ECCV 2026 Schedule

Filter Events

TUE 8 SEP

9 a.m.

Workshop:

Hyperbolic Deep Learning for Computer Vision: 3th Beyond Euclidean Workshop

(ends 1:00 PM)

Workshop:

OpenSUN3D: Workshop and Challenge on Open-World 3D Scene Understanding and Representations

(ends 1:00 PM)

Workshop:

TwinWorld: Visual Intelligence for Built Environment Digital Twins

(ends 1:00 PM)

Workshop:

ViLMa – 2nd Workshop on Visual Localization and Mapping; From Optimization to 3D Foundation Models

(ends 1:00 PM)

Workshop:

Workshop on Geometric Intelligence: From Vision to Scientific Discovery

(ends 6:00 PM)

Workshop:

14th International Workshop on Assistive Computer Vision and Robotics

(ends 1:00 PM)

Workshop:

Agent in World: Living Worlds with Interactive Agents

(ends 1:00 PM)

Workshop:

Interactive Social Avatars with the 4th GENEA Gesture Generation Challenge

(ends 1:00 PM)

Workshop:

Workshop on Visual Perception and Reasoning in the Interactable World

(ends 6:00 PM)

Workshop:

Multimodal Digital Agents Workshop

(ends 6:00 PM)

Workshop:

Emerging Behaviors in Embodied AI for Achieving Robust Autonomy

(ends 6:00 PM)

Workshop:

Towards Sim2Real Transfer and Unified Reasoning: 10th AI City Challenge

(ends 1:00 PM)

Workshop:

Biomedical Image and Signal Computing for Unbiasedness, Interpretability, and Trustworthiness

(ends 6:00 PM)

Workshop:

2nd Workshop on Marine Vision

(ends 6:00 PM)

Workshop:

Instance-Level Recognition and Generation

(ends 1:00 PM)

Workshop:

The 2nd workshop on Generative AI for Audio-Visual Content Creation

(ends 1:00 PM)

Workshop:

Workshop on Human-AI Co-Creation

(ends 1:00 PM)

Workshop:

2nd Workshop on MUCG: Multimodal Large Language Models for Unified Comprehension and Generation

(ends 6:00 PM)

Workshop:

4th LIMIT Workshop

(ends 1:00 PM)

Workshop:

3rd Workshop on Explainable CV (eXCV): Challenges and Opportunities in the Era of Foundation Models

(ends 6:00 PM)

Workshop:

3rd workshop on Fairness and Ethics in AI: facing the ChalLEnge through Model Debiasing (FAILED)

(ends 1:00 PM)

Workshop:

ECCV 2026 Workshop on Viual Persuasion (VisPer)

(ends 1:00 PM)

Workshop:

LifeGenIP: Life-Cycle Intellectual Property Governance of Visual Generative Models

(ends 1:00 PM)

Workshop:

Uncertainty Quantification for Computer Vision UNCV

(ends 6:00 PM)

Workshop:

Workshop on Artificial Intelligence for Multimedia Forensics and Disinformation Detection: AI4MFDD

(ends 6:00 PM)

Workshop:

TerraBytes II: Towards global datasets and models for Earth Observation

(ends 6:00 PM)

Workshop:

3rd Workshop on Computer Vision for Ecology

(ends 6:00 PM)

Workshop:

Event-Based Multimodal Vision: Imaging, Perception, and Understanding

(ends 6:00 PM)

Workshop:

CVNH - Computer Vision for Natural Heritage

(ends 1:00 PM)

Tutorial:

The Fifth Hands-on Egocentric Research Tutorial with Project Aria from Meta

(ends 1:00 PM)

Tutorial:

Efficient MLLM Inference via Approximated and Exact Computing

(ends 1:00 PM)

2 p.m.

Workshop:

3rd Neural SLAM Workshop (NeuSLAM)

(ends 6:00 PM)

Workshop:

Privacy-Preserving Visual Localization and Mapping

(ends 6:00 PM)

Workshop:

Recovering 6D Object Pose

(ends 6:00 PM)

Workshop:

The Path to Manufacturing: Evolving 3D Generation to Intelligent Computer-Aided Design

(ends 6:00 PM)

Workshop:

Observing and Acting as Dexterous Hands

(ends 6:00 PM)

Workshop:

World Models in the Loop: Towards Application-Driven World Model Evaluation

(ends 6:00 PM)

Workshop:

Human-inspired Computer Vision

(ends 6:00 PM)

Workshop:

3D Human Understanding: Towards Human-centric World Models

(ends 6:00 PM)

Workshop:

Human-Centered Multimodal Intelligence in the Wild: Foundation Models and Beyond

(ends 6:00 PM)

Workshop:

Medical Foundation Models and Benchmarks

(ends 6:00 PM)

Workshop:

RetailVision7 - Revolutionizing the World of Retail

(ends 6:00 PM)

Workshop:

SLoMO: Story-Level Movie Understanding and Audio Description

(ends 6:00 PM)

Workshop:

2nd Workshop on Benchmarking Evidence-Aligned Multimodal Reasoning (BEAM 2)

(ends 6:00 PM)

Workshop:

Efficient-Visual Generation (EVG)

(ends 6:00 PM)

Workshop:

CV4GOOD: Computer Vision for Humanitarian Action

(ends 6:00 PM)

Workshop:

On-device Embodied World Models

(ends 6:00 PM)

Workshop:

Vision for Art and Culture (VISART) VIII

(ends 6:00 PM)

Workshop:

E.T.: Empirical Theory in representation Learning

(ends 6:00 PM)

Tutorial:

From Perception to Simulation: The Emergence of World Models in Multi-modal Reasoning

(ends 6:00 PM)

Tutorial:

Post-Training Diffusion Models: Enhancing Capabilities, Control, and Alignment

(ends 6:00 PM)

WED 9 SEP

9 a.m.

Workshop:

Perception Test: from Tabletop to City Scale

(ends 1:00 PM)

Workshop:

Physical AI: Understanding and Building the Physical World

(ends 6:00 PM)

Workshop:

Structure-from-Motion in the Age of Deep Learning (SfM-ADL)

(ends 1:00 PM)

Workshop:

3D in the Era of World Models

(ends 6:00 PM)

Workshop:

Embodied Agent and Dialog

(ends 1:00 PM)

Workshop:

How to Build Effective World Models for Embodied AI

(ends 6:00 PM)

Workshop:

Human–Scene Interaction (HSI): Towards Scene-Aware Motion, Communication, and Embodied Agents

(ends 1:00 PM)

Workshop:

Safe World Models for Trustworthy Embodied AI

(ends 1:00 PM)

Workshop:

Workshop on Embodied Multimodal Reasoning in Physical Environments

(ends 6:00 PM)

Workshop:

Safe and Defensive Autonomous Driving

(ends 6:00 PM)

Workshop:

DriveX - Foundation Models for Autonomous Driving

(ends 6:00 PM)

Workshop:

11th Workshop and Competition on Affective & Behavior Analysis in-the-wild

(ends 1:00 PM)

Workshop:

Human motion-informed world models and socially intelligent action

(ends 1:00 PM)

Workshop:

AI4M3D: Artificial Intelligence for Medical 3D Vision

(ends 1:00 PM)

Workshop:

Data Curation and Augmentation in Medical Imaging

(ends 6:00 PM)

Workshop:

BioImage Computing

(ends 6:00 PM)

Workshop:

Real-World Video Representation Learning

(ends 1:00 PM)

Workshop:

Scalable 3D Scene Generation and 3D Geometric Scene Understanding

(ends 1:00 PM)

Workshop:

Low- Level Vision Frontiers with Generative AI, Preference Optimization, and Agentic Systems

(ends 6:00 PM)

Workshop:

Third Workshop on Audio-Visual Generation and Learning (AVGenL)

(ends 6:00 PM)

Workshop:

2nd Workshop on Foundation Data for Industrial Tech Transfer

(ends 1:00 PM)

Workshop:

Multimodal Reasoning and Slow Thinking in the Large Model Era: Towards System 2 and Beyond

(ends 1:00 PM)

Workshop:

UniWorld: Universal Representations for Perception, Reasoning, and World Modeling

(ends 6:00 PM)

Workshop:

The 2nd Workshop on Curated Data for Efficient Learning (CDEL)

(ends 6:00 PM)

Workshop:

3rd International Workshop on Privacy-Preserving Computer Vision

(ends 1:00 PM)

Workshop:

The 3rd Workshop and Challenge on Unlearning and Model Editing (U&ME)

(ends 1:00 PM)

Workshop:

Women in Computer Vision

(ends 1:00 PM)

Workshop:

AI for Climate and Conservation (AICC)

(ends 6:00 PM)

Workshop:

Workshop on Neuromorphic Vision (NeVi)

(ends 1:00 PM)

Workshop:

3rd Workshop on More Exploration, Less Exploitation (MELEX)

(ends 1:00 PM)

Tutorial:

Building Large Video Generation Models: Data Processing, Architectural Insights, Optimization Methods and Evaluation Strategies

(ends 1:00 PM)

Tutorial:

From Hallucination Detection to Adversarial Defense: A Unified Framework for LVLM and LLM Safety

(ends 1:00 PM)

Tutorial:

X-Sense: Cooperative Perception and Distributed Foundation Models for Smart Mobility

(ends 6:00 PM)

2 p.m.

Workshop:

Computer Vision for MUltimedia Spatial intelligence through Time (MUSTCV, formerly CV4Metaverse)

(ends 6:00 PM)

Workshop:

Wild3D: 3D Modeling, Reconstruction, and Generation in the Wild

(ends 6:00 PM)

Workshop:

Force-Grounded, Cross-View Articulated Manipulation

(ends 6:00 PM)

Workshop:

Functionality, Articulation, and Interaction for Modeling and Generating 3D Objects

(ends 6:00 PM)

Workshop:

CONTEXTUS: Understanding Multi-Actor Scene Interaction in Context

(ends 6:00 PM)

Workshop:

Human Motion in Real-World and Clinical Setting -- Benchmark and Challenge on Parkinsonian Gait

(ends 6:00 PM)

Workshop:

Workshop on Medical Video Understanding (MedVidU)

(ends 6:00 PM)

Workshop:

Large-scale Video Object Segmentation

(ends 6:00 PM)

Workshop:

Visual object tracking and segmentation challenge VOTS2026 workshop

(ends 6:00 PM)

Workshop:

Privacy, Fairness, Accountability and Transparency in Computer Vision (PFATCV)

(ends 6:00 PM)

Workshop:

Third Workshop on Foundation and Generative Models in Biometrics

(ends 6:00 PM)

Workshop:

11th Workshop in Computer Vision in Plant Phenotyping and Agriculture

(ends 6:00 PM)

Workshop:

GAIA 2026: Geospatial AI and Foundation Models

(ends 6:00 PM)

Workshop:

Wearables AI Workshop: Towards Building Real-time Multimodal Contextual Assistants

(ends 6:00 PM)

Workshop:

The 4th AI for Visual Arts Workshop and Challenges (AI4VA)

(ends 6:00 PM)

Workshop:

3rd Workshop on Quantum Computer Vision and Machine Learning (QCVML)

(ends 6:00 PM)

Tutorial:

Evaluating Visual Foundation Models

(ends 6:00 PM)

Tutorial:

Aligning Diffusion Models with Human Preferences

(ends 6:00 PM)

THU 10 SEP

8 a.m.

Opening Ceremony [8:00-9:00]

(ends 9:00 AM)

9 a.m.

3D Reconstruction, Gaussian Splatting & Neural Rendering [9:00-10:30]

Spotlights 9:00-10:15

[9:00] GRF-Recon: Global Ray-Field Optimization for Long-Sequence Feed-forward Reconstruction

[9:05] Wat3R: Underwater 3D Geometry Learning without Underwater Annotations

[9:10] GeoNVS: Geometry Grounded Video Diffusion for Novel View Synthesis

[9:15] DreamWorld: Geometry-Grounded Video Diffusion for 3D-Consistent World Modeling

[9:20] Edit3r: Instant 3D Scene Editing from Sparse Unposed Images

[9:25] PriSplat: Propagating Reliable Multi-view Information for Distractor-Free 3DGS

[9:30] ReSplat: Learning Recurrent Gaussian Splatting

[9:35] SA-ResGS: Self-Augmented Residual 3D Gaussian Splatting for Next Best View Selection

[9:40] GaussianLens: Localized High-Resolution Reconstruction via On-Demand Gaussian Densification

[9:45] SubSplat: High-Resolution Pixel-aligned 3DGS via Sub-pixel Gaussian Reparameterization

[9:50] Deformable Triangle Splatting: Flexible Primitives for Real-Time Radiance Field Rendering

[9:55] Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction

[10:00] CubicSplat: Differentiable Vector Graphics via Error-Bounded Forward Relaxation

[10:05] RayRoPE: Projective Ray Positional Encoding for Multi-view Attention

[10:10] TetraSDF: Analytic Isosurface Extraction with Multi-resolution Tetrahedral Grid

(ends 10:30 AM)

Computational Imaging, Shape Recovery and Camera Geometry [9:00-10:30]

Orals 9:00-10:30

[9:00] Provable and Robust Wavefront Sensing via Self-Reference Interferometry

[9:15] Broadband Wide Field of View Imaging with Computational Mirrors

[9:30] Poppy: Polarization-Based Plug-and-Play Guidance for Enhancing Surface Normal Estimation

[9:45] A second-order theory of texture for depth from focus

[10:00] PRISM-VO: Scale-Aware Visual Odometry Using Photometric Plenoptic Bundle Adjustment

[10:15] Cross-View Yaw Estimation in Location Uncertainty with Line-Aligning Yaw Scoring

(ends 10:30 AM)

Vision-Language Models & Foundation Models [9:00-10:30]

Spotlights 9:00-10:10

[9:00] CFM: Language-aligned Concept Foundation Model for Vision

[9:05] AdaBoosting Text Prompts for Vision-Language Models

[9:10] Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations

[9:15] Molmo-Point: Better Pointing for VLMs with Grounding Tokens

[9:20] Why Far Looks Up: Probing Spatial Representation in Vision-Language Models

[9:25] Do Not Leave a Gap: Hallucination-Free Object Concealment in Vision-Language Models

[9:30] Learning to Deny: Action Denial in Multimodal Large Language Models

[9:35] PuzLM: Solving Jigsaw Puzzles with Sequence-to-Sequence Language Models

[9:40] GRADE: Benchmarking Discipline-Informed Reasoning in Image Editing

[9:45] On Test-Time Scaling for Vision-Language Models

[9:50] URoPE: Universal Relative Position Embedding across Geometric Spaces

[9:55] Fourier Compressor: Frequency-Domain Visual Token Compression for Vision-Language Models

[10:00] EmbedCopilot: Evaluating Vision-Language Models for Hardware-Aware Embedded System Development

[10:05] SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models

(ends 10:30 AM)

10:30 a.m.

Poster Session 1 [10:30-12:30]

Posters 10:30-12:30

Learning Physics-based Forward Model Corrections in Unrolled Networks for Diffuser-based Imaging

Denoising the Deep Sky: Physics-Based CCD Noise Formation for Astronomical Imaging

Bridge-UniPS: Bridging Calibrated Photometric Stereo toward Universal Photometric Stereo

RL-AWB: Deep Reinforcement Learning for Auto White Balance Correction in Low-Light Night-time Scenes

Ranked Activation Shift for Post-hoc Out-of-Distribution Detection

WiFlow: Estimating Optical Flow using WiFi Channel State Information

Stabilizing Deep Reconstruction Operators with Contractive Anchoring

Provable and Robust Wavefront Sensing via Self-Reference Interferometry

BLASt3R: Bundle Adjustment of Any Image Set with Multi-View Matching and Monocular priors

NeLU3D: Neural Inverse Structured Light without Modeling the Projector

Estimating Individual Tree Height and Species from UAV Imagery

From Phase to Phenomenon: Self-Supervised Learning of Subsurface Scattering with Minimal Phase-shift Inputs

The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding

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

SeeClear: Reliable Transparent Object Depth Estimation via Generative Opacification

High-speed Imaging through Turbulence with Event-based Light Fields

Any to Full: Prompting Depth Anything for Depth Completion in One Stage

Filterless Snapshot Hyperspectral Imaging using Guided Patch Diffusion

Modeling and Compensating Phase Error in High-speed 3D Reconstruction

Learning to Suppress SPAD-based LiDAR Flare

Broadband Wide Field of View Imaging with Computational Mirrors

Physically Grounded Monocular Depth via Nanophotonic Wavefront Encoding

ResilPhase: Plug-and-Play Phase Mapping and Noise-Resilient Macro-Trajectory Extrapolation for Diffusion Acceleration

Under One Sun: Multi-Object Generative Perception of Materials and Illumination

TPCNet: A Low-Light Image Enhancement Network Inspired by Triple Physical Constraints

AiSCREAM: Absolute Target Localization with Language-Conditioned Cross-View Alignment for Autonomous Vehicles

Video Generative Models as Geometry Learner

Parallax Portrait Matting

SynLF: Zero-Shot Metric Depth from Light Field Cameras via Physics-Grounded Synthesis

OneHSI: A Unified Hyperspectral Foundation Model with Physical Consistency

DP-BOA: Dirichlet-Process Birth-or-Assign for On-the-Fly Category Discovery

From Perspective to Fisheye Depth Estimation and Open-Vocabulary Segmentation

Leveraging Phase Information to Boost Unrolled Network Learning for Image Deblurring

Generalized Biomedicine Discovery

Poppy: Polarization-Based Plug-and-Play Guidance for Enhancing Surface Normal Estimation

Consistent Monocular Depth Estimation with Contact Region Boundary-Aware Refinement

EventSpecPS: Photometric Stereo with Multispectral Reflectance Using an Event Camera

Color Pass-Through via Camera-Display Coupling

λSplit: Self-Supervised Content-Aware Spectral Unmixing for Fluorescence Microscopy

A Mechanism-Driven Theory of Phase Transitions in Active Learning

Stable and Scalable Bundle Adjustment of Holistic 3D Structures

SiPhy: Single-Image Physical Property Reasoning

Dotting the Eye: An Intent-Driven Image Retouching Agent for Visual Focus Enhancement

FoundDP: Revisiting Weak Disparity Observability in Dual-Pixel Depth Estimation

Sticking Information in Plain Sight: Encoding and Detecting Hidden Stickers in the Real World

FlashBEV: Fast and Memory-Efficient Exact BEV Transformation with IO-Awareness

FlatLands: Generative Floormap Completion From a Single Egocentric View

Cast and Attached Shadow Detection via Iterative Light and Geometry Reasoning

A second-order theory of texture for depth from focus

Depth-guided Multi-view Exposure Bracketing for HDR Robot Vision

The Devil Is in the Dark Pixels: Toward Brightness Bias-Robust Denoising

SOMA: From Surface Observations to Muscle Anatomy

AIMold: An Autonomous AI-based Pipeline for Complex Mold Design

CSS-BA: Gate Guided Column Space Search for Bundle Adjustment

Asymmetric Anchoring: Opening the Black Box of MLLMs for Forgery Detection

FUSE: Filter-Free Unified Spatiotemporal Estimation of SpO2 via Wave-Transport Modeling

UHD-MFF: Shattering Barriers in Multi-Focus Ultra-High-Definition Image Fusion via Learnable Lookup Tables

Mapping Dark-Matter Clusters via Physics-Guided Diffusion Models

Geometry-Aware Visual Representation for Remaining Useful Life Prediction

Semantic Line Diffusion: Character-Consistent Line Art from text-annotated Storyboards

Dynamic Inverse Rendering for Enhanced Material-Lighting Decomposition

Video Can Teach PAN-Sharpening: PSF-Aware Cross-Domain Supervision

PRISM-VO: Scale-Aware Visual Odometry Using Photometric Plenoptic Bundle Adjustment

OmniPoint: Universal Monocular Metric Pointcloud from Any Camera

TurboMPLE: Joint Infrared Turbulence Mitigation and Physical Fields Estimation via Mutual Progressive Layered Extraction

Weather-Conditioned Depth Anything

Don’t Mask Out the Background! Natural-Light Photometric Stereo via Illumination Reconstruction

mmIR: Frequency-Space Inverse Rendering for 3D Millimeter-Wave Radar ADC Synthesis

TriNLOS: Triplane Representations for Neural Non-Line-of-Sight Imaging

ESNE: Efficient Surface Normal Estimation for LiDAR Point Clouds with Sequential Modeling and Variability Guidance

SFD-Net: Sharp Feature Detection Network Based on Local Geometric Features

Pixel-wise Planarity for High-Precision Monocular Plane Segmentation

Boosting 6D Object Pose Estimation via Monocular Depth Cues

Synthetic Sub-Aperture Phase Augmentation for Demosaicing 2×2 Shared Microlens Sensors

WildDepth: A Multimodal Dataset for 3D Wildlife Perception and Depth Estimation

PixVOD: Pixel-Distributed Direct Visual Odometry and Depth Estimation

Cross-View Yaw Estimation in Location Uncertainty with Line-Aligning Yaw Scoring

Partial Skeleton Visibility for Action Recognition: A Constrained Field-of-View Approach

CrossFeat: Bridging Imaging Modalities in Feature Descriptor Space

SONIC: Spectral Optimization of Noise for Inpainting with Consistency

Tricam-rPPG: A Multimodal Multispectral Dataset for remote Photoplethysmography

Learning Ego-Centric BEV Representations from a Perspective-Privileged View: Cross-View Supervision for Online HD Map Construction

The 3D Mirage: Probing and Taming 3D Hallucinations

Monte Carlo Energy Aggregation for Mobile 3D Gaussian Splatting

OmniRen: Neural Rendering wih Heterogeneous Scene Primitives

OREO: Fidelity Alignment in 3D Generation via On-the-fly Rendering-Editing Optimization

VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction

Real-Time LiDAR Gaussian Splatting SLAM via Geometry-Aware Covariance Coupling

SceneHI: High-Resolution 3D-Consistent Scene Texturing with Controllable Illumination

DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis

GRF-Recon: Global Ray-Field Optimization for Long-Sequence Feed-forward Reconstruction

VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignment

Multi4D: High-Fidelity Dynamic Gaussian Splatting via Multi-Level Competitive Allocation

RAGA: Real Time Ray Traced Gaussian Shadow Casting for 3DGS Avatar-Scene Interaction

Incremental Online Scene Reconstruction by 3D Gaussian Triangulation

Matryoshka Gaussian Splatting

Identity-Preserving Human Reconstruction from a Single Image via 3D Token Inference

Geometrically Consistent Multi-View Scene Generation from Freehand Sketches

Decoupled Illumination Priors for Spatially Controllable Multi-View Indoor Scene Relighting

Open-Vocabulary BEV Segmentation with 3D-Aware Geometric Constraints

GRAFT: Geometric Refinement and Fitting Transformer for Human Scene Reconstruction

OmniX: Any-view and Any-time 4D reconstruction via Feed-forward Trajectory Fields

NanoGS: Training-Free and Lightweight Gaussian Splat Simplification

SkySplat-OV: Generalizable Language Gaussian Splatting for Open-Vocabulary Scene Understanding from Sparse Satellite Views

Wat3R: Underwater 3D Geometry Learning without Underwater Annotations

ZeroSplat: Generalized Referring Segmentation in 3D Gaussian Splatting

StereoGS: Sparse-View 3D Gaussian Splatting via Stereo Priors

Sparse auto-regressive modeling for scene generation from multi-view images

Holo-Captioning: A Comprehensive Textual View of 3D Scenes

From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space

Global Pose Control for Generative View Synthesis in Normalized Object Coordinate Space

RefracGS: Novel View Synthesis Through Refractive Water Surfaces with 3D Gaussian Ray Tracing

StructSplat: Generalizable 3D Gaussian Splatting from Uncalibrated Sparse Views

IRIS: Intersection-aware Ray-based Implicit Editable Scenes

World Reconstruction From Inconsistent Views

GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherence

Geo-ID: Test-Time Geometric Consensus for Cross-View Consistent Intrinsics

AirSplat: Alignment and Rating for Robust Feed-Forward 3D Gaussian Splatting

FaCT-GS: Fast and Scalable CT Reconstruction with Gaussian Splatting

GAP-Track: Bridging the Resolution Gap for Cross-Resolution RGBT Tracking

GaINeR: Geometry-Aware Implicit Neural Representation for Image Editing

Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction

Geometric Distillation from Rectified Stereo: Leveraging Epipolar Cues for Monocular Depth

PanoLess: Environment Reconstruction from Partial Reflective Views

CARA: Collision-Aware Resolution Adaptation for Multiresolution Hash Encoding Based Image Fitting

GeoNVS: Geometry Grounded Video Diffusion for Novel View Synthesis

FillGS: Filling Observation Gaps in 4D Gaussian Splatting via Viewpoint-Time Selection and Generative Refinement

Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures

Confidence-Based Mesh Extraction from 3D Gaussians

InstantHDR: Single-forward Gaussian Splatting for High Dynamic Range 3D Reconstruction

ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generation

Edit in 2D, Verify in 3D: Reinforcement Learning for Multi-view Consistent Scene Editing

SpectralSplats: Robust Differentiable Tracking via Spectral Moment Supervision

Do Flat Minima Improve Sparse Novel View Synthesis?

ViewSplat: View-Adaptive Dynamic Gaussian Splatting for Feed-Forward Synthesis

Fast and Compact 3D Gaussian Splatting with Polarized Opacity Prior

DINO-SLAM: DINO-Informed RGB-D SLAM for Neural Implicit and Explicit Representations

COSY: Compositional 3DGS Synthesis for Disentangled Human Head Editing

SkyLume: A Large-Scale Multi-Illumination Aerial Benchmark for Urban Scene Reconstruction and Beyond

DreamWorld: Geometry-Grounded Video Diffusion for 3D-Consistent World Modeling

Active View Selection with Perturbed Gaussian Ensemble for Tomographic Reconstruction

LiteGS: a high-performance framework to train 3dgs in subminutes via system and algorithm codesign

REFINE: Super-efficient Pruning for 3D Gaussian Splatting via Rendering-Free Primitive Importance

Interact3D: Compositional 3D Generation of Interactive Objects

HandSCS: Structural Coordinate Space for Animatable Hand Gaussian Splatting

UniGeo: Unifying Geometric Constraints for Camera-Controllable Image Editing via Video Priors

HairOrbit: Multi-view Aware 3D Hair Modeling from Single Portraits

Nexels: Neurally-Textured Surfels for Real-Time Novel View Synthesis with Sparse Primitives

Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-View Videos

EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learning

Inclusive Interactive Collisions for Multi-View Consistent Compositional 3D Generation

3DGS3: Joint Super Sampling and Frame Interpolation for Real-Time Large-Scale 3DGS Rendering

FreeGen: Feed-Forward Reconstruction–Generation Co-Training for Free-Viewpoint Driving Scene Synthesis

Edit3r: Instant 3D Scene Editing from Sparse Unposed Images

PointSplat: Compact Gaussian Splatting via Human-Centric Prediction

MeGAS: Thermomechanical Dynamic Gaussian Splatting for Thermophysical Scene Editing

VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM

IMMoE: Incomplete Multi-View Anomaly Detection via Mixture of View Experts Fusion

AVSplat:Dense-View Feed-Forward 3D Gaussian Splatting with Assist-View Preconditioning

Multi-view Multi-vehicle Driving Dataset for Novel View Synthesis

Enhancing Embodied Reasoning and Grounding by Novel View Synthesis

Reflection-aware generative novel view synthesis

Manifold-Aware Spectral Compaction: A Graph Signal Processing Perspective on Online Gaussian Reduction for 3DGS SLAM

Instant Expressive Gaussian Head Avatars at Over 100 FPS

DualDiff3D: Dual Structure-Appearance Diffusion Priors for Reliability-Enhanced 3D Gaussian Splatting

Towards Geometry-Grounded Dense Semantic Matching with VGGT Priors

Sparse-View Surface Reconstruction using Gaussian Splatting through High-Confidence Depth Propagation with Normal Priors

PriSplat: Propagating Reliable Multi-view Information for Distractor-Free 3DGS

City-Level 3D Surface Reconstruction with Viewpoint Orientation Partitioning and Scene Completion

AutoWeather4D: Autonomous Driving Video Weather Conversion via G-Buffer Dual-Pass Editing

PaD-GS: Leveraging Distortion Map for Panoramic Gaussian Splatting

Render-FM: Feedforward Model for Real-time Photorealistic Volumetric Rendering

DR-GS: Physically-Based Deformable and Relightable 2D Gaussians

StructureGS: Structure-aware Gaussian Splatting for Articulated Object Reconstruction

Geometry-Aware Style Transfer in 3D Gaussian Splatting

Rotate Your Character: Revisiting Video Diffusion Models for High-Quality 3D Character Generation

3D Gaussian Splatting Compression with Object Scalability

InstGS: Shared-Template Gaussian Instancing for Object-Redundancy-Free Rendering

CoIn: Comprehensive 2D-3D Inpainting with Gaussian Splatting Guidance

Efficient Camera Pose Augmentation for View Generalization in Robotic Policy Learning

Cube-Splat: High-Fidelity 360° Gaussian Splatting SLAM via Cubemap Factorization and Adjoint-Consistent Optimization

ReSplat: Learning Recurrent Gaussian Splatting

AnchorSplat: Fast and Structure Consistent Detail Synthesis for Gaussian Splatting

AdaptiveSplat: Texture Aware Controllable 3D Gaussian Allocation for Feed-Forward Reconstruction

Denoising-GS: Gaussian Splatting with Spatial-aware Denoising

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

DINOv3D: 2D-3D Joint Optimization for Unified Spatial Understanding

Capacity-Controlled Multi-View Stylization of 3D Gaussian Splatting

MVGS: Multi-view Regulated Gaussian Splatting for Novel View Synthesis

MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors

SharpGS: Sharpness-Preserving 3D Gaussian Splatting with Differentiable Blur-Driven Density Control

GlassGS: Geometry and Concept-Aware 3D Gaussian Splatting for Reflective Enclosures

ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views

SA-ResGS: Self-Augmented Residual 3D Gaussian Splatting for Next Best View Selection

MAC-Splat: Multi-Attribute Consistency for High-Fidelity Sparse-View Reconstruction

BEV-GS: Feed-forward Gaussian Splatting in Bird’s-Eye-View for Road Reconstruction

CapFrame: Text-Instructed Viewpoint Grounding in 3D Gaussian Scenes via Geometric Pseudo Labels

Racing in Volume with Flow Ensembles

EAGS: Error-Aware Gaussian Splatting with Dual-Confidence-Guided Modeling for Uncalibrated Driving Scenes

LiteMatch: Lightweight Zero-Shot Stereo Matching via Cost Volume Stabilization

Fast Spatial Memory with Scalable Elastic Test-Time Training

ReGen3D: Generalizable Unified Representation Learning for 3D Understanding

PointGT: Simultaneous Geometric and Textural Editing for Point-Based Representations

P-CORE: Self-Supervised Surface Consistency for Point-Based Neural Editing

Large-Scale Light Field Synthesis from Videos Enables Geometrically Consistent Bokeh Editing

GAINS: Gaussian-based Inverse Rendering from Sparse Multi-View Captures

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

Relaxed Rigidity with Ray-based Grouping for Dynamic Gaussian Splatting

WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images

MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics

Geometry-Preserving in 3D Gaussian Splatting for LiDAR-Camera Extrinsic Calibration

One-Shot Feed-Forward 360° Animatable Avatar via Inpainted UV-Space Gaussian Modeling

DLGStream: Dynamic Language-embedded Guassian Splatting for Open-vocabulary Enabled Free-viewpoint Video Streaming

GaussianLens: Localized High-Resolution Reconstruction via On-Demand Gaussian Densification

Temporally Aware Densification for Dynamic 3D Gaussian Splatting

Robust and Efficient Monocular 3D Gaussian SLAM for Kilometer-Scale Outdoor Scenes

LVSPM: Long Sequence View Synthesis and Pose Estimation Model

FLM-Occ: Feed-forward Likelihood Maximization for Efficient Indoor Occupancy Prediction

Generalizable Neural Reconstruction of High-Fidelity Surfaces via Sparse Volumetric Representations

DASAM3D: A Unified Foundation Model for Enhanced 3D Scene Reconstruction and Segmentation

UniTriSplat: A Unified 3D Gaussian Splatting Framework with Uniform Spherical Rasterization for Universal Cameras

DreamEdit3D: Personalization of Multi-View Diffusion Models for 3D Editing

Gaussians on Fire: High-Frequency Reconstruction of Flames

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

R3RECON: Radiance-Field-Free Active Reconstruction via Renderability

UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization

SubSplat: High-Resolution Pixel-aligned 3DGS via Sub-pixel Gaussian Reparameterization

Raymap-Guided Coupling for Drift-Robust Unposed Feed-Forward 3D Reconstruction

KISS-GS: 3D Gaussian Splatting Compression Kept Simple

SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training

Drop-In Perceptual Optimization for 3D Gaussian Splatting

SkipGS: Post-Densification Backward Skipping for Efficient 3DGS Training

Predictive Photometric Uncertainty in Gaussian Splatting for Novel View Synthesis

Structure Gaussian Splatting SLAM

F⁴Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting

InceptionGS: Generative Bootstrapping for Large-Scale Gaussian Splatting under Unstructured View Sampling

Director: Instance-aware Gaussian Splatting for Dynamic Scene Modeling and Understanding

TRiGS: Temporal Rigid-Body Motion for Scalable 4D Gaussian Splatting

Targeted Structure Completion for Sparse-View 3D Reconstruction in Autonomous Driving

RaysUp: Ultra-light Universal Feature Upsampling via Geometry-Aware Ray Representation

Deformable Triangle Splatting: Flexible Primitives for Real-Time Radiance Field Rendering

FLEG: Feed-Forward Language Embedded Gaussian Splatting from Any Views via Compact Semantic Representation

ActiveStructure: Plane Scene Graph-Guided Active 3D Gaussian Splatting

3D Gaussian Texture for Real-time Mesoscale Appearance Synthesis and Rendering

Geometry Grounding: Elevating Blind Distortion Correction with 3D Structural Priors

The Sterkfontein Caves Dataset: A Novel View Rendering Challenge from the Cradle of Humankind

GeoV2V: Geometry-Grounded Video Diffusion Model for Driving Scene Generation

AGE: Agentic Gaussian Editing in 3D Scenarios

Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views

GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens

Proto-Gaussian: MRI Modality Translation Based on Learnable Structural Prototypes and 2D Gaussian Splatting

∂DIBR: Differentiable Depth Image-based Rendering for Fast Novel View Synthesis

Geometric Probing for Isotropic Optimization Manifold in Sparse-View 3D Gaussian Splatting

WilLaGS: Latent-Conditional 3D Appearance Fields for Robust Gaussian Splatting In-the-Wild

Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction

TriSplat: Adaptive Triplane for Sparse-View Large-Scale Scene Reconstruction

IndoorSplat: Enhanced Indoor Scene Reconstruction with Structured 2D Gaussian Splatting

MVFusion-GS: Motion-Variance Guided Temporal Attention for High-Quality Dynamic Gaussian Splatting

HiReFF: High-Resolution Feedforward Human Reconstruction from Uncalibrated Sparse-View Video

When 3D Gaussian Splatting Recovers Real Surfaces

PIC: Revisiting INR for Image Coding with Fast Encoding and Sub-Millisecond Decoding

Geometry-Propagated Gaussian Splatting for Aerial Sparse Novel View Synthesis

Improving Sparse-View 3DGS Generalization via Flat Minima Optimization

Graph-GSReg: Leveraging 3D Scene Graphs for Gaussian Splatting Registration

LEGO: Leveled Language Gaussian Splatting

NoPA: Non-Parametric Online 3D Scene Graph Generation

Triangle Splatting SLAM

Towards Alias-Free 4D Gaussian Representations with Motion-Aware Filtering

Latent Fusion: Decoding Consolidated 3D Geometry from Feed-forward Geometry Transformer Latents

Novel View Synthesis as Video Completion

Wid3R: Wide Field-of-View 3D Reconstruction via Camera Model Conditioning

MLP Splatting: Object-Centric Neural Fields

RaPTGS: Render-Agnostic Post-Training Compression of 3D Gaussian Splatting

Fourier Splatting: Generalized Fourier encoded primitives for scalable radiance fields

SyncFix: Multi-View Consistent Diffusion Refinement of 3D Reconstructions

CubicSplat: Differentiable Vector Graphics via Error-Bounded Forward Relaxation

CAM3R: Camera-Agnostic Model for 3D Reconstruction

FixAnything: 3D-Consistent Rendering Refinement via Video Generative Priors

3D-ReGen: A Unified 3D Geometry Regeneration Framework

CoDePose: Multi-View 3D Human Pose Estimation via Coupled 2D-3D Denoising Diffusion

SMP-UWGS: Coupled Physics-Geometry Optimization for Scalable Multi-Partition Underwater 3D Reconstruction

Diversity-Aware View Partitioning for Scalable VGGT

Extending a Large View Synthesis Model for Multi-view Panoptic Segmentation

StratoSplat: Taming Layered Regularities for Sparse Aerial 3D Gaussian Splatting

ReInGS: Re-Initializing 3D Gaussians against Sparsity Discrepancy in Few-Shot Novel View Synthesis

LinStereo: Linear-Complexity Global Attention for Multi-Scale Iterative Stereo Matching

Steering 3D Generations: Preference Alignment via Direct Reward and Preference Optimization

SupIR-GS: Thermal Infrared Super-Resolution Novel View Synthesis with Imaging-Calibrated 3D Gaussian Splatting

EGGS: Explicitly Granular 3D Gaussian Splatting via Luma-Aware and Volume-Preserving Attribute Factorization

RayRoPE: Projective Ray Positional Encoding for Multi-view Attention

Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation

DecoupleGS: Interactive 3D Gaussian Splatting for End-to-End Autonomous Driving Testing

TopoGS: Planar Reconstruction via Topology-Aware 3D Gaussian Splatting

X-SG2S: Safe and Generalizable Gaussian Splatting with X-dimensional Watermarks

Online Segment 3D Gaussians via Launching Virtual Drones

Dynamic-Robust Photometric–Semantic Reconstruction for Open-Vocabulary 3D Scene Understanding

Minute4D: Training High-Fidelity 4D Gaussian Splatting in One Minute

BioMTBee: Biologically Constrained Multi-View Template-Based 3D Reconstruction of Bumblebee

RoomPlanner: Reachability-Aware View Sampling for Text-to-Room 3D Gaussian Splatting

MedGSSR: Generalizable Medical Image Super-Resolution 3D Reconstruction via Hierarchical Feed-forward Gaussian Splatting

SPECSIA: Stylization Dataset for Novel-View Enhancement in Drawing-based 3D Animation

Physically Grounded Dual-Opacity Gaussian Splatting for Joint RGB-TIR Reconstruction

Flash-Refine: Frustum-Guided Local Incremental Learning for Efficient 3D Gaussian Splatting Completion

TetraSDF: Analytic Isosurface Extraction with Multi-resolution Tetrahedral Grid

From Blobs to Spokes: High-Fidelity Surface Reconstruction via Oriented Gaussians

ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in 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

TIIF-Bench: How Does Your T2I Model Follow Your Instructions?

TransVLM: A Vision-Language Framework and Benchmark for Detecting Any Shot Transitions

Disentangling Pictorial Cue Understanding from Language Bias in VLMs via Depth Ordering Task

LEAP-VLA: Latent-Enhanced Action Prototyping via Continuous Residual Latent Spaces for Vision-Language-Action Models

Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models

Token-Based Affordance Grounding with Large Vision-Language Models

A4-Agent: An Agentic Framework for Zero-Shot Affordance Reasoning

GEM: Generative Supervision Helps Embodied Intelligence

Less is More: Reducing Complexity in Vision-Language-Action Systems

CFM: Language-aligned Concept Foundation Model for Vision

EvoVLA: Self-Evolving Vision-Language-Action Model

SPOT-E: Test-Time Entropy Shaping with Visual Spotlights for Frozen VLMs

CVSBench: A Comprehensive Benchmark for Cross-view Spatial Reasoning and Dreaming

Hybrid Advantage Estimation with Unified Critic for VLM Agentic Reinforcement Learning

RAU: Reference-based Anatomical Understanding with Vision-Language Models

DiaDem: Advancing Dialogue Descriptions in Audiovisual Video Captioning for Multimodal Large Language Models

OpenGround: Planning-based Online Perception for Open-World 3D Visual Grounding

Trustworthy Image Authentication using Forensic Knowledge Graphs

AutoV: Loss-Oriented Ranking for Visual Prompt Retrieval in LVLMs

Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models

PercepTax: Benchmarking Cross-Property Reasoning in Vision-Language Models

LongVQUBench: Benchmarking Long-Term Video Quality Understanding of Vision-Language Models

Foveated Reasoning: Stateful, Action-based Visual Focusing for Vision-Language Models

AdaBoosting Text Prompts for Vision-Language Models

Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models

Guardrail-Agnostic Societal Bias Evaluation in Large Vision-Language Models

Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction

TruthLens: Object Hallucination Detection via Self-Evaluating Truthfulness Scores in LVLMs

How Far Are Vision-Language Models from Constructing the Real World? A Benchmark for Physical Generative Reasoning

GKDT: General Keypoint Detection Transformer

Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations

C3-Bench: A Context-Aware Change Captioning Benchmark

To Adapt or Not to Adapt? Selective Adaptation for Vision-Language Models

VersaViT: Enhancing MLLM Vision Backbones via Task-Guided Optimization

Domain Generalization via Text-Anchored Information Bottleneck

Text-Guided 6D Object Pose Rearrangement via Closed-Loop VLM Agents

VisCoP: Visual Probing for Video Domain Adaptation of Vision Language Models

Gaze-to-text Generation: Beyond Categorical Decoding of Human Attention

See Only When Needed: Context-Aware Attention Intervention for Hallucination-Free LVLMs

RSICCLLM: A Multimodal Large Language Model for Remote Sensing Image Change Captioning

PhenoLIP: Phenotype Guided Medical Vision–Language Pretraining

MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robots

Exploring Efficient Reasoning Segmentation with Small Language Models

Beyond Atomic Layouts: Compositional Design Understanding with Vision-Language Models

Molmo-Point: Better Pointing for VLMs with Grounding Tokens

Benchmarking Vision-Language Models for Microscopic Plant Image Understanding

HIVE: Understanding Post Hallucination Reasoning in Vision Language Models

Beyond Language: Grounding Referring Expressions with Hand Pointing in Egocentric Vision

VLA Knows Its Limits

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking

Neural Gate: Mitigating Privacy Risks in LVLMs via Neuron-Level Gradient Gating

Attention-based Vision-Language Memory for Spatial Reasoning

NaVLM-PVC: Progressive Visual Compression for Efficient Native-Resolution Encoding in MLLMs

TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs

Zoom-IQA: Image Quality Assessment with Reliable Region-Aware Reasoning

Gripper-aware Vision Language Action Models

MonoSR: Open-Vocabulary Spatial Reasoning on Monocular Images

Skin-R1: Clinical Knowledge-Guided Dermatological Diagnosis Using Vision-Language Models

Why Far Looks Up: Probing Spatial Representation in Vision-Language Models

DiCoBench: Benchmarking Multi-Image Fine-Grained Perception via Differential and Commonality Visual Cues

PanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-based 3D Visual Grounding

Are Video Reasoning Models Ready to Go Outside?

