Model Verification for Mobile Manipulation
• RelAfford6D: Relational 6D Affordance Graphs for Constraint-Driven Robotic Manipulation
• Understanding Cross-Rig Generalization in Automotive Perception: a Multi-Rig Benchmark and Rig Variation Metrics
• A scalar per patch from pre-trained ViTs enables fast moving navigation in the real world
• SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion
• VPA-WM: Vision-Priors-Aligned World Models for Robust Visual Reinforcement Learning
• MG2-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation
• Stabilizing Real-World Visual Active Tracking with Action-Smooth Test-Time Adaptation
• HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human–Scene Interactions
• Unpaired Geometry-Guided Sim2Real Translation for Autonomous Driving
• ViewFusion: Structured Spatial Thinking Chains for Multi-View Reasoning
• CRAG-MM-Diagnostics: Enabling Stage-Wise Analysis of Knowledge-Intensive VQA
• HippoCamp: Benchmarking Contextual Agents on Personal Computers
• SWIFT: Spatial-Window Integrated Frequency-aware Token Pruning for Efficient MLLMs on Edge Devices
• On Geometric Understanding and Learned Priors in Feed-forward 3D Reconstruction Models
• OmniFit: Multi-modal 3D Body Fitting via Scale-agnostic Dense Landmark Prediction
• Sparse-Aware Vector Quantization for Bandwidth-Efficient Collaborative 3D Semantic Occupancy Prediction
• SAFER-Activities: A Dataset for Smart Assessment of Fall Events and Routine Activities
• ConTrack: Constrained Hand Motion Tracking with Adaptive Trade-off Control
• HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task
• Taming LLMs for Codematic Indoor Scene Generation
• DocLayout-VL: A Foundational Model for Hierarchical, Open-set, and Promptable Document Layout Segmentation
• UniTac: A Unified Multimodal Model for Cross-Sensor Tactile Understanding and Generation
• Scene Generation at Absolute Scale: Utilizing Semantic and Geometric Guidance From Text for Accurate and Interpretable 3D Indoor Scene Generation
• HSDF-Lane: Height-Aligned Signed Distance Field with Semantic Lane Prior for 3D Lane Detection
• Eliciting Self-Verification in Multimodal Reasoning Agents with Reinforcement Learning
• Point Diffusion Mamba: Unified Diffusion-State-Space Modeling for Single-View 3D Reconstruction under Data Scarcity
• BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoning
• SPEAR: A Simulator for Photorealistic Embodied AI Research
• XDen-1K: A Density Field Dataset of Real-World Objects
• Enhancing Alignment for Unified Multimodal Models via Semantically-Grounded Supervision
• GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generation
• GeoMix: Descriptor-Free Visual Localization via Global Context and Multi-Detector Training
• What Matters in RL-Based Methods for Object-Goal Navigation? An Empirical Study and A Unified Framework
• CiQi-Agent: Aligning Vision, Tools and Aesthetics in Multimodal Agent for Cultural Reasoning on Chinese Porcelains
• PersonaDrive: Controllable Trajectory Prediction with Multi-Dimensional Driving Personas
• OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder
• Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decoding
• Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding
• E-VLA: Event-Augmented Vision-Language-Action Model for Dark and Blurred Scenes
• OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial Agents
• SLAM-Former: Putting SLAM into One Transformer
• VOCA: Visual Odometry with Codec Awareness
• GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding
• Looking Back and Forth: Cross-Image Attention Calibration and Attentive Preference Learning for Multi-Image Hallucination Mitigation
• FILT3R: Latent State Adaptive Kalman Filter for Streaming 3D Reconstruction