Towards Reliable Medical Large Vision-Language Models via Counterfactual Preference Optimization

ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models

SDSA: Shallow-Deep Squeezing Adapter for Vision-Language Models

Do Not Leave a Gap: Hallucination-Free Object Concealment in Vision-Language Models

Concept-as-Tree: A Controllable Synthetic Data Framework Makes Stronger Personalized VLMs

Gradient sparsity regularization for training unlearning-compatible models

VisWordBench: Bridging the Gap in Cross-modal Reasoning for Multimodal Large Language Models

The Cost of Reasoning: Chain-of-Thought Induces Overconfidence in Vision-Language Models

3D-Layout-R1: Structured Reasoning for Language-Instructed Spatial Editing

Towards Robustness against Typographic Attack with Training-free Concept Localization

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

Read or Ignore? A Unified Benchmark for Typographic-Attack Robustness and Text Recognition in Vision-Language Models

HUGE-Bench: A Benchmark for High-Level UAV Vision-Language-Action Tasks

Towards More Efficient Decoding for Autoregressive Vision-language-action Models

Visual Prompt Discovery via Semantic Exploration

From Masks to Pixels and Meaning: A New Taxonomy, Benchmark and Metrics for VLM Image Tampering

Learning to Deny: Action Denial in Multimodal Large Language Models

DIVA: Instruction-Aware Vision Token Pruning via Dual-Probe Attention Discrepancy

Direct Preference Optimization for Perceptual Alignment via Vision-Language Consistency

ME-IQA: Memory-Enhanced Image Quality Assessment via Re-Ranking

CARE: Causally-Aligned Reasoning Exploration for Medical Large Language Models

Learning from Primitive: Probing Visual Reasoning of LVLMs via Counting

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

VoxAnchor: Explicit Voxel-Semantic Grounding for Spatial Understanding in Videos

VLA-R1: Enhancing Reasoning in Vision-Language-Action Models

E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation

M2Tok: Multi-head Multi-codebook Discrete Action Tokenization for Vision-Language-Action Models

LIBERO-Safety: A Comprehensive Benchmark for Physical and Semantic Safety in Vision-Language-Action Models

PuzLM: Solving Jigsaw Puzzles with Sequence-to-Sequence Language Models

ScenarioControl: Vision-language Controllable Vectorized Latent Scenario Generation

WeatherReasonSeg: A Benchmark for Weather-Aware Reasoning Segmentation in Visual Language Models

ScAle: Attention Head Scaling as a Minimal Adapter for Spatial Reasoning in Vision–Language Models

GenRecal: Generation after Recalibration from Large to Small Vision-Language Models

CURE: Cumulative Knowledge Reuse for Efficient Device-Server Hybrid Inference in Vision-Language Models

GAIA: A Data Flywheel System for Training GUI Test-Time Scaling Critic Models

Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models

DIGS: Differentiable, Incremental, Global, Scalable Pruning for Language Models

Same Pool, Different Answer: Stable Best-of-N Selection for Vision-Language Models

SAFE-Pruner: Semantic Attention–Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation

Do Vision Language Models Recognize Visual Ambiguity?

ATOMIC: A Domain-Specific Vision-Language Model for Transmission Electron Microscopy

Evaluating Reasoning Coherence in Video Generative Models with Text and Visual Hints

GRADE: Benchmarking Discipline-Informed Reasoning in Image Editing

GEO-Detective: Unveiling Location Privacy Risks in Images with LLM Agents

From Macro to Micro: Benchmarking Microscopic Spatial Intelligence on Molecules via Vision-Language Models

Restoring Linguistic Grounding in VLA Models via Train-Free Attention Recalibration

Where to Look Matters: Learning Influential Views for VLM-based 3D Visual Grounding

CASA: Cross-Attention over Self-Attention for Efficient Vision-Language Fusion

Dynamic Cluster Data Sampling for Efficient and Long-Tail-Aware Vision-Language Pre-training

On Test-Time Scaling for Vision-Language Models

Overlap-Consistent View Decomposition for Adapting Vision--Language Models to 360° Panoramas

SpatiO: Adaptive Test-Time Orchestration of Vision-Language Agents for Spatial Reasoning

Why Do Vision Language Models Struggle To Recognize Human Emotions?

StarDojo: Benchmarking Open-Ended Behaviors of Agentic Multimodal LLMs in Production–Living Simulations with Stardew Valley

EGM: Efficient Visual Grounding Language Models

BeTTER: Diagnose the Illusion of Embodied Reasoning in Vision-Language-Action Models

3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering

HCSU: A Dataset and Benchmark for Fine-Grained Historical Calligraphy Style Understanding

Decompose, Compare, and Decide: Multimodal LLMs are Implicit Few-Shot Learners

Show Me Examples: Inferring Visual Concepts from Image Sets

DEX-AR: A Dynamic Explainability Method for Autoregressive Vision-Language Models

PARL-VLA: Pruning-Aware On-Policy Reinforcement Learning for Vision-Language-Action Model

Art Beyond Semantics: Sheaf-Informed Contrastive Learning for Multi-Relational Representations

URoPE: Universal Relative Position Embedding across Geometric Spaces

CulinaryCut: A Physics-aware Vision-Language-Action Benchmark for Food Cutting via Material Point Method

EoS-FM: Can an Ensemble of Specialist Models act as a Generalist Feature Extractor?

VERITAS: A Multi-agent Co-scientist for Verifiable Image-Derived Hypothesis Testing

StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning

Unlocking Few-Shot Capabilities in LVLMs via Prompt Conditioning and Head Selection

From Gaze to Meaning: An AI Agent for Unified Zero-Shot Grounding and Explanation

Natural Image Pretraining Improves Abstract Reasoning

Reinforcing Vision-Language Models for Image Quality Assessment with Grounding Process Rewards

MVPruner: Dynamic Token Pruning for Accelerating Multi-view Vision-Language Models in Autonomous Driving

Seeing Isn't Orienting: A Cognitively Grounded Hierarchical Benchmark for Object Orientation in MLLMs

Ceptor: Vision-Language Model-Infused Diverse Guidance for Detecting Anything

Gender Bias in Vision-Language In-Context Learning

Less is More: A Simple yet Effective Object-Centric Prompting Strategy for Vision-Language Reasoning in Autonomous Driving

Fourier Compressor: Frequency-Domain Visual Token Compression for Vision-Language Models

Personalize Your Large Vision-language Models With In-context Prompt Tuning

TecoPrompt: Temporal-Conservative Prompt Learning for Vision-Language Models

EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon Reasoning

LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?

DICE: Disentangled Instance-Class knowlEdge prompt tuning via SAE for Vision-Language Models

MMR-Bench: A Comprehensive Benchmark for Multimodal LLM Routing

EmbedCopilot: Evaluating Vision-Language Models for Hardware-Aware Embedded System Development

Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action Alignment

Delineating Knowledge Boundaries for Honest Large Vision-Language Models

EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving

Context Blindness in DPO: Mitigating Object Hallucination in MLLMs via Context-Calibrated Preference Optimization

TDSR-VLA: Transition-aware Denoising Sequence Representations for Vision-Language-Action

Teaching Vision-Language-Action Models What to See and Where to Look

ReShift: Aha-Moment-Driven Reasoning-Level Backdoor Attacks on Vision–Language Models

Open Your Eyes: Benchmarking the Detection of Fabricated Realities and Weaponized Ethics in VLMs

Evaluating and Understanding Model Editing for Medical Vision Language Models

ESC: Emotional Self-Correction for Reliable Vision-Language Models

CrossView: Can Vision-Language Models Reason Across Cameras?

VisReflect: Latent Visual Reflection for Fine-Grained Perception in Long Visual Context

V-REX: Benchmarking Exploratory Visual Reasoning via Chain-of-Questions

SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models

VISOR++ : VISUAL INPUT BASED STEERING FOR LARGE VISION LANGUAGE MODELS

(ends 12:30 PM)

Break:

Coffee Break

(ends 11:00 AM)

Demo Session 1 [10:30-12:30]

(ends 12:30 PM)

noon

Lunch:

Lunch

(ends 1:30 PM)

1:30 p.m.

Video Understanding, Generation and Multimodal Learning [1:30-3:00]

Orals 1:30-2:45

[1:30] Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability

[1:45] OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video

[2:00] OmniForcing: Unleashing Real-time Joint Audio-Visual Generation

[2:15] Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding

[2:30] FEEL (Force-Enhanced Egocentric Learning): A Dataset for Physical Action Understanding

(ends 3:00 PM)

Robustness, Privacy, Learning & Theory [1:30-3:00]

Spotlights 1:30-2:30

[1:30] On the Reliability of Cue Conflict and Beyond

[1:35] One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models

[1:40] TR-MoE: Temporal Reliability-Aware Mixture-of-Experts for Robust Tracking

[1:45] Generating Multi-view Adversarial Examples for Visual Geometry Grounded Transformer

[1:50] LoRC: Detecting AI-Generated Images via Low-Rank Collapse in the Semantic-Residual Space

[1:55] Proteus: Model Leakage-Induced Adversarial Attack in Federated Learning

[2:00] Beyond Filter Pruning: Top-K Spatial Selection for Efficient Neural Networks

[2:05] Spectral Gating via Damped Oscillations for Adaptive Implicit Neural Representations

[2:10] When Higher Order Hurts: Pre-Asymptotic Order Collapse in Generative ODE Sampling — A Theory of Discretization–Learning Interaction

[2:15] Structured-Noise Masked Modeling for Video, Audio and Beyond

[2:20] Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations

[2:25] Multi-Anchor Distillation with Text-Guided Analytic Classifier for Continual Learning

(ends 3:00 PM)

Computational Imaging, Medical & Scientific Vision [1:30-3:00]

Spotlights 1:30-2:30

[1:30] Atlas is Your Perfect Context: One-Shot Customization for Generalizable Foundational Medical Image Segmentation

[1:35] Mimicking Radiologists: A Coarse-to-Fine Framework with Structural Sparse Tokens for Dual-LLM Computed Tomography Report Generation

[1:40] VesselTok: Tokenizing Vessel-like 3D Biomedical Graph Representations for Reconstruction and Generation

[1:45] RPM-Distill: Physiology-guided Adaptive Cross-modal Distillation for Robust Remote Physiological Measurement

[1:50] Pushing the Limits of High-Resolution Weather Forecasting through Data Scaling

[1:55] Ice Cloud Geometry Retrieval with Calibrated Uncertainty from Passive Satellite Imagery

[2:00] Event-based Sparse-view Background-Oriented Schlieren Tomography

[2:05] Zero-shot Depth from Defocus

[2:10] Bayesian Self-Attention with Local Pixel Correlations for Lightweight Denoising Transformers

[2:15] PolarAPP: Beyond Polarization Demosaicking for Polarimetric Applications

[2:20] Stokes-Informed Diffusion for Robust Linear Polarization Estimation

[2:25] Off the Planckian Locus: Using 2D Chromaticity to Improve In-Camera Color

(ends 3:00 PM)

3 p.m.

Keynote:

Kristen Grauman

(ends 4:00 PM)

4 p.m.

Panel:

The Age of LLMs: Who Is the Researcher Now?: How LLMs Are Changing Search, Ideation, and Scientific Judgment

(ends 4:30 PM)

4:30 p.m.

Demo Session 2 [4:30-6:30]

(ends 6:30 PM)

Break:

Coffee Break

(ends 5:30 PM)

Poster Session 2 [4:30-6:30]

Posters 4:30-6:30

MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding

Ring Forcing: Towards Precise Long-Term Memory for Autoregressive Video Diffusion

Frames2Residual: Spatiotemporal Decoupling for Self-Supervised Video Denoising

Anchor Forcing: Anchor Memory and Tri-Region RoPE for Interactive Streaming Video Diffusion

EgoExo-Con: Exploring View-Invariant Video Temporal Understanding

MomentSeg: Moment-Centric Sampling for Enhanced Referring Video Object Segmentation

Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding

ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously

Linear Scaling Video VLMs for Long Video Understanding

GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation

VDC-Agent: When Video Detailed Captioners Evolve Themselves via Agentic Self-Reflection

GeoBrowse: A Geolocation Benchmark for Agentic Tool Use with Expert-Annotated Reasoning Traces

STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding

Objects as Audio-Visual Modal Sound Fields

ID-LoRA: Identity-Driven Audio-Video Personalization with In-Context LoRA

Online Reasoning Video Object Segmentation

Gen2Balance: Generative Balancing for Long-Tailed Video Action Recognition

ProLaViT: Learning Progressive Latent Visual Thoughts in Structured Latent Space

GuideMe: Benchmarking Multi-Domain Task Guidance and Intervention in Streaming Video

InterCMDM: Block-Causal Diffusion for Autoregressive Human Interaction Generation

Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability

Self-Evolving Agentic Image Restoration via Deliberate Planning and Intuitive Execution

VersatileMotion: A Unified Framework for Motion Synthesis and Comprehension

Enhanced Neural Video Representation Compression with High Scalability

Accelerating Text-to-Video Generation with Calibrated Sparse Attention

Taming Text-to-Sounding Video Generation via Advanced Modality Condition and Interaction

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

SALT: Self-Consistent Distribution Matching with Cache-Aware Training for Few-Step Video Generation

Em-Garde: A Propose-Match Framework for Proactive Streaming Video Understanding

Surprise Forcing: What to Remember, When to Skip in Long Video Generation

Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors

Beyond Sequential Distance: Inter-Modal Distance Invariant Position Encoding

Consistent Video-to-Video Translation via Explicit Correspondences

Test-time Counterfactual Calibration for Hallucination-Resistant Temporal Grounding

InterEdit: Navigating Text-Guided Multi-Human 3D Motion Editing

PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion

SV-TAD: Native Sparse Convolutions for Efficient Temporal Action Detection

Multi-modal Knowledge Preserving Adapter for Embedding Backward Compatibility

Better Call CineCrew: Consistent Ultra-Long Narrative-to-Film Generation

PhysDrape: Learning Explicit Forces and Collision Constraints for Physically Realistic Garment Draping

X-Stream: Benchmarking MLLMs as Multiplexers for Multi-Stream Understanding

HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising

ECoSim: Data Efficient Fine-Tuning for Controllable Traffic Simulation

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning

Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models

Human-Level Accuracy, Non-Human Strategies: Revealing Model-Human Divergence in Video Physical Reasoning

SpecEyes: Accelerating Agentic Multimodal LLM via Speculative Planning and Perception

EmbodiedVAE: Disentangled Video VAE for Efficient and Controllable Embodied Manipulation

Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs

S2Gest: Split-Scan State Space Models for Dynamic Hand Gesture Recognition

Reasoning with Memory: A Temporal Granularity-Adaptive Framework for Training-Free Long Video Understanding

Latent Visual Diffusion Reasoning with Monte Carlo Tree Search

Learning Egocentric Cues from Exocentric Video using Privileged Egocentric Supervision

SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation

DART: Deformable Adaptive Reasoning with Temporal Queries for Online Skeleton-Based Action Recognition

FingerCap: Fine-grained Finger-level Hand Motion Captioning

FreeSwim: Revisiting Sliding-Window Attention Mechanisms for Training-Free Ultra-High-Resolution Video Generation

Evaluating and Enhancing Negation Comprehension in Remote Sensing MLLMs

Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos

LogFA: Efficient Feature-Space Data Augmentation for Egocentric Temporal Action Segmentation

OnPoint: Offline-to-Online Multi-Level Distillation for Point-Supervised Online Temporal Action Localization

SPAR: A Sequential Primacy and Attribution Ranking Framework for Skill Determination

X2SAM: Any Segmentation in Images and Videos

OneVAE: Joint Discrete and Continuous Optimization Helps Discrete Video VAE Train Better

A Benchmark and Multi-Agent System for Instruction-driven Cinematic Video Compilation

FeatTracker: Short- and Long-Range Temporal Feature Consistency for Robust Underwater Object Tracking

Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation

DeRA: Decoupled Representation Alignment for Video Tokenization

OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video

GryphOne: Symbol-Aware Masked Diffusion for Structural Refinement in Offline Handwritten Mathematical Expression Recognition

SHIFT: Motion Alignment in Video Diffusion Models with Adversarial Hybrid Fine-Tuning

ClearText-Video: A Large-Scale Text-Centric Video Dataset Bridging Video Restoration and Scene-Text Enhancement

LoT-Pass: Long-term-robust Image Watermarking for Image to Video Generation

TinyHistory: Lightweight Video History Embeddings via Two-Stage Context Learning

ChronusOmni: Improving Time Awareness of Omni-Modal Large Language Models

Autoregressive Image Generation Needs Only a Few Lines of Cached Tokens

DART: Difficulty-Adaptive Routing for Zero-Shot Video Temporal Grounding

Audio-Visual Continual Test-Time Adaptation without Forgetting

RoboMirror: Understand Before You Imitate for Video to Humanoid Locomotion

Structural Assessment for Understanding and Guiding Dataset Distillation in Discrete Token Space

Adapting MLLMs for Nuanced Video Retrieval

Cambrian-P: Pose-Grounded Video Understanding

TAR: Temporal Anchor-Constrained Reasoning for Video Temporal Grounding

Adaptive Latent Trajectory Anchoring for Action Segmentation Dataset Condensation

Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-Turn Editing

Precise Video-to-Audio Generation with Cross-Modal Alignment in Latent Space

Safe Responses Matter: Output-Aware Safety Guardrail Mitigate Over-Refusal in MLLMs

Delayed Bidirectional Alignment via Disentangled Audio Semantics for Audio-Visual Segmentation

SMART: When is it Actually Worth Expanding a Speculative Tree?

Pistachio: Towards Synthetic, Balanced, and Long-Form Video Anomaly Benchmarks

End-to-End Training for Autoregressive Video Diffusion via Self-Resampling

Step-by-Step Video-to-Audio Synthesis via Negative Audio Guidance

VoCa: Unified Autoregressive Modeling for Talking Audio-Video Generation

PanoSAM2: Lightweight Distortion- and Memory-aware Adaptions of SAM2 for 360 Video Object Segmentation

Video-Holmes: Can MLLM Think like Holmes for Complex Video Reasoning?

Reflect-R1: Evidence-Driven Reflection for Self-Correction in Long Video Understanding

Guiding the Blind: Generalizing GUI Agents to Unseen Websites via Multimodal Tutorials

Test Time Training for Long Videos via Frame Forgetting Network

Trajectory-Level Continuous Action Representation for Robotic Manipulation

Temporal and Cross-modal Alignment for Enhanced Audiovisual Video Captioning

SIGNER: Temporally Grounded Sign Language Generation via Time-Resolved Conditioning

Clue Matters: Empower Video Reasoning with Brain-Inspired Latent Clue Learning

Towards Long-Form Spatio-Temporal Video Grounding

AffoGato: Open-Vocabulary Affordance Grounding with Automated Data Generation at Scale

SPAR: Semantic-Pixel Self-Alignment and Adaptive Routing for Unified Multimodal Models

Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning

From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for Video Generative Models

SAM-MT: Real-Time Interactive Multi-Target Video Segmentation

V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning

Pathwise Test-Time Correction for Autoregressive Long Video Generation

EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding

CritiqueDriveVLM: From Verifier-Guided Reinforcement Learning to Latent Thought Distillation for Autonomous Driving

DG-Force: Disentangling and Gathering Forensic Cues is Needed for Image Manipulation Localization

Conditional Flow Matching for Visually-Guided Acoustic Highlighting

C3ASD: Multi-Level Consistency-Driven Representation Learning for Robust Active Speaker Detection

PeCA: Palette Context Assisted Inference for Test-Time Paint-Bucket Colourisation on Animation Videos

From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation

OmniForcing: Unleashing Real-time Joint Audio-Visual Generation

Towards Memory-Efficient Autoregressive Video Generation via Instance-Specific Parametric Absorption

JoVA: Unified Multimodal Learning for Joint Video-Audio Generation and Editing

EgoVITA: Learning to Plan and Verify for Egocentric Video Reasoning

EgoEverything: A Benchmark for Human Behavior–Inspired Long-Context Egocentric Video Understanding in AR Environment

Egocentric Procedure Parsing

StoryTeller: Training-Free Narrative Grounding for Long-Form Audio Description

Anchored Video Generation: Decoupling Scene Construction and Temporal Synthesis in Text-to-Video Diffusion Models

AnaPFL: When Closed-Form Solutions Meet Generalizationand Personalization in Personalized Federated Learning

Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation

Counterfactual World Models via Digital Twin-conditioned Video Diffusion

MG-RWKV: Multi-Grained Context-Aware RWKV for Temporal Forgery Localization

ProAct: Agentic Lookahead in Interactive Environments

Benchmarking Dynamic Affective Reasoning: A Viewer-Centric Video Emotion Dataset

Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance

Whence the Voice? Self-supervised Dual-source Audio-Visual Localisation via Selective Convergence

WorldWander: Bridging Egocentric and Exocentric Worlds in Video Generation

Towards Temporal Compositional Reasoning in Long-Form Sports Videos

ReQuest: Rethinking-based Question-Aware Frame Selection for Long-Form Video QA

SENTRY: SAM2-Enhanced Neighbor-Aware and Temporally Reasoned Memory for Visual Tracking

HorizonRelight: Relighting Long-horizon Videos Consistently via Diffusion Transformers

Q-TriM: Question-Guided Tri-Modal Attention for Audio–Visual Question Answering

VC-VAE: Leveraging Video Codecs for Training-Efficient and High-Fidelity Video VAE

LINA: Learning INterventions Adaptively for Physical Alignment and Counterfactual Generation in Diffusion Models

VideoTIR: Accurate Understanding for Long Videos with Efficient Tool-Integrated Reasoning

Actor as Its Own Critic: Unifying Region Understanding and Localization via CycleGRPO

Demystifing Video Reasoning

Table-MCR2TR: Merged-Cell-Aware Table Recognition via Reinforced Multimodal Language Models

VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting

Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention

LENS: Adaptive Spatio-Temporal Zooming for Keyframe Sampling in Long-Form Videos

CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts

Open-Vocabulary Long Term Action Anticipation

MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech

DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression

EventSTU: Event-Guided Efficient Spatio-Temporal Understanding for Video-LLMs

Thinking in Streaming Video

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

TaxoGrasp: Taxonomy-Guided Human Grasp Synthesis with Sparse Contact Constraint

QCA: Query- and Content-Aware Keyframe Selection for Long Video Understanding

Video-HolmesV2: Can MLLMs Reason with Spatio-Temporal Audio-Visual Evidence in Long Videos?

Conversational Human Audio-visual Talking Dialogue Generation

Don't Let the Video Speak: Audio-Contrastive Preference Optimization for Audio-visual Language Models

SIGNET: Motion-Level Knowledge Transfer for Cross-Language Sign Language Translation

Reward Modeling for Computer-Using Agent from Video Execution

SignBind-LLM: Multi-Stage Modality Fusion for Sign Language Translation

PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning

EgoCogNav: Cognition-aware Human Egocentric Navigation

Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding

STVFocus: Query-guided Spatio-Temporal Visual Focusing for Video LLMs

LARY: A Latent Action Representation Yielding Benchmark

HyLaR: Hybrid Latent Reasoning with Decoupled Policy Optimization

Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models

From Script to Shot: A Benchmark for Grounding Screenplays in Movies

GTR: Guide-Then-Refine Token Compression for Training-Free Acceleration of Video-LLMs

Distribution-Alignment Bridge for Uncertainty-Aware Text-to-Video Retrieval

RoboGesture: Real-Time Semantic-aligned Co-Speech Gestures Generation for Humanoid Interaction

Keep-or-Drop? Adaptive Tokenizer for Compact Video Representation

S3-Prune: Stability-Aware Token Budgeting for Long-Form Video-Language Models

Video-Oasis: Rethinking Evaluation of Video Understanding

Beyond Script Family Boundaries: Towards Unified Open-Set Scene Text Recognition

Revisiting Weakly-Supervised Video Scene Graph Generation via Pair Affinity Learning

Mitigating Modality and Language-Style Gaps for Zero-Shot Video Moment Retrieval

H2SVC: Head-aware Heterogeneous Streaming Video Cache for Online Video Understanding

RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks

EgoPHI: Estimating 3D Hand-Object Contact and Force from Egocentric Vision

ActionPlan: Future-Aware Streaming Motion Synthesis via Frame-Level Action Planning

Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction

MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing

No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairs

Accelerating Diffusion Models via Equal-Risk Caching

Continuous Heart Rate Variability Estimation from Egocentric Systems for Skill Assessment

AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation

LongEgoRefer: A Benchmark for Long-Form Egocentric Video Referring Expression Comprehension

MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment

DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer

Learning Consistent Temporal Grounding between Related Tasks in Sports Coaching

GEAR-Seg: A Grounded Explainable Agent for Reasoning Segmentation and Data Engine

Natural Language Camera Movement Understanding

UniTemp: Unlocking Video Generation in Any Temporal Order via Autoregressive Distillation

JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching

Fine-Grained Text-to-Video Retrieval for Camera-Trap Data

Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents

MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learning

Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench

Causal Yet Future-Aware: Dual-Path Temporal Modeling for Online Action Segmentation

Towards Effective Long Video Understanding: Dynamic MAS Construction via Meta-Agent

EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use

Small Vision-Language Models are Smart Compressors for Long Video Understanding

FeVOS: Foresight Expression Video Object Segmentation

Histopathology Multi-modal Embedding for Pathology Composed Retrieval

Unified Video Dense Prediction from Disjoint Data

FastSTAR: Spatiotemporal Token Pruning for Efficient Autoregressive Video Synthesis

Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos

Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks

Learning to Mask: Cross-Modal Noise Modulation for Hallucination Mitigation in Multi-modal Large Language Models

STAC: Selective Spatiotemporal Aggregation and Compression for Video Reasoning Segmentation

FEEL (Force-Enhanced Egocentric Learning): A Dataset for Physical Action Understanding

Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning

PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference

OCTOPUS: Multi‑Agentic Universal Compositional Visual Retrieval

VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement

Perceptual Projection Pruning: Diversity-Aware Video Token Pruning for Multimodal Large Language Models

RL from Physical Feedback: Aligning Large Motion Models with Humanoid Control

Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction Tuning

Unifying CNNs and ViTs for Learning-Efficient and Scalable Variational AutoEncoder

RotateAttention : RoPE-Aware Rotation and Range Rectification for INT4 Quantized Attention in Video Generation

CTEPM: Continuous-Time Event Process Memory for Long-Video Language Models

Self-Evolving MCP-GUI Agents via Automated Environment Generation and Experience Learning

LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning

SymbOmni: Evolving Agentic Omni Models via Symbolic Concept Learning

QSVideo: Query-Conditioned Semantic Temporal Retrieval for Video Understanding

ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding

CurveStream: Boosting Streaming Video Understanding in MLLMs via Curvature-Aware Hierarchical Visual Memory Management

Remembering Across Blocks: Topology-Conditioned Block-Progressive Memory for Skeleton-Based Action Recognition

HAS: Highlight-guided Attention Steering for Multimodal LLM Video Summarization

NanoVSR: Towards Real-Time Video Super-Resolution on Edge Devices

Reasoning-Guided Part-Level Visual Grounding via Reinforcement Learning

LogicIR: Logic Gate Networks for Image Restoration

FedLAS: Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration

Freqformer: Image-Demoiréing Transformer via Effective Frequency Decomposition

NeuroRefiner: Morphology-Aware Multi-Agent Refinement for 3D Fluorescence Microscopy Neuron Segmentation

Raw-JPEG Adapter: Efficient Raw Image Compression with JPEG

Spatiotemporal Flux Probing for Single-Photon Videography

Less Tokens, Better Forecasts: Sparse Residual Routing for Efficient Weather Prediction

Atlas is Your Perfect Context: One-Shot Customization for Generalizable Foundational Medical Image Segmentation

Posterior Samplings are Missing Modalities Generators for Medical Image Translation

HIDA: A Human-Intuition-Guided Depth-Aware Framework for Zero-Shot Amodal Segmentation

TRAM: Finetuning-Free Test-Time Adaptation for Generalized Face Anti-Spoofing with Only a Few Bonafide Samples

PyraE2E: Enhancing End-to-End WSI Analysis via Cross-Scale Super-Resolution

MegaFlow: Zero-Shot Large Displacement Optical Flow

From Local Windows to Adaptive Candidates via Individualized Exploratory: Rethinking Attention for Image Super-Resolution

Gaussian Belief Propagation Network for Depth Completion

ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion

WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching

MambaRaw: Selective State Space Modeling for Efficient 4K RAW Image Reconstruction

AlphaRad: Grounded Zero-Shot Classification in Chest Radiology via α-Corrected Binary Cross Entropy and Factorized Latent Supervision

Memory-Supported Synergistic Adaptation for Training-Free Test-Time Medical Image Segmentation

IDeaL: Data-Free Multi-Teacher Distillation via Improved Dead Leaves

Mimicking Radiologists: A Coarse-to-Fine Framework with Structural Sparse Tokens for Dual-LLM Computed Tomography Report Generation

Neuromorphic X-ray Computed Tomography

Synesthesia via Direct Latent Augmentation: Bypassing the Decode-Encode Loop for Cross-Modal Distillation

Flexible Control of 3D CT Generation via Text and Semantically-Defined Segmentation Prompts

Resolution-Agnostic Neural Operators for Multi-Rate Sparse-View CT

MedQ-Deg: A Multidimensional Benchmark for Evaluating MLLMs Across Medical Image Quality Degradations

SeekFlow: Synergizing Radiology and Pathology Foundation Models for Precision Oncology via Knowledge-Guided Evidence Flow

MArFE: Multi-Contrast MRI Arbitrary Scale Super-Resolution with Fourier Enhancement

Kiroshi: An Agentic Perception System for High-Accuracy Image Parsing

EcoVideo: Entropy-Orchestrated Video Generation Paradigm in Cloud-Edge Dynamics

Hybrid Event–Frame Sensors: Modeling, Calibration, and Simulation

Dual-Prior Guided Null-Space Learning with Mixture-of-Splines for Arbitrary Medical Slice Super-Resolution

MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution

DRIFT: Difficulty-aware Rectified Flows for Through-plane MRI Super-Resolution

VesselTok: Tokenizing Vessel-like 3D Biomedical Graph Representations for Reconstruction and Generation

RePer-360: Releasing Perspective Priors for 360° Depth Estimation via Self-Modulation

Scaling Whole-Slide Pathology Foundation Model Pretraining with Billions Off-the-Shelf Tokens

FlexiBrain: Resolution-Agnostic Voxel-Level Encoding for Native fMRI

FreqPhys: Repurposing Implicit Physiological Frequency Prior for Robust Remote Photoplethysmography

Fidelity- and Perception-Aware Local Implicit Attention for Arbitrary-Scale Image Super-Resolution

From Local to Global: A Progressive Reconstruction Network for Diffractive Snapshot Spectral Imaging

Quantile‑Adaptive Temperature Scaling for Confidence Calibration

Hyper-Network Neural Functional Maps for Unsupervised Robust 3D Shape Matching

MediRound: Multi-Round Entity-Level Reasoning Segmentation in Medical Images

Rethinking Training and Inference for Trajectory Forecasting: Linking Winner-Take-All back to GMMs

STARLINC: Satellite Trail Artifact Removal using Inter-Frame Correlation

If It's Not Efficient, It's Not Usable: Real-Time OOD Detection with Latent De-Biasing and High-Quality Negative Samples

Masked BRep Autoencoder via Hierarchical Graph Transformer

RPM-Distill: Physiology-guided Adaptive Cross-modal Distillation for Robust Remote Physiological Measurement

RainODE: Continuous-Time Precipitation Forecasting with Latent Neural ODEs

TopoGAT: Plug-and-Play Topological Graph Attention for Fine-Grained 3D Segmentation

Learn to See the Unseen in Low-light Spike Streams

2K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Prediction

BWAFDA: Block-wise Weighted Attention Fusion with Detail-aware for No-Reference Image Quality Assessment

NGPS: Structure-Preserving Self-Supervised Denoising via Neighbor-Guided Patch Sampling

Concept-to-Pixel: Prompt-Free Universal Medical Image Segmentation

CUST : Clustered Unit-level Similarity Transformer for Lightweight Image Super-Resolution

DeLux: Cross-Modal Local Artifact Restoration in Video Using Neuromorphic Data

LIIFusion: Coarse-to-fine Framework for Generative MEF via Implicit Neural Representation

EvDiff: High Quality Video with an Event Camera

Dual-Output Multi-Exposure HDR Reconstruction via SDR Fusion and Gain Map Inverse Tone Mapping

XPos3R: Cross-Modal Transformer for Intraoperative 2D/3D Registration

Pushing the Limits of High-Resolution Weather Forecasting through Data Scaling

Multi-Channel Uncertainty-Weighted Score Matching for Conditional Diffusion in Medical UDA

Semantic-Anchored Evidential Fusion for Domain-Robust Whole-Slide Survival Analysis

UniH3: Unifying Hierarchical Homogeneity and Heterogeneity for All-in-One Medical Image Restoration

Pol-CACTI: A System and dataset forHigh-Speed Polarized Video Compressive Imaging

MedCAGD: Context-Aware Gated Decoder for Robust Medical Image Segmentation

Foundation-Guided Representation Alignment for Multimodal Medical Image Registration

Φeat: Physically-Grounded Material Feature Representation

From Multi-Resolution Cells to Gigapixel Whole Slide Images Foundation Model for Computational Pathology

Progression as Latent Drift: Generative Forecasting of Slow-Evolving Pathologies

Improving Knowledge Distillation Under Unknown Covariate Shift Through Confidence-Guided Data Augmentation

SDUM: A Scalable Deep Unrolled Model for Universal Cardiac MRI Reconstruction

Towards Trustworthy Dermatology MLLMs: A Benchmark and Multimodal Evaluator for Diagnostic Narratives

Physics-Grounded Disentangled Flow Modeling for Brain Disease Progression Trajectory

Ice Cloud Geometry Retrieval with Calibrated Uncertainty from Passive Satellite Imagery

Implicit Neural Representation for Spherical Harmonics Reconstruction of Motion-Corrupted Fetal Diffusion MRI

From Minimal Clinical Prompts to 3D: Spacing-Aware Prompt Propagation for Multimodal Prostate Lesion Segmentation in bpMRI

When the Teacher Has More Bits: Self-Teacher Latent Distillation for Learned Image Compression

340 FPS Reflection-free Video from Spikes Modulated by a Rapidly Rotating Polarizer

Clinical Cognition Alignment for Gastrointestinal Diagnosis with Multimodal LLMs

Score-Based Matching with Target Guidance for Cryo-EM Denoising

Event-based Sparse-view Background-Oriented Schlieren Tomography

CLARITY: Medical World Model for Guiding Treatment Decisions by Simulating Context-Aware Disease Trajectories in Latent Space

Do Multimodal LLMs Understand Intraoral Dental Data? Dataset, Platform, and Baselines

LineGraph2Road: Structural Graph Reasoning on Line Graphs for Road Network Extraction

MoCA3D: Monocular 3D Bounding Box Prediction in the Image Plane

SFDATrack: Generalized Source-Free Domain Adaptive Tracking Under Adverse Weather Conditions

WARP: Wide Attention with Rich Projections for Image Super-Resolution

Multi-Block-Attention-based Color Constancy

MorphJEPA: Morphology-Aware Latent Prediction for Hyperspectral Images

G-ZAP: A Generalizable Zero-Shot Framework for Arbitrary-Scale Pansharpening

Proximity-Constrained Counterfactual Decoding for Hallucination-Robust Medical VQA

MOOZY: A Patient-First Foundation Model for Computational Pathology

DiffVP:Differential Visual Semantic Prompting for LLM-Based CT Report Generation

Finding Highlight Images In Your Albums:From Benchmark To MLLM

Zero-shot Depth from Defocus

HybridSim: A Physics–Learning Hybrid Digital Twin for mmWave Human Sensing

HSFM: Hard-Set-Guided Feature-Space Meta-Learning for Robust Classification under Spurious Correlations

CLDefocus: Physically Grounded Compound-Lens Defocus Blur Synthesis

TopoAgent: An Agentic Framework for Automated Topology Learning in Medical Imaging

2D Features Are All You Need for 3D Shape Understanding

REALM: An RGB and Event Aligned Latent Manifold for Cross-Modal Perception

MedRepBench: Benchmarking Structured Understanding of Medical Report Images

Progressive and Localized Super-Resolution of 3D Objects via Localized Latent Voxel Diffusion

Reconstructing Dense Depth of Dark Scenes with Sparse LiDAR, Noisy Events, and Blurry RGB

TaxoMIL: Taxonomy-Constrained Learning for Hierarchical Whole Slide Image Analysis

Seeing What Matters: Lesion-Aware High-Resolution Patch Discovery and Fusion for Chest X-ray Report Generation

SPHERE: From MRI Sampling Mechanisms to Spatial Priors for Generalizable Brain Tumor Segmentation

Region-Aware Multimodal Large Language Model via SlowFast Tokenization and Pseudo-Mask Guidance for 3D CT Report Generation

Bayesian Self-Attention with Local Pixel Correlations for Lightweight Denoising Transformers

LumiDepth: Stable Monocular Depth in Multi-Illumination Scenes

MCPNet:Masked Coordinate Pooling-based Attention Network for Medical Landmark Detection

DiffuPrompt: Adapting Video Foundation Models to 3D Medical Volumes via Latent Trajectory Priors

SVI360: Spherical Video Interpolation

Task-driven Processing with Coarse-to-Fine Glimpse-based Active Perception

From Reconstruction to Decision: A Post-Encoder Plug-in Adapter for Curvilinear Segmentation

EchoSonar-R: A Multi-View Reasoning-Enabled Model for Disease Classification and Report Generation in Echocardiography

Keep Your Friends Close, and the Right Neighbours Closer: Disaster-Conditioned Kernel-Regularized Graph Attention for Building Damage Classification

Beyond Random Sampling: Distribution-Aware Alignment for Semi-Supervised Medical Image Segmentation

SurvMILKD: A Weakly Supervised Survival Analysis Framework for Multi-Teacher Knowledge Distillation using Pathology Foundation Models

Urban Boundaries, Social Barriers: A Benchmark and Vision-Centric Framework for Mapping Gated Communities and Equity Implications

Low-Level Dataset Distillation for Medical Image Enhancement

DualResPS: Dual-Resolution Photometric Stereo Using a Frame-Event Hybrid Camera

PolarAPP: Beyond Polarization Demosaicking for Polarimetric Applications

Fast and Accurate Image Restoration with Rank Enhanced Linear Attention

REVA-PO: Stabilizing Reinforcement Learning for Chest X-ray Report Generation

Beyond Isolated Scans: Cross-Phase Alignment of Structure and Topology for 3D Medical Pretraining

Integrated Forward–Inverse Network for Reconstruction for Lensless Image Reconstruction

Gaussian Volumetric Representation for Efficient Shear–Warp Visualization

RobustRDP: Advancing Reaction Diagram Parsing via Synthetic-to-Real Data Scaling and Robustness-Oriented Training

SHINE-PPG: Non-Lambertian Intrinsic Decomposition for Illumination-Robust rPPG

Physics-Guided Deep Learning for Linear Mueller Matrix Acquisition

EventVGGT: Exploring Cross-Modal Distillation for Consistent Event-based Depth Estimation

Beyond the Embedding Bottleneck: Adaptive Retrieval-Augmented 3D CT Report Generation

Towards Reliable Multi-Label Classification via Conditional Dependency Modeling

Interpretation-Oriented Cloud Removal via Observation-Anchored Residual Flow with Geo-Contextual Alignment

Moonstone: A Multimodal Foundation Model and Benchmark for Lunar Remote Sensing

Stokes-Informed Diffusion for Robust Linear Polarization Estimation

RIGS: Radar-Informed Gaussian Splatting for Uncertainty-Aware 3D Occupancy and Motion Prediction

Structured SIR: Efficient and Expressive Importance-Weighted Inference for High-Dimensional Image Registration

Comprehensive language–image pre-training for 3D medical image understanding

iMED: A Multi-Endoscope Dataset for Surgical 3D Perception

GeoCFM: Positive-Only Conditional Flow Matching for Mineral Occurrence Sampling

ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device

MedSPOT: A Workflow-Aware Sequential Grounding Benchmark for Clinical GUI

MobileSAM2: Lightweight Segment Anything in Images and Videos via Hypergraphical Knowledge Distillation

Linguistically-Aligned and Visually-Grounded Preference Optimization for Clinically-Augmented Medical Report Generation

3D Field of Junctions: A Noise-Robust, Training-Free Structural Prior for Volumetric Inverse Problems

NeuralDMD: Interpretable Untrained Neural Network for Imaging from Sparse and Noisy Observations

SEMIR: Topology-Preserving Graph Minors for Thin-Structure Segmentation

Pay Attention to Attention Distribution: A New Local Lipschitz Bound for Transformers

Off the Planckian Locus: Using 2D Chromaticity to Improve In-Camera Color

BiCE-HG: A Bi-Conditional Egocentric Hand Gesture Dataset for Intelligent Reality Systems

OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure

Learning from Adversity: Semantic-Aware Mask Refinement through Adversarial Perturbation

Escaping the Low-Frequency Bias: Adversarial Frequency Perturbation for Generalisable Gaze Estimation

Fully Rotation-Equivariant Spectral-Spatial Learning for Multispectral Object Detection

Don’t Teach Instability, Teach Robustness: Selective Sensitivity Gating for Adversarial Robust Distillation

On the Reliability of Cue Conflict and Beyond

Topology-Weighted Effective Rank: A Zero-Cost Proxy for Training Dynamics Stability in Neural Architecture Search

This Looks Distinctly Like That: Grounding Interpretable Recognition in Stiefel Geometry against Neural Collapse

Learn to Rank: Visual Attribution by Learning Importance Ranking

GeoDetect: Geometric Adversarial Detection for VLPs

Geometric Gradient Rectification for Safe Open-Set Semi-Supervised Learning

Scaling Laws for Black-box Adversarial Attacks

One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models

Data Circuit Breaker: Identifying Training, Test, and Generated Data in Image Generative Models

Denoised Variance-Based Pruning with Optimal Brain Bias Compensation

Adaptive Neural Dynamics for Robust Geometric LiDAR-Inertial State Estimation on UAVs

Compact and Structurally Transparent Cervical Cytology with Geometry-Driven Features and Closed-Form Attention

REDistill: Robust Estimator Distillation for Balancing Robustness and Efficiency

Beyond Artifacts: Real-Centric Envelope Modeling for Reliable AI-Generated Image Detection

TR-MoE: Temporal Reliability-Aware Mixture-of-Experts for Robust Tracking

Different Changes Require Different Reasoning: Change-Type-Specialized Experts for Robust Change Captioning

Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection

Spectral-Aware Analytic Class-Incremental Learning for Long-Tailed Distributions

Look But Don't Touch with Sparse Autoencoders for Unlearning in Diffusion Models

Frequency Director: Learnable Mixture of Frequency Experts for Unified Concealed Scene Segmentation

Learning Probabilistic Prompt for Continual Learning

Generating Multi-view Adversarial Examples for Visual Geometry Grounded Transformer