Spotlights

• CFM: Language-aligned Concept Foundation Model for Vision
• AdaBoosting Text Prompts for Vision-Language Models
• GeoNVS: Geometry Grounded Video Diffusion for Novel View Synthesis
• Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations
• DreamWorld: Geometry-Grounded Video Diffusion for 3D-Consistent World Modeling
• Molmo-Point: Better Pointing for VLMs with Grounding Tokens
• Edit3r: Instant 3D Scene Editing from Sparse Unposed Images
• Why Far Looks Up: Probing Spatial Representation in Vision-Language Models
• PriSplat: Propagating Reliable Multi-view Information for Distractor-Free 3DGS
• Do Not Leave a Gap: Hallucination-Free Object Concealment in Vision-Language Models
• ReSplat: Learning Recurrent Gaussian Splatting
• Learning to Deny: Action Denial in Multimodal Large Language Models
• SA-ResGS: Self-Augmented Residual 3D Gaussian Splatting for Next Best View Selection
• PuzLM: Solving Jigsaw Puzzles with Sequence-to-Sequence Language Models
• GaussianLens: Localized High-Resolution Reconstruction via On-Demand Gaussian Densification
• SubSplat: High-Resolution Pixel-aligned 3DGS via Sub-pixel Gaussian Reparameterization
• On Test-Time Scaling for Vision-Language Models
• Deformable Triangle Splatting: Flexible Primitives for Real-Time Radiance Field Rendering
• URoPE: Universal Relative Position Embedding across Geometric Spaces
• Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction
• Fourier Compressor: Frequency-Domain Visual Token Compression for Vision-Language Models
• EmbedCopilot: Evaluating Vision-Language Models for Hardware-Aware Embedded System Development
• RayRoPE: Projective Ray Positional Encoding for Multi-view Attention
• SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models
• TetraSDF: Analytic Isosurface Extraction with Multi-resolution Tetrahedral Grid
• Atlas is Your Perfect Context: One-Shot Customization for Generalizable Foundational Medical Image Segmentation
• On the Reliability of Cue Conflict and Beyond
• Mimicking Radiologists: A Coarse-to-Fine Framework with Structural Sparse Tokens for Dual-LLM Computed Tomography Report Generation
• One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models
• VesselTok: Tokenizing Vessel-like 3D Biomedical Graph Representations for Reconstruction and Generation
• TR-MoE: Temporal Reliability-Aware Mixture-of-Experts for Robust Tracking
• RPM-Distill: Physiology-guided Adaptive Cross-modal Distillation for Robust Remote Physiological Measurement
• Generating Multi-view Adversarial Examples for Visual Geometry Grounded Transformer
• Pushing the Limits of High-Resolution Weather Forecasting through Data Scaling
• Proteus: Model Leakage-Induced Adversarial Attack in Federated Learning
• Event-based Sparse-view Background-Oriented Schlieren Tomography
• Zero-shot Depth from Defocus
• Spectral Gating via Damped Oscillations for Adaptive Implicit Neural Representations
• Bayesian Self-Attention with Local Pixel Correlations for Lightweight Denoising Transformers
• When Higher Order Hurts: Pre-Asymptotic Order Collapse in Generative ODE Sampling — A Theory of Discretization–Learning Interaction
• PolarAPP: Beyond Polarization Demosaicking for Polarimetric Applications
• Structured-Noise Masked Modeling for Video, Audio and Beyond
• Stokes-Informed Diffusion for Robust Linear Polarization Estimation
• Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations
• Off the Planckian Locus: Using 2D Chromaticity to Improve In-Camera Color
• RoMa v2: Harder Better Faster Denser Feature Matching
• LoMa: Local Feature Matching Revisited
• Mind-to-Face: Neural-Driven Photorealistic Avatar Synthesis via EEG Decoding
• Gravity-aware partially calibrated absolute pose estimation from affine- or rotation-covariant features
• GenLCA: 3D Diffusion for Full-Body Avatars from In-the-Wild Videos
• Rolling Shutter Camera Self-Calibration
• Lost in the Tail: Addressing Geographic Imbalance in Urban Visual Place Recognition
• OpenCVL: An Open, Diverse, and Large-Scale Dataset for Fine-Grained Cross-View Localization
• MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control