ProtoMappingNet: Interpretable Hierarchical Prototypes through Relational Prototype Mappings

Intrinsically Stable Spiking Neural Networks: Overcoming the Performance Barrier in the Absence of Batch Normalization

R-ESC: Robustly Erasing Space Concepts via Stochastic Feature Remapping

Weight-Space Mixture-of-Experts for Implicit Neural Representation Classification

Defending from GeoLocalization through Adversarial Road Trips

IConE: Batch Independent Collapse Prevention for Self-Supervised Representation Learning

LoRC: Detecting AI-Generated Images via Low-Rank Collapse in the Semantic-Residual Space

Fast and Flexible Robustness Certificates for Semantic Segmentation

Ada-VNNs: Adaptive Equivariance for Vector Neural Networks

On the Plasticity Collapse in Continual Machine Unlearning

Weight Feedback Computes the Exact Jacobian Transpose in Modern Deep Networks

Geometry-Anchored Transport Framework for Exemplar-Free Class-Incremental Learning

SWAN: World-Aware Adaptive Multimodal Networks for Runtime Variations

Proteus: Model Leakage-Induced Adversarial Attack in Federated Learning

Spectral Gradient Orthogonalization Improves Differentially Private Training at Scale

Geometry Aware Reliable Instance Selection for Noisy Partial Label Learning

Rethinking Temporal Modeling in Visual Object Tracking via Decoupled Auxiliary Supervision

ORBIT: Overcoming Hallucination Risks via Bi-manifold Interaction and Traction

Calibrated Harmonic Overlaid Implicit Neural Representations for Multi-Dimensional Data

A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP

Beyond Filter Pruning: Top-K Spatial Selection for Efficient Neural Networks

Enhancing Pretrained Model-based Continual Representation Learning via Guided Random Projection

BackTranslation2.0 - A Linguistically Motivated Metric to Assess Sign Language Production

AracNet: Revealing Debiasing Signals across Layers with Shallow Monitors

Exposing Implicit Vulnerabilities in Text-to-Image Models via Adversarial Agentic Probing

Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussions

Closing the Capacity–Convergence Gap: Globally Optimal Configuration of Implicit Neural Representations

Spectral Gating via Damped Oscillations for Adaptive Implicit Neural Representations

RoME: Robust Mixture of Low-Rank Experts against Multiple Adversarial Perturbations

Explainability-aware Frustum Attack: Exposing Structural Vulnerabilities in LiDAR-Based 3D Object Detectors

Robustness Emerges Early in Training Dynamics, but Is Not Preserved

REVEAL: Reasoning-Enhanced Forensic Evidence Analysis for Explainable AI-Generated Image Detection

Implicit Neural Representation Facilitates Unified Universal Vision Encoding

VICAL: Vicinal Consistency Alignment for Long-Tailed Visual Recognition

When Higher Order Hurts: Pre-Asymptotic Order Collapse in Generative ODE Sampling — A Theory of Discretization–Learning Interaction

Noise-Robust Face Recognition via Non-target Similarity Distribution Guided Sample Selection

UC-VLM: Consistency-Driven Learning for AI-Generated Image Detection with Vision-Language Large Models

Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification

SPICE: Simple Polysemantic feature Interpretation via Clustering-based Explanations

BrainRiem: Riemannian Prototype Learning for Source-Free Cross-Site Brain Network Diagnosis

Bridging Theory and Practice in Source-Free Domain Adaptation via Adversarial Proxy Perturbation

Structured-Noise Masked Modeling for Video, Audio and Beyond

SpaR3D-MoE: Adaptive 3D Spatial Reasoning from Sparse Views Meets Geometry-Inductive Mixture-of-Experts

Mapping the Concept Landscape: Structural Perception of Global Distributions for Transparent Data Pruning

Causal Intervention in Concept Bottleneck Models

iSyncTab: Learning Cross-Modal Feature Sequencing for Image-Tabular Data via Neural Synchrony

Puppet-CNN: Continuous Parameter Dynamics for Input-Adaptive Convolutional Networks

MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE

Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations

DiffUE: Enhancing Utility-Unlearnability Trade-off of Unlearnable Examples via Diffusion Autoencoders

Learning with Bilevel-Minimax Optimization for Efficient and Reliable Transfer Attacks

Improving Adversarial Robustness by Mitigating Instability through Relearning

Prior-Conditioned Gaussian Discriminants for Generalizable AI-generated Image Detection

Dynamic-V2C: Editable and Continual Vision-to-Concept Bottleneck Models via Influence Functions

FaceArmor: A Universal Facial Image Protection Against Diffusion-Based Manipulations

Multi-Anchor Distillation with Text-Guided Analytic Classifier for Continual Learning

Deep Noise Label Learning via Effective Rank Reduction

D-VLAM: Differential Vision and Language Mixing for Rehearsal Free Continual Learning

Adversarial Attack and Disturbance Detection by Hadamard-Coded Output Representations for Object Detection and Semantic Segmentation

Breaking High Confidence: Practical Face Impersonation under High-Security Thresholds

Simple Filtering Improves Masked Autoencoders

Leveraging Dark Knowledge for Intrinsic Multimodal Out-of-Distribution Detection

(ends 6:30 PM)

FRI 11 SEP

9 a.m.

Video Generation, Avatars & Dynamic Worlds [9:00-10:30]

Spotlights 9:00-10:15

[9:00] Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length

[9:05] Mind-to-Face: Neural-Driven Photorealistic Avatar Synthesis via EEG Decoding

[9:10] GenLCA: 3D Diffusion for Full-Body Avatars from In-the-Wild Videos

[9:15] OmniFace: Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer

[9:20] OmniDance: Multimodal Driven Dance Video Generation with Large-scale Internet Data

[9:25] MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control

[9:30] Progressive Pose-Guided 4D Animal Reconstruction from Monocular Video

[9:35] Monocular Models are Strong Learners for Multi-View Human Mesh Recovery

[9:40] EgoExoMoCap: Distributed Human Motion Capture via Ego- and Exocentric Body Tracking from Head-Mounted Devices

[9:45] Interaction-Aware 4D Gaussian Splatting for Dynamic Hand-Object Interaction Reconstruction

[9:50] OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control

[9:55] CameraAnything: Refilming Videos with Arbitrary Camera Control

[10:00] RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video

[10:05] A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models

[10:10] Grounding World Simulation Models in a Real-World Metropolis

(ends 10:30 AM)

Vision Foundation Models: Interpretability and Reasoning [9:00-10:30]

Orals 9:00-10:30

[9:00] Steerable Vision Transformers

[9:15] Understanding Geometric Representations in Self-Supervised Vision Transformers via Subspace Intervention

[9:30] World Knowledge in the Weights: Reading Concept Circuits of Vision Transformers

[9:45] What CLIP Knows but Cannot Say: Recovering Negation from Frozen Intermediate Features

[10:00] Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens

[10:15] Make Geometry Matter for Spatial Reasoning

(ends 10:30 AM)

Geometry, Localization, Matching & Motion [9:00-10:30]

Spotlights 9:00-10:15

[9:00] RoMa v2: Harder Better Faster Denser Feature Matching

[9:05] LoMa: Local Feature Matching Revisited

[9:10] Gravity-aware partially calibrated absolute pose estimation from affine- or rotation-covariant features

[9:15] Rolling Shutter Camera Self-Calibration

[9:20] Lost in the Tail: Addressing Geographic Imbalance in Urban Visual Place Recognition

[9:25] OpenCVL: An Open, Diverse, and Large-Scale Dataset for Fine-Grained Cross-View Localization

[9:30] E-MOTION: A Dataset for Event-Based Scene Flow Estimation with Independent Moving Objects

[9:35] SPARC: Single-Pass Scaling for Motion Forecasting with Conformal Bayesian Last Layers

[9:40] Training-free Controllable Motion Generation under Heterogeneous Constraints

[9:45] OVGGT: O(1) Constant-Cost Streaming Visual Geometry Transformer

[9:50] VKSR: Scalable Kernel Surface Reconstruction Using Vecchia's Approximation

[9:55] RADmesh: Remesh-Aware Mesh Deformation

[10:00] Face Anything: 4D Face Reconstruction from Any Image Sequence

[10:05] HoloTetSphere: Unified TetSphere Mesh Reconstruction for Physical Simulations

[10:10] InSpace: Structure-Aware 3D Indoor Scene Generation from a Single 360° Image

(ends 10:30 AM)

10:30 a.m.

Demo Session 3 [10:30-12:30]

(ends 12:30 PM)

Poster Session 3 [10:30-12:30]

Posters 10:30-12:30

Blind to Position, Biased in Language: Probing Mid-Layer Representational Bias in Vision-Language Encoders for Zero-Shot Language-Grounded Spatial Understanding

TaskTok: Delving into Task Tokens for Task-driven Image Restoration

Hyperbolic Hierarchical Clustering for Visual Representation Learning

3D-Aware VLMs with Implicit and Explicit Geometries

ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP

VQT: Vector Quantization Tuning for Efficient Fine-tuning and Compression of Pre-trained Vision Transformers

Leveraging Cross-Modal Knowledge Transfer for Knowledge-Aware Concept Customization

Steerable Vision Transformers

Unsupervised Semantic Segmentation Facilitates Model Understanding

Attention is Case-Sensitive

Task Alignment: A simple and effective proxy for model merging in computer vision

DriftScope: Measuring The Hidden Effects of Diffusion Model Fine-Tuning

Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models

Diffusion-Based Immersive Visual Reasoning

Rethink Backdoor Robustness in Vision Transformers

CS-TTA: Preserving Concept Sensitivity in Test-Time Adaptation

Efficient Quantization-Aware Adaptation for Visual Foundation Models

Look Less, Think Faster: Joint Token-Compute Adaptation for Multimodal LLMs

DnA: Denoising Attention for Visual Tasks

Inductive Visual Logic for Few-Shot Out-Of-Distribution Adaptation in VLMs

Enlightening Photographic Style Transfer with a Self-Supervised Photographic Embedding

Understanding Geometric Representations in Self-Supervised Vision Transformers via Subspace Intervention

Verifying Cancer Segmentation in Vision Transformers via Internal Concepts

Let ViT Speak: Generative Language-Image Pre-training

Quick ViTs: Speeding up Vision Transformers through Equivariance

Auto-Prompting: Layer-Specific Prompt Fusion Discovery via Differentiable Search

DeCoPatch: Revealing Causal Latent Subspaces in Vision-Language Models for GUI Grounding

Spanning the Visual Analogy Space with a Weight Basis of LoRAs

Multi-Head Normalization for Wide Vision Transformers

UrbanAlign: Post-hoc Semantic Calibration for VLM-Human Preference Alignment

Metric-Bench: Exploring In-context Spatial Metric Reasoning in VLMs for Indoor Scenes

Rethinking Attention Reallocation for Multimodal Emotion Recognition

Dynamic Image Prompt Adapter for Scalable Zero-shot Personalized Text-to-Image Generation

Invisible Shortcuts: Why Vision Encoders Know Your Camera

Circuit-MLLM: Topological Logic-Guided Latent-Space Visual Reasoning for Circuit Schematic Understanding

World Knowledge in the Weights: Reading Concept Circuits of Vision Transformers

SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning

CL4D: Contrastive Language–4D Pretraining for Vision-Language Reasoning in Dynamic Scenes

Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective

From Drop-off to Recovery: A Mechanistic Analysis of Segmentation in MLLMs

Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning

Why Can Accurate Models Be Learned from Inaccurate Annotations?

MIRROR: Aligning Semantic Relations from Language to Image via Gromov--Wasserstein

Last-Layer-Centric Feature Recombination: Unleashing 3D Geometric Knowledge in DINOv3 for Monocular Depth Estimation

VIVAS: Vitalizing Visual Perception in VLM Pre-training via Vision-language Unified Autoregressive Supervision

MuSViT: A Foundation Vision Model for Sheet Music Representation

Moving Beyond More Views: Redundancy-Aware Ego–Exo Fusion for Proficiency Estimation

Plug-and-Play Attention Linearization for Pretrained Transformers

MMDiff: Extending Diffusion Transformers for Multi-Modal Generation

Frozen CLIP Priors for Robust Self-Supervised Poisson Inverse Problems

Background Blurring Matters: Improving Visual Grounding by Merging Text-Irrelevant Tokens

Contrastive-Guided Self-Supervised Latent Visual Reasoning for Hallucination Mitigation

SyncVL: Synchronizing Vision ⟷ Language Using Unsupervised Adaptation

Activation Quantization of Vision Encoders Needs Prefixing Registers

Test-Time Registers as Global Priors for Tokenized Image Generation

Vision-TTT: Efficient and Expressive Visual Representation Learning with Test-Time Training

What CLIP Knows but Cannot Say: Recovering Negation from Frozen Intermediate Features

SRRA: Stable-Rank-Based Residual Adaptation for Generalizable Deepfake Detection

From One-to-One to Many-to-Many: Dynamic Cross-Layer Injection for Deep Vision-Language Fusion

ICLAgent: Integrated Circuit Footprint Geometry Labeling via LMM-empowered Multi-Agent Framework

Mechanistic interventions for explainable digital pathology uncovers adversarial vulnerabilities

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning

Tesselating The Earth

Disentangling Hallucinations: Orthogonal Semantic Projection for Robust Interpretability

CLIMP: Contrastive Language-Image Mamba Pretraining

Human-like Object Grouping in Self-supervised Vision Transformers

Seeing Through Circuits: Faithful Mechanistic Interpretability for Vision Transformers

BLOB-Q: Boosting Low Bit ViT Quantization via Global Optimization on Model Distortion

ARGENT: Adaptive Hierarchical Image-Text Representations

HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding

Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens

MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Model

Structured Hyperedge Adaptation for Parameter-Efficient Fine-Tuning of Vision Transformers

AFFMAE: Scalable Vision Pre-Training for High-Resolution Microscopy Segmentation on Desktop Hardware

SafeSAE-VLA: Interpreting OpenVLA Progress Dynamics with Sparse Feature Analysis

When Token Compression Breaks: Structural Pruning vs. Token Reduction for Robust ViT Segmentation under High Compression

ECC: Encoder-Centric Corruption for Fine-Grained Vision in VLMs

BrepLLM: Enabling Large Language Models to Understand Boundary Representations

Practice Makes Perfect: From Explicit Decomposition to Reinforced Latent Planning in Text-to-Human Motion

LoCA: Spatially-Aware Low-Rank Convolutional Adaptation of Vision Foundation Models

ORFC: Orthogonal Reparameterization for Low-Bitrate ViT Feature Coding

What VGGT Knows About Overlap: Probing Geometric Foundation Models for Co-Visibility

On Locality and Length-Generalization in Visual Reasoning

Kilometer-Vision: A New Frontier for Large-Scale Spatial Awareness in VLMs

Make Geometry Matter for Spatial Reasoning

Probing the 3D Object-Level Understanding of Pre-Trained Detection Transformers

TETO: Tracking Events with Teacher Observation for Motion Estimation and Frame Interpolation

FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry

StreamTalk: Streaming Co-Speech Gesture Generation with Key-Pose Anchoring

Syn4D: A Multiview Synthetic 4D Dataset

FlowPainter: Inpainting Optical Flow via Confidence-Guided Completion

MASS: Motion-Aligned Selective Scan for Flow-Based Video Frame Interpolation

PMGC-SimVP: Parametric Multi-scale Gated Convolution for Global Ionospheric TEC Prediction

4D-VGGT: A SpatioTemporal Foundation Model for Dynamic Scene Geometry Estimation

Auto3R: Automated 3D Reconstruction and Scanning via Data-driven Uncertainty Quantification

UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priors

PointLAM: Local Attentive Mamba for Efficient Point-based 3D Object Detection

MemPose: Category-level Object Pose Estimation with Memory

RoMa v2: Harder Better Faster Denser Feature Matching

Event-driven Motion Deblurring via Trajectory-based Kernel Reconstruction

Schroedinger’s Cat: Probabilistic Representation and Prediction of Potential Scene Kinematics

AutoSpeed: Annotation-Free Stage-Adaptive Motion Speed Learning for Robot Manipulation

TACO-Net: Topological Signatures Triumph in 3D Object Classification

WildProp: Visual Estimation of Wildlife Body Proportions at Scale

VectorReLoc: Reliable Vectorized SD Map Visual Re-localization with Contrastive Feature Alignment

LoMa: Local Feature Matching Revisited

Controlling Motion Transfer in Diffusion Transformers via Attention Heads

Prosthesis-Aware 3D Human Pose Estimation: A Dataset and Benchmark for RSP Users

360Anything: Geometry-Free Lifting of Images and Videos to 360°

SemGAN: A Semantic and Hierarchical Adversarial Network for 3D Human Pose Estimation

Rolling Shutter Relative Pose Estimation Made Practical

Honey, I Shrunk the Arc de Triomphe!

Gravity-aware partially calibrated absolute pose estimation from affine- or rotation-covariant features

ClusterStyle: Modeling Intra-Style Diversity with Prototypical Clustering for Stylized Motion Generation

Beyond 2D Matching: A Unified Single-Stage Framework for Geometry-Aware Cross-View Object Geo-Localization

AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labels

Reconstructing Humans and Objects in Interaction using Large Reconstruction Models

SKEL-CF: Coarse-to-Fine Biomechanical Skeleton and Surface Mesh Recovery

General Self-Calibration with Varying Intrinsics

Pointer-CAD v2: Plan-Then-Construct CAD Generation with Dimension-Aware Parametric Precision

UniFlow: Zero-Shot LiDAR Scene Flow for Autonomous Driving

On the real-world generalisability of Optical Flow models

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

Detect by Track: Making Detector-Free Matcher Trackable

Rolling Shutter Camera Self-Calibration

GARDEN: Gravity-Aligned Reconstruction of Disentangled ENvironments from RGB images

FreeFlow: A Bias-free Hierarchical Transformer for Optical Flow Estimation

SPARC: Scalable Path-Specific Counterfactual Fairness via Causal Conditional Independence

Holo360D: A Large-Scale Real-World Dataset with Continuous Trajectories for Advancing Panoramic 3D Reconstruction and Beyond

ObjectForesight: Predicting 3D Object Trajectories from Human Videos

Sequential Visual Place Recognition: Exploiting Trajectory Priors for Robust Localization

Lost in the Tail: Addressing Geographic Imbalance in Urban Visual Place Recognition

Towards Reconfigurable Visual Feature Compression

Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification

Global Graph-Validated Optimization for VLM-based 3D Indoor Scene Generation

UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer

PriorPose: Reference-Guided Joint Deformation and Alignment for Category-Level Object Pose Estimation

Learning Global Camera Poses from Noisy View-Graphs for Structure from Motion

OpenCVL: An Open, Diverse, and Large-Scale Dataset for Fine-Grained Cross-View Localization

Articulated Object Reconstruction from Rest-State Observation

VisTa3D: A Dataset and Benchmark for Vision, Tactile, and 3D Point Clouds-based Thin Object Reconstruction

Coarse-to-fine Contrast: A Hybrid Self-supervised Method for Non-rigid 3D Shape Matching

Roam2Room: A Unified Floorplan-to-Furnished Framework for Controllable Indoor Scene Generation

Rethinking Detection Calibration: A Coordinate Perspective

Following Motion for Sequential Modeling in Video Frame Interpolation

Rosetum3D: A Large-Scale 3D Vision Dataset from Preharvest Roses

Mitigating Radar-Inertial Calibration Ambiguities via SO(3) Manifold Steering

Social-Mamba: Socially-Aware Trajectory Forecasting with State-Space Models

OrthoTrack: Continuous 6-DoF UAV Trajectory Estimation Anchored in Public Orthophotos

Category-Level 3D Correspondence in Camera Space via Morphable Object Priors

Equivariant Symmetry-Aware Head Pose Estimation for Fetal MRI

LaVPR: Benchmarking Language and Vision for Place Recognition

E-MOTION: A Dataset for Event-Based Scene Flow Estimation with Independent Moving Objects

Estimating Velocity and Spin of Spherical Objects from Rolling-Shutter Image(s)

VideoSfM: Exploiting Temporal Structure for Video-Based Structure-from-Motion

MMEarth-Bench: Global Model Adaptation via Multimodal Test-Time Training

Dense Dynamic Scene Reconstruction and Camera Pose Estimation from Multi-View Videos

OmniDS: Dual-Stream Context Fusion for Omnidirectional Depth from Fisheye Cameras

SynHMR: Synergistic Joint-Mesh Modeling for LiDAR-based Human Mesh Reconstruction

SPARC: Single-Pass Scaling for Motion Forecasting with Conformal Bayesian Last Layers

Lightweight Online Reinforcement Learning for Block Decomposition of CAD Models

LaxMotion: Rethinking Supervision Granularity for 3D Human Motion Generation

MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources

SemCityLoc: Aerial 6DoF Localization Using Semantic 3D City Models

Reweighting Framewise Attention in Video Transformers for Facial Expression Understanding

PRISM3D: Probabilistic Refinement and Robust Initialization for Physically Consistent Scene Modeling under Extreme Motion Blur

Training-free Controllable Motion Generation under Heterogeneous Constraints

Boosting 3D Foundation Models with Featureless Pose Optimization

4DGS360: 360° Gaussian Reconstruction of Dynamic Objects from a Single Video

Boosting Correspondence Learning with Structure-Aware Estimator

RBE-Flow:Recurrent Bayesian Estimation on Feature Manifolds for Cross-Modal Registration

Match-Any-Events: Zero-Shot Motion-Robust Feature Matching Across Wide Baselines for Event Cameras

XSurfer: Reconstructing surface meshes of cerebral and cerebellar cortex from diverse MRI data using untrained neural networks

AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories

Retrieving and Refining Winning Noise Tickets for Diffusion-Based Motion Generation