• E-MOTION: A Dataset for Event-Based Scene Flow Estimation with Independent Moving Objects
• Progressive Pose-Guided 4D Animal Reconstruction from Monocular Video
• SPARC: Single-Pass Scaling for Motion Forecasting with Conformal Bayesian Last Layers
• Monocular Models are Strong Learners for Multi-View Human Mesh Recovery
• Training-free Controllable Motion Generation under Heterogeneous Constraints
• EgoExoMoCap: Distributed Human Motion Capture via Ego- and Exocentric Body Tracking from Head-Mounted Devices
• OVGGT: O(1) Constant-Cost Streaming Visual Geometry Transformer
• Interaction-Aware 4D Gaussian Splatting for Dynamic Hand-Object Interaction Reconstruction
• VKSR: Scalable Kernel Surface Reconstruction Using Vecchia's Approximation
• OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control
• RADmesh: Remesh-Aware Mesh Deformation
• CameraAnything: Refilming Videos with Arbitrary Camera Control
• Face Anything: 4D Face Reconstruction from Any Image Sequence
• A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models
• InSpace: Structure-Aware 3D Indoor Scene Generation from a Single 360° Image
• Grounding World Simulation Models in a Real-World Metropolis
• Silhouette-based Gait Foundation Model
• RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards
• Scaling Multi-Reference Image Generation with Dynamic Reward Optimization
• QVAM: Query-guided View-aware Adaptive Modulation for Aerial-Ground Person Re-Identification
• AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
• Divide and Align: Disentangled Vision-Language Learning for Text-Based Person Anomaly Search
• Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion
• EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing
• RiO-DETR: DETR for Real-time Oriented Object Detection
• Align and Segment: Unsupervised Learning for Building Segmentation From Misaligned Labels
• Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off
• Exclusivity-Guided Mask Learning for Semi-Supervised Crowd Instance Segmentation and Counting
• Push–Pull Attentional Anchoring for Diffusion Concept Erasure
• SelfMOTR: Revisiting MOTR with Self-Generating Detection Priors
• When Rubrics Fail: Error Enumeration as Reward for Reference-Free RL Post-Training
• PhenoLeaf-TS: A Time-Series Benchmark for Leaf Instance Segmentation, Tracking, and Growth Stage Classification
• Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting
• Event-based Gaze Control Systems for Real-time Spin Estimation in Professional Ball Games
• DoCoG: Mask-based Multi-Type Grounded Chain-of-Thought for Document QA
• SPEAR: A Simulator for Photorealistic Embodied AI Research
• SyntheticDoc: A Large Synthetic Dataset for Document Unwarping and Illumination Correction
• Predicting Consequences and Reinforcing Navigation Policies with Latent World Models
• NarrativeTrack: Evaluating Entity-Centric Reasoning for Narrative Understanding
• Incentivizing Vision Language Models to Search for Long Video Question Answering
• Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing
• Physically Grounded 3D Generative Reconstruction under Hand Occlusion using Proprioception and Multi-Contact Touch
• HumanOmni-Speaker: Identifying Who said What and When
• Cooking beyond Frames: A Stereo Event Camera Dataset in the Kitchen
• UniTac: A Unified Multimodal Model for Cross-Sensor Tactile Understanding and Generation
• TriO: Tri-Modal Unsupervised Occupancy World Model for Anything Perception
• See & Sniff: Learning Visuo-Olfactory Representations
• VOCA: Visual Odometry with Codec Awareness
• Bridging Vision and Language Concepts through Optimal Transport Semantic Flow
• PriorEye: Geospatial Visual Priors for End-to-End Autonomous Driving
• CoverPrune: Coverage-Driven Token Pruning for 3D VLMs via Optimal Transport
• When Sinks Help or Hurt: Unified Framework for Attention Sink in MLLMs
• MV2GF: Multi-view Pedestrian Detection with a Visual Geometric Foundation Model
• How to Teach Large Multimodal Models New Skills
• CooperScene: Multi-Modal Cooperative Autonomy Benchmark with C-V2X Communication Characterization
• Event-Driven Video Generation
• VIPS: Vehicle-Infrastructure Cooperative Planning Benchmark via Pseudo-Simulation

Spotlight Sessions

• Spotlight Session: 3D Reconstruction, Gaussian Splatting & Neural Rendering
• Spotlight Session: Vision-Language Models & Visual Foundation Models
• Spotlight Session: Robustness, Privacy & Learning Foundations
• Spotlight Session: Geometry, Localization, Matching & Motion
• Spotlight Session: Video Generation, Avatars & Dynamic Scene Modeling
• Spotlight Session: Visual Generation, Editing & Diffusion Models
• Spotlight Session: Visual Recognition, Tracking & Anomaly Detection
• Spotlight Session: Multimodal Models: Video, Documents & Cross-Sensor Learning
• Spotlight Session: Embodied AI, Robotics & Autonomous Driving

Tutorials

• From Perception to Simulation: The Emergence of World Models in Multi-modal Reasoning
• X-Sense: Cooperative Perception and Distributed Foundation Models for Smart Mobility
• From Hallucination Detection to Adversarial Defense: A Unified Framework for LVLM and LLM Safety

Workshops

• Event-Based Multimodal Vision: Imaging, Perception, and Understanding
• ViLMa – 2nd Workshop on Visual Localization and Mapping; From Optimization to 3D Foundation Models
• Towards Sim2Real Transfer and Unified Reasoning: 10th AI City Challenge
• OpenSUN3D: Workshop and Challenge on Open-World 3D Scene Understanding and Representations
• 4th LIMIT Workshop
• LifeGenIP: Life-Cycle Intellectual Property Governance of Visual Generative Models
• Instance-Level Recognition and Generation
• 3rd workshop on Fairness and Ethics in AI: facing the ChalLEnge through Model Debiasing (FAILED)
• CVNH - Computer Vision for Natural Heritage
• 14th International Workshop on Assistive Computer Vision and Robotics
• 3rd Workshop on Explainable CV (eXCV): Challenges and Opportunities in the Era of Foundation Models
• ECCV 2026 Workshop on Visual Persuasion (VisPer)
• Workshop on Artificial Intelligence for Multimedia Forensics and Disinformation Detection: AI4MFDD
• 2nd Workshop on MUCG: Multimodal Large Language Models for Unified Comprehension and Generation
• Hyperbolic Deep Learning for Computer Vision: 3th Beyond Euclidean Workshop
• TerraBytes II: Towards global datasets and models for Earth Observation
• Workshop on Human-AI Co-Creation
• Emerging Behaviors in Embodied AI for Achieving Robust Autonomy
• TwinWorld: Visual Intelligence for Built Environment Digital Twins
• Multimodal Digital Agents Workshop
• Uncertainty Quantification for Computer Vision UNCV
• The 2nd workshop on Generative AI for Audio-Visual Content Creation
• 3D Human Understanding: Towards Human-centric World Models
• Efficient-Visual Generation (EVG)
• On-device Embodied World Models
• World Models in the Loop: Towards Application-Driven World Model Evaluation
• The Path to Manufacturing: Evolving 3D Generation to Intelligent Computer-Aided Design
• Observing and Acting as Dexterous Hands
• Vision for Art and Culture (VISART) VIII
• 3rd Neural SLAM Workshop (NeuSLAM)
• SLoMO: Story-Level Movie Understanding and Audio Description
• 2nd Workshop on Benchmarking Evidence-Aligned Multimodal Reasoning (BEAM 2)
• CV4GOOD: Computer Vision for Humanitarian Action
• Recovering 6D Object Pose
• Medical Foundation Models and Benchmarks
• RetailVision7 - Revolutionizing the World of Retail
• DriveX - Foundation Models for Autonomous Driving
• Human motion-informed world models and socially intelligent action
• Low- Level Vision Frontiers with Generative AI, Preference Optimization, and Agentic Systems
• 11th Workshop and Competition on Affective & Behavior Analysis in-the-wild
• The 2nd Workshop on Curated Data for Efficient Learning (CDEL)
• Workshop on Neuromorphic Vision (NeVi)
• Safe World Models for Trustworthy Embodied AI
• 2nd Workshop on Foundation Data for Industrial Tech Transfer
• Structure-from-Motion in the Age of Deep Learning (SfM-ADL)
• AI4M3D: Artificial Intelligence for Medical 3D Vision
• Scalable 3D Scene Generation and 3D Geometric Scene Understanding
• UniWorld: Universal Representations for Perception, Reasoning, and World Modeling
• Workshop on Embodied Multimodal Reasoning in Physical Environments
• Physical AI: Understanding and Building the Physical World
• How to Build Effective World Models for Embodied AI
• Data Curation and Augmentation in Medical Imaging
• Embodied Agent and Dialog
• Real-World Video Representation Learning
• Perception Test: from Tabletop to City Scale
• Safe and Defensive Autonomous Driving
• BioImage Computing
• Force-Grounded, Cross-View Articulated Manipulation
• GAIA 2026: Geospatial AI and Foundation Models
• CONTEXTUS: Understanding Multi-Actor Scene Interaction in Context
• Large-scale Video Object Segmentation
• Workshop on Medical Video Understanding (MedVidU)
• Human Motion in Real-World and Clinical Setting -- Benchmark and Challenge on Parkinsonian Gait
• Functionality, Articulation, and Interaction for Modeling and Generating 3D Objects
• Computer Vision for MUltimedia Spatial intelligence through Time (MUSTCV, formerly CV4Metaverse)

Report issues here.