SGMatch: Semantic-Guided Non-Rigid Shape Matching with Flow Regularization

CtrlCoMo: Controllable Co-Speech Motion Generation with Gesture–Action Disentanglement

There and Back Again: A Flexible-Frame Transformer for Multi-Exposure Fusion

Optimizing Mesh Animation from Video via Shape Flow Guidance

LivingWorld: Interactive 4D World Generation with Environmental Dynamics

OVGGT: O(1) Constant-Cost Streaming Visual Geometry Transformer

Sector-Level Cross-View Geo-Localization with Implicit Orientation via Azimuthal Scanning

Category-Level Articulated Object Pose Estimation via Pose–Shape Hypothesis Generation and Verification

Ego-Human Motion Prediction with 3D-Aware LLM

Every Dog Has Its Day, Probably: A Balanced Synthetic Benchmark and Probabilistic Modeling for 3D Dog Pose Estimation

TIDES: Time-Derivative Event Simulation via Deformable Reconstruction

SynFlow: Scaling Up LiDAR Scene Flow Estimation with Synthetic Data

VKSR: Scalable Kernel Surface Reconstruction Using Vecchia's Approximation

PoseImageNet: Pose Estimation for Extensive Classes Based on Rich Structure Prototypes

Variational Patch Gating for Training-Free Few-Shot Classification

Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flow

AnyMatch: Supercharging Universal Multi-Modal Image Matching with Large-Scale Single-View Images

SemLight: Distilled Semantic–Geometric Fusion for Efficient Local Feature Matching

Coordinate Singularities Break Conformal Coverage for Gaze and Head Pose

RADmesh: Remesh-Aware Mesh Deformation

GrowFields: Compositional 4D Neural Fields for Topology-Changing Plant Growth

AirZoo: A Unified Large-Scale Dataset for Grounding Aerial Geometric 3D Vision

IoUCert: Robustness Verification for Anchor-based Object Detectors

Sparsity-Inducing Divergence Losses for Biometric Verification

Leaving the City: A Large-Scale Aerial Dataset for Cross-Season Localization in Unstructured Environments

Unveiling Transferability in Trajectory Prediction via Latent Scene Embeddings

PhyMAGIC: Physical Motion-Aware Generative Inference with Confidence-guided VLM

Trajectory-aware Cross-view Geo-Localization with Sequential Observations

StreetForward: Perceiving Dynamic Street with Feedforward Causal Dynamics

MoBa-GS: Learning a Spatially-Varying Motion Basis over a Dynamic Canonical Space for 4D Reconstruction

RegHead: Non-Humanoid Head Blendshapes via Feed-Forward Registration

UniDynamics: Event-RGB Fusion for Unified Future 4D Dynamic Scene Generation

Tempo-SAM3D: Monocular Video to 4D via Temporal Memory-Guided Generation

Face Anything: 4D Face Reconstruction from Any Image Sequence

UF0-6D: Unified Flow-based Zero-Shot 6D Object Pose Estimation without Refinement

Unified and Efficient Point-Line Local Features

Motion Style Slider: Endpoint-Supervised Continuous Style Control for Human Motion Diffusion

ReflectCAP: Detailed Image Captioning with Reflective Memory

PrimitiveUDF: Primitive-Based Unsigned Distance Fields for Surface Reconstruction from Point Clouds

Embedding Rotation Invariance for Provable Multi-Oriented Scene Text Recognition

HoloTetSphere: Unified TetSphere Mesh Reconstruction for Physical Simulations

Analytic Bayesian Uncertainty for LiDAR Segmentation: A Single-pass Generative Approach

Discovering Geometric Biases in 3D Face Reconstruction: A Curvature-Aware Spectral Framework for Fairness Evaluation

Geometry-Preserving Image Generation for 6D Object Pose Estimation

Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image

WiFi-JEPA: Self-supervised Learning for WiFi-CSI 3D Human Pose Estimation

PolyLayout: Multi-room Manhattan Layout Estimation

InSpace: Structure-Aware 3D Indoor Scene Generation from a Single 360° Image

Revisiting the Volumetric Data of 4DME: Compression, Extension and Benchmarking for Micro-Expression Analysis

Visible Yet Unrecognizable: Frequency-Selective Facial Privacy via Attention

Learning Manifolds in High-D Point Embedding for Anisotropic Surface Approximation from Unstructured Point Clouds

CCFM: Collision-Constrained Flow Matching for Safety-Critical Scenario Generation

NEOMAP: Novel-View Synthesis via Noise Initialization by Manifold Alternating Projection

Odoriko: A Shape-Aware Multimodal Diffusion Framework for Human Motion

Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

Multi-THuMBS: Multi-person Tracking of 3D Human Meshes Beyond Video Shots

Stylized Video Generation via Decoupled Data Synthesis and Gated Style Token Injection

MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens

AHOY! Animatable Humans under Occlusion from YouTube Videos with Gaussian Splatting and Video Diffusion Priors

LibraGen: Playing a Balance Game in Subject-Driven Video Generation

Forecasting Animal Motion

Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length

GO-Renderer: Generative Object Rendering with 3D-aware Controllable Video Diffusion Models

ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video

Walking in the Implicit: Interactive World Exploration via Neural Scene Representation

MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction

Sim, Yet Same: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds

VOID: Video Object and Interaction Deletion

StreamGVE: Training-Free Video Editing via Few-Step Streaming Video Generation

One Video, One World: Turning Monocular Video into Physical 4D Scenes

DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generation

DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxies

TIGER: Taming Identity, Geometry, and Generative Priors for High-Quality Face Video Restoration

TriMotion: Modality-Agnostic Camera Control for Video Generation

InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars

MuCHeR: Multi-Person Camera-Centric Human Detection, Mesh Recovery and Tracking

Human Mesh Modeling for Anny Body

TryOnCrafter: Unleashing Camera Trajectories for Realistic Video Virtual Try-on via a Renderable 4D Try-on Proxy

EgoSim: Egocentric World Simulator for Embodiment Interaction Generation

DeforM: Reasoning-Guided Physics-Aware Video Generation via Spatial-Temporal Masking

Predictive Structure Improves Video Diffusion Dynamics

PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Models

Mind-to-Face: Neural-Driven Photorealistic Avatar Synthesis via EEG Decoding

ComplexMimic: Human–Scene Interaction Imitation in Complex 3D Environments

CoSyncDiT: Cognitive Synchronous Diffusion Transformer for Movie Dubbing

What Moves? Localized Motion Representations for Compositional Scene Control

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

ECHO: Ego-centric Modeling of Human-Object Interactions

InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics

Video2Reaction: Mapping Video to Audience Reaction Distribution in the Wild

SignNet-1M: Large-Scale Multilingual Sign Language Video Dataset with Downstream Benchmarks

MetaPoint: Unlocking Precise Spatial Control in Visual Generation

Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints

Measuring 3D Spatial Geometric Consistency in Dynamic Video Generation

GenLCA: 3D Diffusion for Full-Body Avatars from In-the-Wild Videos

Narrative-Driven Paper-to-Slide Generation via ArcDeck

MemoBench: Benchmarking World Modeling in Dynamically Changing Environments

VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations

Meric: A Unified Framework for Multimodal Music Generation and Retrieval via Representation Space Anchoring

Fabric Image Demoiréing Benchmark from Synthesis to Restoration

Scalable Cross-embodiment Dexterous Grasping via Morphology-Prior Diffusion

DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models

STANCE: Controllable Video Generation for Structured Dynamics via Sparse-To-dense ANChored Encoding

PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models

FlexiAvatar: Unified 3D Gaussian Human Avatars Under Arbitrary Body Visibility

Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods

InfiniteDance: Scalable 3D Dance Generation Towards in-the-wild Generalization

ReinDriveGen: Reinforcement Post-Training for Out-of-Distribution Driving Scene Generation

OmniFace: Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer

Learning to Generate Rigid Body Interactions with Video Diffusion Models

Self-supervised Garment Dynamics with Persistent Wrinkles

Recognizing Co-Speech Gestures in-the-Wild

Composing Driving Worlds through Disentangled Control for Adversarial Scenario Generation

SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence

Axolotl3D: a Unified Framework for Faithful 3D Shape Completion

GimbalDiffusion: Gravity-Aware Camera Control for Video Generation

Egocentric World Model for Photorealistic Hand Object Interaction Synthesis

EMOTE: Expressive Motion and Shape Disentanglement for Human Animation

Dynamic World Generation Made Efficient

Moiré Video Authentication: A Physical Signature Against AI Video Generation

Semantic-Aware, Physics-Informed, Geometry-Grounded Weather Synthesis

DiTex4D: Direct Text-Driven 4D Generation with Structured Latent Diffusion

PhysPO: Physics-Aware Local Preference Optimization for Physically Consistent Video Diffusion

Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting

MindFlow: Harmonizing Cognitive Semantics and Acoustic Dynamics for Facial Animation Generation in Dyadic Conversations

ID-PreFeR: ID-Preserving Face Restoration with Mixed Data Quality

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

OmniDance: Multimodal Driven Dance Video Generation with Large-scale Internet Data

Kirin: Animal Motion Generation from In-the-Wild Video

OctWorld: Long-Range World-Consistent Video Generation with Octree-based 3D Mapping

Taming Camera-Controlled Video Generation with Verifiable Geometry Reward

Beyond Inpainting: Unleash 3D Understanding for Stable Camera-Controlled Video Re-rendering

SMG: Semantic Motion Graph for Monocular Dynamic Gaussian Splatting

Inference-time Motion Calibration for Video Generation

ConfCtrl: Enabling Precise Camera Control in Video Diffusion via Confidence-Aware Interpolation

MemLearner: Learning to Query Context Memory for Video World Models

REON-NVS: Real-Time Online Novel-View Synthesis from Sparse-View Videos

GRE-Diff: Gaussian Room Embeddings for Structured Layout Diffusion

Geometry-Aware Single-Image 4D Synthesis via Dense Trajectory Generation

FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model

Diffusion Models are Open-World Affordance Learners: Leveraging Generative Priors for 3D Affordance Learning

MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control

ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning

AerialMetric: Benchmarking and Adapting UAV Monocular Metric Depth Estimation in the Real World

CustomX: Unified Character, Action, and Scene Customization in Video World Models

Video Generation Models Are Inherent Lighting Estimators

IC-World: In-Context Generation for Shared World Modeling

Layer-Aware Video Composition via Split-then-Merge

Perceiving Better Moments: Cover Frame Reselection and Enhancement for Live Photos with the Live2K Dataset

PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation

GeCo: Evaluating Geometric Consistency for Video Generation via Motion and Structure

EgoMAN: Interaction-Structured Reasoning for Egocentric 3D Hand Trajectory Prediction

Fast Sam 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recovery

Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars

PHOSA: Photorealistic 3D Sign Avatar Modeling and Benchmark

ReCamDriving: LiDAR-Free Camera-Controlled Video Synthesis for Novel Trajectories

PIAvatar: Physically Interactive Avatars via Deformation Gradient Decoupling

InsertAnywhere: Geometrically Grounded and Optics-Aware Video Object Insertion

3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement

Unified Panoramic–Gaussian Representation for Monocular 4D Scene Synthesis

ActionParty: Multi-Subject Action Binding in Generative Video Games

VERTIGO: Visual Preference Optimization for Cinematic Camera Generation

Progressive Pose-Guided 4D Animal Reconstruction from Monocular Video

PASTEL: Panoramic Alignment for Monocular 4D Scene Reconstruction

FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generation

Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos

CortexVideo: A Semantic-Spatial Dual-Anchor Framework for High-Fidelity fMRI-to-Video Reconstruction

OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation

Infinite-Homography as Robust Conditioning for Camera-Controlled Video Generation

LOOM: Weaving Geometry-Consistent Human-Object Interaction Videos via Progressive Curriculum Learning

Head Avatars with Dynamic Explicit Hair

DCARL: A Divide-and-Conquer Framework for Autoregressive Long-Trajectory Video Generation

One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Control

HOIMask: Towards Generative Masked Modeling for Human Object Interaction Generation

FlexAM: Flexible Appearance-Motion Decomposition for Versatile Video Generation Control

HiChor: Hierarchical Choreography Generation from Pop Music with Choreographic Primitives

Monocular Models are Strong Learners for Multi-View Human Mesh Recovery

OmniColor: A Unified Framework for Multi-modal Lineart Colorization

Tuning-free Visual Effect Transfer across Videos

MotionDreamer: Universal Skeletal Motion Generation for 3D Rigged Shapes

Seeing Fast and Slow: Learning the Flow of Time in Videos

MLVC: A Multi-platform Learned Video Codec for Real-World Deployment

ETCH-X: Robustify Expressive Body Fitting to Clothed Humans with Composable Synthetic Data

In-Context Sync-LoRA for Portrait Video Editing

EmbodiedHead: Real-Time Listening and Speaking Avatar for Conversational Agents

EchoStyle: Unlocking High-Fidelity Video Stylization with Reverse Data Synthesis

SignSparK: Efficient Multilingual Sign Language Production via Sparse Keyframe Learning

SpEmoC: A Balanced Speaker-Segment Multimodal Emotion Benchmark

StyleFusion360: View-Consistent Head Stylization via Adaptive Style Modulation

Generative Relightable Avatars

EgoExoMoCap: Distributed Human Motion Capture via Ego- and Exocentric Body Tracking from Head-Mounted Devices

SIMSplat: Language-Aligned 4D Gaussian Splatting for Driving Scenario Generation

Pro-Pose: Unpaired Full-Body Portrait Synthesis via Canonical UV Maps

Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations

HairWeaver: Few-Shot Photorealistic Hair Motion Synthesis with Sim-to-Real Guided Video Diffusion

AnyView: Synthesizing Any Novel View in Dynamic Scenes

Audio-Visual Camera Pose Estimation with Passive Scene Sounds and In-the-Wild Video

Learn2Fold: Structured Origami Generation with World Model Planning

The Dynamic Prior: Understanding 3D Structures for Casual Dynamic Videos

PhysConvex: Physics-Informed Dynamic Convex Fields for Reconstruction and Simulation

NeuIDO: Neural Intrinsic Dynamics Operator for Physics-Informed 4D World Models

BeyondMasks: Evaluating Causal and Physical Consistency in Video Object Removal

PLOT: Pseudo-Labeling via Object Tracking for Monocular 3D Object Detection

AutoPhyX: Automatic Text-Condition Physics Property Generation

Who Does What and Where to Go: Orthogonal Alignment and Hierarchical Planning for Multi-Entity Trajectories

OccDirector: Language-Guided Behavior and Interaction Generation in 4D Occupancy Space

MorphGS: Morphology-Adaptive Articulated Motion Transfer from Videos

PartCHOI: Part-Aware Guidance for Clothed Human-Object Interaction Generation

EmoteGPT: 3D Human Facial Expression from Natural Language Descriptions

LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing

ROSE: Real-Time Open-World Scene Understanding from Monocular Video via Compact Multimodal 4D Scene Graphs

Interaction-Aware 4D Gaussian Splatting for Dynamic Hand-Object Interaction Reconstruction

ProGVC: Progressive-based Generative Video Compression via Auto-Regressive Context Modeling

MotionEditGS: Editing Motion and Appearance of 4D Scenes from Monocular Video via Semantically Anchored Gaussians

SA-V2V: Training-Free Subject-Aware Video-to-Video Personalization

FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Arbitrary Images

Multi-Modal Controlled Coherent Motion Generation

Control-DINO: Feature Space Conditioning for Controllable Video Diffusion

KineticGS: Momentum-driven Coherent 4D Gaussian Splatting for Monocular Dynamic Scene Reconstruction

PWM-ArtGen: Part World Model for Articulated Object Generation

Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models

D-Rex : Diffusion Rendering for Relightable Expressive Avatars

LUNA: Learning Universal 3D Human Animation Beyond Skinning

Towards Flexible, Natural, Efficient Interaction for Conversational Talking Face Generation

ReconPhys: Reconstruct Appearance and Physical Attributes from Single Video

OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control

SICAGE: Speaker-Independent Culture-Aware Gesture Generation using TED4C-L Dataset

Towards Real-World Wearable Motion Reconstruction

GraphVid: Interactive Graph-Controllable Video Generation

SignRefine: Adapting Foundational Video Models for Sign Language Generation

Out of Sight, Out of Mind? Evaluating State Evolution in Video World Models

JointHOI: Jointly Generating Contact Maps Enhances Hand Object Interaction Generation

Infinite Gaze Generation for Videos with Autoregressive Diffusion

RealDyadic: Synthesizing Realistic Dyadic 3D Dialogue with Neural Appearance Priors

Taming Dynamic Clutter: Variance-Driven Adaptive Gain Control for Bio-inspired Small Target Detection

Learning Implicit Constitutive Laws for Dynamic 3D Gaussian Splatting from Monocular Videos

BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing

Learning Zero-Shot Subject-Driven Video Generation Using 1% Compute

Text Dictates, Music Decorates: Energy-based Attention for Editable Dance Generation

FlexComposer: Unified Video Compositing from Images to Dynamic Footage with Flexible Trajectory Control

Long-term Traffic Simulation via Structured Autoregressive Modeling

WristMimic: Full-Body Humanoid Control with Wrist-Guided Manipulation

Nexus-Vid: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models

CAST3D: Customizing Arbitrary 2D Assets into 3D World

DSAR: Dual-Stream Autoregressive Modeling of Temporal Cloth Dynamics for Photorealistic Animatable Avatars

EgoGVAE: Ego-body Mesh Reconstruction via Guided Variational Autoencoder

CameraAnything: Refilming Videos with Arbitrary Camera Control

RASA: Disentangled Spatial-Motional Priors for Cross-Identity Character Animation

PhysRAG: Enhancing Physics-Awareness in Video Generation via Retrieval-Augmented Generation

JacobianAvatar: Temporally Consistent Semi-rigid Avatar Reconstruction from a Monocular Video

TimeWalker: Personalized Neural Space for Lifelong Head Avatars

PhysChoreo: Physics-Controllable Video Generation with Part-Aware Semantic Grounding

SplatCtrlA: Generalizable Single Image to Fully Controllable 3D Avatar

Beyond Pixel Mimicry: Disentangled Self-Similarity Rewards for Diverse Subject-Driven Generation

ExpoMotion: A Large-Scale Benchmark and A Householder Projection Network for Multi-Exposure Fusion

SIFT: Self-Imagination Fine-Tuning for Physically Plausible Motion in Video Diffusion Models

HAT-4D: Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration

Target-Bench: Can Video World Models Achieve Mapless Path Planning with Semantic Targets?

A Dual-Transformer Architecture with Cross-Attention for Multi-Camera View Recommendation

From Synchrony to Sequence: Exo-to-Ego Generation via Interpolation

RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video

EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal

StoryBlender: Inter-Shot Consistent and Editable 3D Storyboard with Spatial-temporal Dynamics

OmniFall: From Staged Through Synthetic to Wild, A Unified Multi-Domain Dataset for Robust Fall Detection

Cycle-World: Mitigating Error Accumulation in Long-term Video World Models via Reverse-Prediction Cycle Consistency

ControlHair: Synergizing Physics Simulator and Video Diffusion for Controllable Dynamic Hair Rendering

LooseControlVideo: Directorial Video Control using Spatial Blocking

DynEval: Holistic Evaluations of T2I Generative Models in the Wild

MotionSplicer: Part-Based Motion Editing for 4D Volumetric Videos

Physics Question Scene Graph: Fine-grained Evaluation of Physical Plausibility in Text-to-Video Generation

Versatile Editing of Video Content, Actions, and Dynamics without Training

TAQ: Static-Deployable Temporal-Aware Quantization for Real-World Video Super-Resolution

DIVER: Disentangling Camera–Object and Active–Passive Motion for Video Generation

Lessons and Open Questions from a Unified Study of Camera-Trap Species Recognition Over Time

A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models

ARMS: Anchor–Relational Motion Streaming for Seamless Solo-Social Motion Transitions

TRINITY: A Multi-Perspective Benchmark for Personal-Style Video Highlight Detection

ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos

Music-to-Dance Generation via Atomic Movements

Towards Robust Driving Perception: A Flexible Scale-Driven Family for Self-Supervised Monocular Depth Estimation

MSEditor: Toward Consistent Multi-Shot Video Editing

OmniLife360: A Benchmark for 3D Reconstruction from In-the-Wild 360° Captures

MotionAnymesh: Physics-Grounded Articulation for Simulation-Ready Digital Twins

SparseCtrl-HOI: Sparse Temporal Control for Human-Object Interaction Video Generation

Test-Time Noise Guided Adaptation for Realistic Autoregressive Video Generation

YeTI: You Only Need Two Noisy Images for Real-World sRGB Noise Generation

Learning Generatable Mutual Distance for Scene-Aware Human Motion Generation

Swap the Right Identity: Spatio-Temporal Preference Optimization for Identity Swapping

TextFace: Compositional Text-Guided Identity Preserving Face Synthesis for Face Recognition

PASDiff: Physics-Aware Semantic Guidance for Joint Real-world Low-Light Face Enhancement and Restoration

IRIS: A Real-World Benchmark for Inverse Recovery and Identification of Physical Dynamic Systems from Monocular Video

FlowLess: Controlling Abstract Image Generation

InterPet4D: A Multimodal 4D Human-Pet Interaction Dataset for Pet Motion Generation

WorldCache: Content-Aware Caching for Accelerated Video World Models

Video Generation Models are General-Purpose Vision Learners

Grounding World Simulation Models in a Real-World Metropolis

(ends 12:30 PM)

Break:

Coffee Break

(ends 11:00 AM)

noon

Lunch:

Lunch

(ends 1:30 PM)

1:30 p.m.

3D Graphics and Geometric Representations [1:30-3:00]

Orals 1:30-2:45

[1:30] Heat Kernel Textures -- the Geodesic Gaussians That Do Not Splat

[1:45] NURBS Splatting: A Unified Differentiable Rendering Framework for Vector Graphics

[2:00] TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields

[2:15] Repurposing Geometric Foundation Models for Multi-view Diffusion

[2:30] MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation

(ends 3:00 PM)

Recognition, Tracking, Re-ID & Anomaly Detection [1:30-3:00]

Spotlights 1:30-2:30

[1:30] Silhouette-based Gait Foundation Model

[1:35] CMCC-ReID: Cross-Modality Clothing-Change Person Re-Identification

[1:40] QVAM: Query-guided View-aware Adaptive Modulation for Aerial-Ground Person Re-Identification

[1:45] Divide and Align: Disentangled Vision-Language Learning for Text-Based Person Anomaly Search

[1:50] PADFormer: Pose-agnostic Anomaly Detection from Sparse View Images

[1:55] RiO-DETR: DETR for Real-time Oriented Object Detection

[2:00] Align and Segment: Unsupervised Learning for Building Segmentation From Misaligned Labels

[2:05] Exclusivity-Guided Mask Learning for Semi-Supervised Crowd Instance Segmentation and Counting

[2:10] Instance Segmentation as Tracking: A New Paradigm for Multi-Small-Object Tracking with Event Cameras

[2:15] SelfMOTR: Revisiting MOTR with Self-Generating Detection Priors

[2:20] PhenoLeaf-TS: A Time-Series Benchmark for Leaf Instance Segmentation, Tracking, and Growth Stage Classification

[2:25] Event-based Gaze Control Systems for Real-time Spin Estimation in Professional Ball Games

(ends 3:00 PM)

Image Generation, Editing & Diffusion [1:30-3:00]

Spotlights 1:30-2:30

[1:30] UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer

[1:35] RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards

[1:40] Scaling Multi-Reference Image Generation with Dynamic Reward Optimization

[1:45] AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation

[1:50] Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion

[1:55] EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing

[2:00] WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing

[2:05] Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off

[2:10] GIDE: Unlocking Diffusion LLMs for Precise Training-Free Image Editing

[2:15] Push–Pull Attentional Anchoring for Diffusion Concept Erasure

[2:20] When Rubrics Fail: Error Enumeration as Reward for Reference-Free RL Post-Training

[2:25] Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting

(ends 3:00 PM)

3 p.m.

Keynote:

Yann LeCun

(ends 4:00 PM)

4 p.m.

Poster Session 4 [4:00-6:00]

Posters 4:00-6:00

Scaling Dense Prediction with Latent Decoding

Kinematics-Agnostic 3D Human Motion Prediction via Equivariant Latent Diffusion

PKINet-v2: Towards Powerful and Efficient Poly-Kernel Remote Sensing Object Detection

CogSENet: Blind Image Deblurring with Blur-Conditioned Semantic Routing and Explicit Frequency Fusion

Dual Masked Generative Adversarial Transformer for Unsupervised Domain Adaptation

G2FM: A Geodesic Flow Matching Framework with Geometric Prior for Category-Level 9-DoF Pose Estimation

Complex-Valued 2D Gaussian Representation for Computer-Generated Holography

Revisiting Avatar-As-Image: High-Fidelity Registration is All You Need

Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling

On the Diffusibility of High-Dimensional Latents

Diffusion-Based Material Regularization for Physics-Based Inverse Rendering

ReDesign: Recovering Editable Design Structures from Raster Images via Agentic Decomposition

MapDreamer: Aerial Imagery Conditioned Latent Diffusion For Lane Level Map Generation

ReSWD: ReSTIR‘d, not shaken. Combining Reservoir Sampling and Sliced Wasserstein Distance for Variance Reduction.

Heat Kernel Textures -- the Geodesic Gaussians That Do Not Splat

ShellMaker: Language-Guided Exterior Completion under Structural Constraints

DiffPro: Joint Timestep and Layer-Wise Precision Optimization for Efficient Diffusion Inference

EVAR: Edge Visual Autoregressive Models via Principled Pruning

JSON: Jigsaw Self-play Optimization for Normalizing Flows

HolisticSemGes: Semantic Grounding of Holistic Co-Speech Gesture Generation with Contrastive Flow-Matching

FlowFace: Rectifying Identity Conditioning with Riemannian Geometry for Face Generation

Bridging Online and Offline Handwriting via Differentiable Physical Rendering

FPicker: Topology-Guided Evolution for Filament Tracing in Low-SNR Microscopy

FontCopilot: Towards Generalist Multimodal Large Language Models for Holistic Chinese Font Engineering

Entropy-Controlled Flow Matching

Triangular Consistency as a Universal Constraint for Learning Optical Flow

Exo2EgoPolicy: Pose-Aligned Cross-View Policy Learning

Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models

EvoTok: A Unified Image Tokenizer via Residual Latent Evolution for Visual Understanding and Generation

GenSP: Consistent Spherical Parameterization via Learning Shape Generative Models

HuCollisionField: Resolving Self-Collisions via Neural Fields for Human Prediction

FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs

Multi-View Foundation Models

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

NURBS Splatting: A Unified Differentiable Rendering Framework for Vector Graphics

DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfaces

Adaptive Noise Covariance Scheduling under Riemannian Metrics for Diffusion Models

DiGS-Avatar: Single-Image Animatable 3D Human Reconstruction via UV-Space Diffusion

Hi-DREAM: Brain Inspired Hierarchical Diffusion for fMRI-to-image Reconstruction via ROI Encoder And visual Mapping

Controlling Embedding Spaces with Text-Conditioned Transformations

APT: Anchor-aligned Perturbations for Tamper Localization in Fully Regenerated Images

SimFlow: Simplified and End-to-End Training of Latent Normalizing Flows

DuoFlow: JVP-Free Finite-Difference Mean Flows for One-Step Image Generation

TopoFuse: Topology-Aware Tri-Planar Fusion for 3D Cryo-Electron Tomography Segmentation

Affordance-Guided Diffusion Prior for 3D Hand Reconstruction

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

Teaching an Agent to Sketch One Part at a Time

BRepFacetGen: Reverse Engineering B-Reps By Generative Face Segmentation

DOGE: Differentiable Bézier Graph Optimization for Road Network Extraction

JanusMesh: Fast and Zero-Shot 3D Visual Illusion Generation via Cross-Space Denoising

Geometric Foundation Model Distillation for Efficient Lunar 3D Reconstruction

Pathryoshka: Compressing Pathology Foundation Models via Multi-Teacher Knowledge Distillation with Nested Embeddings

REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion

MV-GEL: Language-Driven Multi-View Geometric Entity Localization on Meshes

TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields

Parametric SDF for Dynamic Surface Reconstruction

STAT: Soft Tail-dropping for Adaptive Visual Tokenization

Unsupervised Pixel-Level Semantic Left-Right Understanding of In-the-Wild Images

PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion

TreeSRNF: Square-Root Normal Fields for Generative Modelling of the Geometric and Structural Variability in Tree-like 3D Objects

Temporally Stable Generative Illumination with a One-Step Diffusion Model

Learning to Tessellate: Point Cloud Generation via Recursive Spectral Partitioning

Learning Video Dynamics with Predictive Differentiable Rendering

DeCoFlow: Structural Decomposition of Normalizing Flows for Continual Anomaly Detection

URHead: A Unified UV-Space Representation for Joint Mesh–3DGS Optimization in Head Avatars

Hybrid-LUT: Channel-Aware Hybrid Lookup Table and Filtering for Efficient Image Restoration

WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens

Pretrained Video Models as Differentiable Physics Simulators for Urban Wind Flows

WorldMesh: Generating Navigable Multi-Room 3D Scenes via Mesh-Conditioned Image Diffusion

Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback

SAM2Matting: Generalized Image and Video Matting

Learning Geometry-Aware Embedding Fields for Intrinsic Riemannian Mappings

Reflecting Process Expertise in Procedural Material Generation

AVQ-Attention: Adaptive Vector-Quantized Attention

DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising

DANTE-W: Diffuse Albedo Neural Texturing in the Wild

Language-Guided Transformer Tokenizer for Human Motion Generation

Text-based Tactile Graphics Generation for the Visually Impaired

OmniX: From Unified Panoramic Generation and Perception To Graphics-Ready 3D Scenes

Reconstructing 3D Human-Object Interaction via a Unified Triplane Space

Geodesic Flow Matching on a Riemannian Degradation Manifold for Blind Image Restoration

Pixel Ignores, Superpixel Sees: Adverse Weather Image Restoration via Semantic-Center SSM

Repurposing Geometric Foundation Models for Multi-view Diffusion

CoToGrasp: Contact-Topology-Conditioned Dexterous Grasp Synthesis via Canonical Workspace Learning

A Scalable Vector Graphics Latent Space

Differentiable Polarized Path Tracing

Monocular Avatar Reconstruction via Cascaded Diffusion Priors and UV-Space Differentiable Shading

Bridging the Geometry Mismatch: Frequency-Aware Anisotropic Serialization for Thin-Structure SSMs

ReFP-AD: Rectified Flow Preconditioning for Energy-Based Anomaly Detection

Deformable and Multi-view Gradient-Aligned Physical Adversarial Camouflage

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

VNC: A Scale-Space Foundation for Learnable 3D Surface Evolution

Vector Scaffolding: Inter-Scale Orchestration for Differentiable Image Vectorization

Generalization and Memorization in Rectified Flow

Two-Parameter Flow Map Learning for Continuous-Time Diffeomorphic Image Registration

LumiTokens: 3D Relighting via Token-Space Lighting Transformation

Q-BridgeNet: A Quantization Network for Cross-Lingual Sign Language Translation

Penetration-Free Compositional 3D Generation via Gaussian Surface Offset

Diffusion Integrated Gradients: Controllable Path Generation for Flexible Feature Attribution

PRISM: Latent Composition Consistency for Single-Image Reflection Removal

DiffGI: Differentiable Geometry Images for High-Fidelity Thin-Shell 3D Generation

MagnetGS-Mesh: High-Quality Multi-Object Mesh Reconstruction via Adaptive Surface Optimization

MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation

WorldAgents: Can Foundation Image Models be Agents for 3D World Models?

K-Mask: Kinematic-Aware Masked Modeling for Controllable Text-to-Motion Synthesis

Robust 3DGS-based SLAM via Adaptive Kernel Smoothing

Stitched Embeddings: A Unified Latent Space for 3D Garments and 2D Patterns

TiltDiff: Tilted Weight-Space Diffusion for Neural Network Generation

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

ExPLoRe: Expert Patch-Level Loss Routing for Multi-Objective Masked Image Modeling

InnoText: A Unified Model for Visual Text Generation and Editing

CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation

PIPBench: A Profile-Inclusive Framework for Personalized Image Generation Evaluation

CORE-V: Chain-Of-thought REasoning for Image Editing with Visual Interaction

Layout-Conditioned Autoregressive Text-to-Image Generation via Structured Masking

NumColor: Precise Numeric Color Control in Text-to-Image Generation

Vision Bridge Transformer at Scale

OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Based Video Editing

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

UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer

Universal Image Immunization against Diffusion-based Image Editing via Semantic Injection

Anchoring on Reality: Breaking the Pseudo-Target Ceiling in Makeup Transfer

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

Anti-Prompt: Image Protection against Text-Guided Image-to-Video Generation

LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature Caching

UEval: A Benchmark for Unified Multimodal Generation

LISA: Locality-Informed Speculative Decoding for Accelerating Autoregressive Image Generation

RePlan: Reasoning-Guided Region Planning for Complex Instruction-Based Image Editing

UNet-Twice: A Simple Structured Reference-based Inpainting Framework

Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility

SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video

Query-Kontext: An Unified Multimodal Model for Image Generation and Editing

Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priors

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

In-context Region-based Drag: Drag Any Region to Any Shape

FlowInOne: Unifying Multimodal Generation as Image-in, Image-out Flow Matching

AR-CoPO: Align Autoregressive Video Generation with Contrastive Policy Optimization

RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards

Text-Conditioned Background Generation for Editable Multi-Layer Documents

Multi-dimensional Preference Alignment by Conditioning Reward Itself

Follow-Your-Mind: Towards Inversion-Free Brain-Driven Visual Context Synthesis and Editing

Histocomponent-driven Universal Model for Virtual Immunohistochemistry Multiplex Staining via Joint Manifold Evolution

Learning to Stylize by Learning to Destylize: A Scalable Paradigm for Supervised Style Transfer

VSDiffusion: Taming Ill-Posed Shadow Generation via Visibility-Constrained Diffusion

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

VTEdit-Bench: A Comprehensive Benchmark for Multi-Reference Image Editing Models in Virtual Try-On

Training-Free Multi-Concept Image Editing

DARE to Mitigate Hallucination: Dual-path Auto-Regressive-aware Editing

Scaling Multi-Reference Image Generation with Dynamic Reward Optimization

Q-REAL: Towards Naturalness and Distortion Evaluation for AI-Generated Content

RankT2I: A Submodular Framework for Discovering Interpretable and Diverse Semantics in Text-to-Image Models

From Open Loop to Closed Loop: A Test-Time Iterative Optimization Framework for Reference-Consistent Image Generation

NoiseTilt: Noise-Tilted Reverse Kernels for Diffusion Reward Alignment

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

ScrollScape: Unlocking 32K Image Generation With Video Diffusion Priors

Attribute Token Arithmetic: Disentangled and Continuous Semantic Control for Visual Autoregressive Models

MPO: Single-Stream Policy Optimization for Efficient Text-to-Image Alignment

MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training

GenAgent: Scaling Text-to-Image Generation via Agentic Multimodal Reasoning

IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Generation

Revisiting Autoregressive Models for Generative Image Classification

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation

FitControler: Toward Fit-Aware Virtual Try-On

A²-Edit: Precise Reference-Guided Image Editing of Arbitrary Objects and Ambiguous Masks

LoGAN: Multilingual Font Localization with Generative Agents

Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models

RubricRL: Simple Generalizable Rewards for Text-to-Image Generation

ELDiff: When Evidential Learning Meets Text-to-Image Diffusion

Rethinking Garment Conditioning in Diffusion-based Virtual Try-On: Decouple, Don't Denoise

UniTranslator: A Unified Multi-modal framework for End-to-end In-Image Machine Translation

Layering Virtual Try-On

PosterCopilot: Toward Layout Reasoning and Controllable Editing for Professional Graphic Design

Setting the Stage: Text-Driven Scene-Consistent Image Generation

PPTArena: A Benchmark for PowerPoint Editing

Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation

Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion

RADIANCE: Relative Adaptive Denoising with IP-Adapter for Novel Concept Enhancement

UniREditBench: A Unified Reasoning-based Image Editing Benchmark

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models

Policy-Based Tuning of Autoregressive Image Models with Instance- and Distribution-Level Rewards

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

Reward Lightning: Fast Video Generation via Homologous Preference Distillation

Reinforcement Learning for Multimodal Diffusion Language Models via Bidimensional Trajectory and Thought Optimization

Direct Diffusion Score Preference Optimization via Stepwise Contrastive Policy-Pair Supervision

DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing

OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models

Personalized Reward Modeling for Text-to-Image Generation

Distribution Matching Distillation Meets Reinforcement Learning

From Draft to Draft-Free: One-Step Video Object Removal via Privileged Distillation and Fast Planting

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

Unmasking-Time Visual Calibration for Hallucination Mitigation in Multimodal Discrete Diffusion Language Models

EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing

DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models

GR-GRPO: Graph-Diffused Credit for Autoregressive Image RL Alignment

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

Achieving Subcategorical Erasure in Text-to-Image Models

LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents

FairSteer: Cross-Attention Steering Towards a Fairer Text-Guided Image Generation

Unsafe by Reciprocity: How Generation–Understanding Coupling Undermines Safety in Unified Multimodal Models

WearWow: Native 2K Multi-Garment Virtual Try-On via Adaptive Token Packing and Preference Alignment

Towards In-Context Tone Style Transfer with A Large-Scale Triplet Dataset

Target-aware Image Editing via Cycle-consistent Constraints

FineEdit: Fine-Grained Image Edit with Bounding Box Guidance

SpecV: Specification Verification for Robust Unified Multimodal Evaluation

WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing

CGCE: Classifier-Guided Concept Erasure in Generative Models

Accelerated Likelihood Maximization for Diffusion-based Versatile Content Generation

Beyond Absolute Scores: Relative Edit-induced Difference for Generalizable Image Aesthetic Assessment

FDM-MFVT: Few-step Sampling Diffusion Model for Mask-Free Virtual Try-On

DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space

Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation

RefReward-SR: LR-Conditioned Reward Modeling for Preference-Aligned Super-Resolution

Omni-RRM: Advancing Omni Reward Modeling via Automatic Rubric-Grounded Preference Synthesis

Reinforcing Video Reasoning with Focused Thinking

Obliviate: Erasing Concepts from Autoregressive Image Generation Models

Not All Prediction Targets Keep Training-Free Diffusion Guidance on the Manifold

Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning

LightFusion: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation

OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models

Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models

UniReflect: Self-Reflection Tuning for Unified Multimodal Understanding and Generation

PhyEditBench: A Real-World Multi-Stage Benchmark for Physics-Aware Image Editing

MagicMakeup: A Region-Controllable Diffusion Transformer for High-Fidelity Makeup-Transfer

Wavelet-Guided Semantic Signal Compensation for Inversion-Free Image Editing

Rethinking Reward Signals in Video GRPO: When Scores Become Targets

Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off

Correlation-Weighted Multi-Reward Optimization for Compositional Generation

Rethinking Robust Adversarial Concept Erasure in Diffusion Models

On-Policy Diffusion Reinforcement Learning Meets Off-Policy Quality Anchoring

StereoEdit: A Diffusion-Based Framework for Stereo-Consistent Image Editing

Unlocking Complex Image Editing via Natively Interleaved Visual Textual CoT with Deep Confidence Reasoning

OSVE: One Step Video Editing with One Step Diffusion Models

Benchmarking MLLMs on Mistake Recognition and Explanation in Single-Step Components of Cooking

DisRM: Reward Modeling as Discriminative Prediction

InstaEdit: Instant Image Editing via Optimized Noise Prediction

TexTailor: Inference-Time Textual Guidance Tailoring for Multimodal Diffusion Transformers

Coding with Eyes: Visual Feedback Unlocks Reliable GUI Code Generating and Debugging

PhysEdit: Physically Consistent Image Editing via Causal Enforcement

MVI2V: Human Centric Image to Video Generation with Multiview Consistent Appearance

GIDE: Unlocking Diffusion LLMs for Precise Training-Free Image Editing

Zero-Shot Image Personalization from Personas

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models

The Path to Reconciling Quality and Safety Alignment in Text-to-Image Generation

AVSR-Diff: Scale-Agnostic Diffusion Priors for Temporally Consistent Arbitrary-Scale Video Super-Resolution

Optimization-Guided Diffusion for Interactive Scene Generation

OSOR: One-Step Diffusion Inpainting for Effect-Aware Object Removal

h-Flow: Flexible Flow-based Image Editing via Doob's h-Transform

Reference-Free Quality Assessment for Virtual Try-On via Human Feedback

CellFluxRL: Biologically-Constrained Virtual Cell Modeling via Reinforcement Learning

NearID: Identity Representation Learning via Near-identity Distractors

SCALE: Semantic-Calibrated Guidance Enhancement for Prompt-Faithful Diffusion

Seeing to Ground: Visual Attention for Hallucination-Resilient MDLLMs

Intermediate Text Representation Guided Text-to-Image Generation for Enhancing One-and-Only Alignment

Push–Pull Attentional Anchoring for Diffusion Concept Erasure

V-HOLD: Stabilizing Flow Trajectories to Rethink the Edit–Preservation Trade-off

Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs

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

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

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

H-Adapter: Pose-Robust Hairstyle Transfer via Attention-Derived, Source-Aligned Hair Masks

Self-Improving Diffusion Classifiers with Minority Preference Optimization

MirrorPPR: Exemplar-Based Portrait Photo Retouching

When Rubrics Fail: Error Enumeration as Reward for Reference-Free RL Post-Training

Joint Alignment and Distillation for Video Generation via Sample-Guided Distribution Matching

Syn-GRPO: Self-Evolving Data Synthesis for MLLM Perception Reasoning

EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders

SupGRPO: Enhancing GRPO with Matching-based Online SFT for Text Spotting

i-Design: Step-by-Step Graphic Layout Design with Progressive Aesthetic Policy Optimization

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

DSH-Bench: A Difficulty- and Scenario-Aware Benchmark with Hierarchical Subject Taxonomy for Subject-Driven Text-to-Image Generation

Editing Everything Everywhere All at Once

Learning Consistency in Reward Modeling for Multi-Modal Reasoning

OpenSubject: Leveraging Video-Derived Identity and Diversity Priors for Subject-driven Image Generation and Manipulation

SR-Edit: Region-Aware Image Editing via Self-Refinement

Wan-R1: Verifiable-Reinforcement Learning for Generalizable Video Reasoning

InstantRetouch: Personalized Image Retouching without Test-time Fine-tuning

Semantically Aligned Gradient-Driven Context-Preserving Image Editing

When Cars Have Stereotypes: Auditing Demographic Bias in Objects from Text-to-Image Models

FED-Bench: A Cross-Granular Benchmark for Disentangled Evaluation of Facial Expression Editing

Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples

Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting

RCEdit-500K: Reference Completion for Image-Conditioned Image Editing

VLTR: Vision-Language Tool Reasoning for Instruction-Guided Image Editing

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

M4-SAR: A Multi-Resolution, Multi-Polarization, Multi-Scene, Multi-Source Dataset and Benchmark for optical-SAR Object Detection

Decoding Children’s Gait Behavior

InclusiveHuman-10K: Towards Inclusive Human Parsing Beyond the Intact-Limb Assumption

EDM:Event-guided Diffusion Model for Video Shadow Detection in Complex Dynamic Scenes

Streaming Dense Voxel Representations for 3D Occupancy Prediction

Learning Probabilistic Embeddings for Unsupervised Action Segmentation

Region-Aware Multimodal Interleaving for Animal Re-Identification

SGQA: Semantic-Geometric Quality Alignment for Training-Free Few-Shot Instance Segmentation

Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipeline

Silhouette-based Gait Foundation Model

Fast Dynamic Prototypes for Unsupervised Anomaly Detection and Localization

Free‑CD: Probabilistically Decoupled Training-Free Open-Vocabulary Change Detection with Resolution-Invariant Feature Inversion

VCBench: A Streaming Counting Benchmark for Spatial-Temporal State Maintenance in Long Videos

STEP: Score-Based Temporal Energy for Human Pose Video Anomaly Detection

Rethinking Continual Anomaly Detection on the Edge: Benchmarking Under Realistic Industrial Conditions

FoundYou: A Unified Model for Personalized Segmentation and Retrieval

Back-Tracking from Clarity: Self-Learning to See Text from Afar

RePL: Pseudo-label Refinement for Semi-supervised LiDAR Semantic Segmentation

One Slide, Many Views: Unifying Complementary Foundation Model Perspectives for WSI Analysis

High-Throughput Event-Based Feature Detection and Tracking on an Embedded CPU

LogiCo: A Unified Framework for Logical and Structural Anomaly Detection

MiNQVIS: Mitigating Noisy Queries for Robust Online Video Instance Segmentation

LlamaSeg: Image Segmentation via Autoregressive Mask Generation

CMCC-ReID: Cross-Modality Clothing-Change Person Re-Identification

PS-MOT: Cultivating Instance Awareness from Point Seeds for Multi-Object Tracking

Granular Semantic Cognition for Visible-Infrared Person Re-Identification

A Benchmark for Heterogeneous Stereo Deblurring with Physically- and Epipolar-constrained Cross Attention

Bottom-up modeling of repeated elements via single image analysis-by-synthesis

DeMuS: Learning Decoupled Matching and Scoring for Batch Zero-Shot Industrial Anomaly Detection

Uncertainty-aware tree height change regression

Hierarchical Hyperbolic Representation Learning for Aerial-Ground Person Re-Identification

SceneDiff: A Benchmark and Method for Multiview Object Change Detection

Beyond Attention: Convolutional Global Context for Remote Sensing Change Detection

NUN: Nested Unfolding Network for Real-World Concealed Object Segmentation

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

QVAM: Query-guided View-aware Adaptive Modulation for Aerial-Ground Person Re-Identification

YesTrack: Referring Multi-Object Tracking via MLLM-based Yes/No Reasoning

CountEx: Fine-Grained Counting via Exemplars and Exclusion

GroundingAnomaly: Spatially-Grounded Diffusion for Few-Shot Anomaly Synthesis

InstaPano: Zero-shot Instance Layout Controlled Panorama Generation Via Global Attention Fusion

Sound-based Multi-Person 3D Pose Estimation

CerDETR: Cell-Prior Empowered DETR for Cervical Lesion Detection

Where and What: Long-Term Object Tracking in Egocentric Videos

Making Partial-Label Datasets Easier: A Simple Yet Highly Effective Data Augmentation for Deep Partial-Label Learning

Efficient RGB-T Object Detection via Sparse Cross-Modality Fusion

ARGOS: Who, Where, and When in Agentic Multi-Camera Person Search

SCORE: SubDistribution-aware Collaborative Knowledge Reinforcing for Cloth-Hybrid Lifelong Person Re-Identification

SegVGGT: Joint 3D Reconstruction and Instance Segmentation from Multi-View Images

Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective

Divide and Align: Disentangled Vision-Language Learning for Text-Based Person Anomaly Search

Generating a Paracosm for Training-Free Zero-Shot Composed Image Retrieval

GoStop: Reinforcement Learning for Adaptive Temporal Aggregation in Event-Based Feature Tracking

IREU: Identity-Related Encoder-Only Unlearning for Customized Portrait Generation

EM3M: An Electron Micrograph Dataset for Microstructural Segmentation and Generation

WebEyeTrack: Scalable Eye-Tracking for the Browser via On-Device Few-Shot Personalization

EVEE: Event-Based Online Adaptation for Matching on Unknown Targets

TMI: Text-to-Image Meets Image-to-Image for Complementary Data Synthesis to Boost Long-Tailed Instance Segmentation

Seek to Segment: Active Perception for Panoramic Referring Segmentation

Single-Query Person-Centric Bimanual Hand-Object Interaction Detection

DeCo: Zero-Shot Anomaly Generation through Decoupling and Recoupling

UniScale: Arbitrary-Scale Anomaly Generation

FusionTrack: Collaborative Multi-Object Tracking with Arbitrary Multi-UAVs

Environmental Change Detection for Real-World Change Analysis

PADFormer: Pose-agnostic Anomaly Detection from Sparse View Images

SplitHDR: Saturation-Aware HDR Recovery and Denoising for Real-Time Detection

Disentangling Rotation and Translation from SE(3)-Equivariant Features for Shape Assembly

DeltaDeno: Zero-Shot Anomaly Generation via Delta-Denoising Attribution

History-Aware Transformation of ReID Features for Multiple Object Tracking

Beyond Aesthetics: Quantifying Information Loss in Turbid Scenes

Rectified Embedding Flow Learning for Aerial Multi-view  Geo-localization

Unsupervised Source-Free Ranking of Biomedical Segmentation Models Under Distribution Shift

Beyond Common Sense: Grounding Logical Anomaly Detection in Inspection Criteria

P3-SAM: Native 3D Part Segmentation

Low-latency Event-based Object Detection with Spatially-Sparse Linear Attention

Per‑Object IoU Forecasting for Deadline‑Aware Real‑Time Embedded Detection Control

Compositional Non-Face Re-Identification Pressure under Cumulative Vision Releases

StAR: Segment Anything Reasoner

RiO-DETR: DETR for Real-time Oriented Object Detection

ZMIS-SAM: Segment Anything Model Enhanced With Wavelet Transform For Zooplankton Microscopy Image Instance Segmentation

TiCRL: Textual Image Classification with Reinforcement Learning-Based Curriculum Learning

Slim-DETR: Real-Time Tiny Object Detection with Efficient Interaction and Gaussian Query

O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning

Decoupling Moment from Event for Video Temporal Grounding

PA-VAD: Diffusion-Based Pseudo-Only Video Anomaly Detection via Domain-Aligned Memory Updates

Align and Segment: Unsupervised Learning for Building Segmentation From Misaligned Labels

DDStereo: Efficient Dual Decoder Transformers for Stereo 3D Road Anomaly Detection

CLUE-VAD: Structured Semantic Clues for Understanding Explainable Events in Video Anomaly Detection

ODONet: Online Dynamic Offset Network for Visual Object Tracking

BrainFIBRE: A Foundation Model via Information Decomposition for Brain Microstructure

MCVL: Multi-Space Cross-View Learning for Aerial-Ground Person Re-Identification

HieDG: A Hierarchical Discrete Geometry-Guided Framework for Multi-Animal Tracking

UnderOneFacade: Worldwide Facade Semantic Segmentation Benchmark Dataset

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

GH-ESD: Grounded Hypothesis-Driven Error Slice Discovery for Instance-Level Vision Tasks

Constrained Rotation Optimization: Revisiting Crop-Based Gaze Estimation

Exclusivity-Guided Mask Learning for Semi-Supervised Crowd Instance Segmentation and Counting

DualCount: Structurally Consistent Density and Point Modeling for Zero-Shot Object Counting

HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark

Proximity-CLIP: Text-Guided Semantic Proximity Learning for Zero-Shot Anomaly Detection

Uncertainty-Weighted Fusion of Image and Synthetic Event for Video Anomaly Detection

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

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

SAGE: A Synchronized Action and Gaze Estimation Framework for Comprehensive Human Behavior Analysis

FuDU: A Fuzzy Dual-dimension Uncertainty Framework for Streaming Active Learning in Industrial Defect Detection

InstanceControl: Controllable Complex Image Generation without Instance Labeling

ANFI: Rethinking Neighbor Feature Interaction in Person Re-ID

Instance Segmentation as Tracking: A New Paradigm for Multi-Small-Object Tracking with Event Cameras

Online 3D Instance Segmentation at task-oriented granularity with Unposed Monocular Video

ArcAD: Anomaly-Rectified Calibration for Cold-Start Supervised Anomaly Detection

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

HLRAD: High-dimensional Latent Representation for Unified Anomaly Detection

Towards Video Anomaly Detection from Event Streams: A Baseline and Benchmark Datasets

Learning Semantic-Robust Change Detection via Semantic-Invariant Self-Distillation

WAPR: A Foundation Model for Wide-Angle Refinement in Unseen Object Pose Estimation

CAR-MIL: Counterfactual Attention Regularization for Multiple Instance Learning

Local Spacing-Aware Hungarian Matching for Stable Point-Supervised Crowd Counting

SARIF: Segment Anything for Robust Image Forensics

A Comprehensive Analysis about Unsupervised Outlier Detection for Images

SelfMOTR: Revisiting MOTR with Self-Generating Detection Priors

On-Orbit Real-Time Wildfire Detection Under On-Board Constraints

A Simple Baseline with Placement Prior for Point-Supervised Oriented Object Detection

RT-DocLayout: Real-Time End-to-End Document Layout Analysis with Reading Order in the Wild

Pseudo-Stereo Inputs: A Solution to the Occlusion Challenge in Self-Supervised Stereo Matching

ISAC: Training-Free Instance-to-Semantic Attention Control for Multi-Instance Generation

RT-RMOT: A Dataset and Framework for RGB-Thermal Referring Multi-Object Tracking

3D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identification

Robust Zero-shot Anomaly Detection under Limited Auxiliary Anomaly Priors

Reliability-Aware 3D Geometric Injection for Universal Person Re-identification

Denoising-Enhanced Coarse-to-Fine Infrared Small Target Detection with Attention Prior-Guided Knowledge Distillation

BAAF: Universal Transformation of One-Class Classifiers for Unsupervised Image Anomaly Detection

MEVL-STP: Multi-Encoder and Vision Language Model for Arbitrarily Shaped Scene Text Spotting

ModTrack: Sensor-Agnostic Multi-View Tracking via Identity-Informed PHD Filtering with Covariance Propagation

PhenoLeaf-TS: A Time-Series Benchmark for Leaf Instance Segmentation, Tracking, and Growth Stage Classification

Rapidly Deploying On-Device Eye Tracking by Distilling Visual Foundation Models

Diagnosing Aerial-View Object Detectors with Foundational Image Generative Models

CRD-Net: Frequency-Adaptive Feature Injection and Change Decoupling for Building Damage Assessment

Don’t Starve the Boundaries: Boundary-Constrained Label Propagation for Weakly Supervised 3D Segmentation

Motion-aware Sparse Pipeline for Lightweight Object Tracking

CGCC: Towards Generalizable Clothes-Changing Person Re-Identification

Segmenting, Fast and Slow: Real-Time Open-Vocabulary Video Instance Segmentation with Dual-Path Processing

Cross-Species Animal Re-Identification with Semantic Consistency Learning

Following the Flow: Advection-Consistent Modeling for Event-based Small Object Detection

Bounding-Box Trajectories Matter for Video Anomaly Detection

EVKit: An Open-source Flexible Toolkit for Efficient Event Camera Data Storage and Loading

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

Event-based Gaze Control Systems for Real-time Spin Estimation in Professional Ball Games

IACD: Iterative Adversarial Collaborative Detection via Dual-Perspective Blind Spot Discovery

VIGA: View-Conditioned and Identity-Guided Adaptation for Aerial-Ground Person Re-Identification

Point2Pose: Occlusion-Recovering 6D Pose Tracking and 3D Reconstruction for Multiple Unknown Objects Via 2D Point Trackers

ProtoFair: Fair Self-Supervised Contrastive Learning via Pseudo-Counterfactual Pairs

Segmentation-Guided Homography Estimation for Long-Term Planar Tracking

DETRPose: Real-Time End-to-End Multi-Person Pose Estimation via Modified Transformer Decoder and Novel Denoising Keypoints

(ends 6:00 PM)

Demo Session 4 [4:00-6:00]

(ends 6:00 PM)

6 p.m.

Reception:

Reception / Concert

(ends 9:00 PM)

SAT 12 SEP

9 a.m.

Keynote:

Jamie Shotton

(ends 10:00 AM)

10 a.m.

Panel:

Can AI Build New Knowledge?

(ends 10:30 AM)

10:30 a.m.

Break:

Coffee Break

(ends 11:00 AM)

Demo Session 5 [10:30-12:30]

(ends 12:30 PM)

Poster Session 5 [10:30-12:30]

Posters 10:30-12:30

Don’t Settle at the Mode! Mitigating Diversity Collapse in Pretrained Flow Models via Feature Self-Guidance

Diffusion-based dual-view reflection removal

ParaFlow: Parallel Sampling for Flow Matching Models

Direct Autoregressive Diffusion Distillation via Error-aware Causal Pretraining

Training-Free Refinement of Flow Matching with Divergence-based Sampling

LACON: Training Text-to-Image Model from Uncurated Data

Discrete Diffusion Models with MLLMs for Unified Medical Multimodal Generation

Discrete Diffusion Bridges for Spatiotemporally Aligned Image Translation and Generation

RawGen: Learning Camera Raw Image Generation

Self-transcendence: Is External Feature Guidance Indispensable for Accelerating Diffusion Transformer Training?

AViTS：Adaptive Spatiotemporal Token Selection for Efficient Dynamic-Resolution Generation

Expert Weaving: Marrying Masked AutoRegressive and Diffusion Models for Unified Image Restoration

Source-Agnostic Image Translation Based on Latent Aware Adaptive Masking

SSBP: Stage-Specialized Block Pruning for Video Diffusion Models

ProSR: Semantic-Prototype-Guided Discrete Modeling for Physically Consistent SAR Super-Resolution

V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising

Efficient and High-Quality Depth Estimation via Pixel-Space Diffusion with Linear Attention

Prompt2Effect: Training-Free LoRA Synthesis for Controllable Video Effects

Allo{SR}2: Rectifying One-Step Super-Resolution to Stay Real via Allomorphic Generative Flows

NaP-Control: Navigating Diffusion Prior for Versatile and Fast Character Control

UltraGen: Efficient Ultra-High-Resolution Image Generation with Hierarchical Local Attention

Inference-Time Scaling of Diffusion Models via Progressive Pruning Search

DiTailed: Ensuring Visual Object Consistency in Text-Image-to-Image Flow Matching Models

Vitality-Aware Compression for Efficient Image-to-Shape Diffusion Transformers

SK-Adapter: Skeleton-Based Structural Control for Native 3D Generation

ARVAR: Accelerating Visual Autoregressive Model via Attention Retrospect

ViBe: Ultra-High-Resolution Video Synthesis Born from Pure Images

LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion

Generative Refinement Network for Visual Synthesis

When Distillation Breaks Motion Control: Restoring Generative Trajectories for Fast Video Generators

HNDiff: Haze-Noise Diffusion for Image Dehazing

QualiTeacher: Quality-Conditioned Pseudo-Labeling for Real-World Image Restoration

Difficulty-Conditioned Attribute-Specific Restoration for Low-Light Image Enhancement

From smooth to sharp: Frequency-Decoupled Latent Optimization for Realistic Image Generation

Learning to Corrupt for Better Restoration

Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorations

Physics Meets Perception: A Reinforcement Learning Framework for Unpaired Real-World Image Dehazing

RefAlign: Representation Alignment for Reference-to-Video Generation

Glance: Accelerating Diffusion Models with 1 Sample

Analyzing and Improving Training-Free Fast Sampling of Text-to-Image Diffusion Models

Towards Scalable Pre-training of Visual Tokenizers for Generation

Spectral Consistent Flow for One-step 3D Medical Image Translation

Adversarial Score Distillation for Stable One-Step Diffusion in Real-World Image Super-Resolution

SD3.5-Flash: Distribution-Guided Distillation of Generative Flows

From Noise to Events: Conditional Diffusion for Event Data Augmentation

Region-Aware Test-Time Scaling for Compositional Image Generation

Decoupling Complexity from Scale in Latent Diffusion Model

Beyond the Boundary: RL-Driven Solution Space Exploration for Blind Face Restoration

EMAG: Self-Rectifying Diffusion Sampling with Exponential Moving Average Guidance

QWERTY: Training-Free Motion Control via Query-Warped Video Diffusion Transformers

Histogram-constrained Image Generation

RTE-FM-Dehazer: Radiative Transfer Equation Inspired Flow Matching for Real-World Image Dehazing

Parsimonious Flow Matching for Efficient Image Generation

AlignMorph: Tuning-Free Diffusion Image Morphing via Explicit Semantic Transport

DiverseVAR: Balancing Diversity and Quality of Next-Scale Visual Autoregressive Models

SkelEM: Explicit Decoupling of Topology and Details for Self-supervised Axial Super-Resolution in Volume Microscopy

UNITY: Attention Flow Networks for Adaptive Conditioning in Diffusion

SLAIR: Structured Latent Flow Matching for All-in-One Image Restoration

Recolour What Matters: Region-Aware Colour Editing via Token-Level Diffusion

Semantic Browsing: Controllable Diversity for Image Generation

InverseCrafter: Efficient Video ReCapture as a Latent Domain Inverse Problem

Fill2SR: Repurposing Inpainting Diffusion Transformers for Real-World Super-Resolution

Reconstruction-Anchored Diffusion Model for Text-to-Motion Generation

Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

CMDer: Controllable Mode Decomposition-Based Single Motion Synthesis with Diffusion

SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization

Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders

Solving Diffusion Inverse Problems with Restart Posterior Sampling

Posterior Augmented Flow Matching

Contrastive Conditional–Unconditional Alignment for Long-tailed Diffusion Model

D3F-IR: Dual-Domain Deterministic Flow Matching for Visible-to-Infrared Translation

GLARE: Towards Generalizable Detection of Latent Diffusion Images with Global-Local Reconstruction Error

ColorFM: An Optimization-to-Learning Framework for Color Transfer via Flow Matching

Be Tangential to Manifold: Discovering Riemannian Metric for Diffusion Models

Straight-Path Flow Matching for Incomplete Multi-View Clustering

ART-VSR: Adaptive Rectified Trajectories for One-Step Video Super-Resolution

AccelAes: Accelerating Diffusion Transformers for Training-Free Aesthetic-Enhanced Image Generation

Zero-Shot Inference-Time Rectification for Real-World Arbitrary-Scale Super-Resolution

GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models

OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolution

Representation Alignment for Just Image Transformers is not Easier than You Think

G3AFT: Glance Guided Gradient Aligned Fine-Tuning for Visual Autoregressive Models

UniCSG: Unified High-Fidelity content-constrained style-driven generation via Staged Semantic and Frequency Disentanglement

Hi-DiT: Hybrid Latent-Pixel Diffusion Transformer for Image Generation

Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers

MTVDiff: Multimodal Conditional Latent Diffusion for Enhanced Thermal-to-Visible Face Translation

SAND: Stage-Aware Noise Decomposition for Training-Free Diffusion Guidance

Jumping the Landing Phase: Noise Variance Matching Enables Accurate Few-Step Inversion

AnyStyle: A Single LoRA is Sufficient for Image-Guided Style Transfer

Rethinking Real-World MRI Denoising: Learning from Physical Noise

FUMO: Prior-Modulated Diffusion for Single Image Reflection Removal

MaterialFlow: Attribute-Disentangled Material Transfer via Trajectory-Aware Velocity Modulation

FreqOrtho-SR: Frequency-Guided Orthogonal Expert Learning for Real-World Image Super-Resolution

Diffusion Image Generation with Explicitly Modeling of Data Manifold Geometry

Linear Fusion MultiDiffusion for Fast Training-Free Spherical Panorama Generation

Introspective Attention Modulation for Safe Text-to-Image Generation

Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models

Continuous Adversarial Flow Models

WaterGen: Decoupling Scene and Medium in Underwater Image Generation

ReAL: Reference-to-Image (R2I) Aware Latent Diffusion for Image Super-Resolution

Stochastic Optimal Control Sampling for Diffusion Inverse Problems

Fair and Faithful: A Diffusion-Enhanced Dataset and Hybrid State-Space Mamba for Face Super-Resolution

High-Resolution Artwork Outpainting with Global Blueprint Guidance and Layout Control

Image Warping for Image-to-Image Translation

ConceptWeaver: Weaving Disentangled Concepts with Flow

Beyond Linear Shortcuts: Rectifying Diffusion Preference Optimization with Intrinsic Generative Geometry

TEASR: Training-Efficient Any-Step Diffusion Transformer for Real-World Image Super-Resolution

D2PO: Optimizing Diffusion Samplers via Dynamic Preference

AC3S: Adaptive Conditioning for 3D-Aware Synthetic Data Generation

Spectral Prior for Reducing Exposure Bias in Diffusion Models

Unified Multi-plane Autoregressive Diffusion for 3D Multi-Contrast MRI Synthesis

Y-diff: Structure-Texture Decoupled Diffusion Distillation for H&E-to-pCLE Translation

DiffRGD: An Inference-Time Diffusion Guidance Through Riemannian Gradient Descent

Dual-End Consistency Model

GeoFlow: Efficient Driving Video Generation via Geometry-Aligned Priors

Controllable Generative Reference for Stereo Image Compression via Reliability-Aware Gating

D²R²OSR: Degradation-Disentangled Representation for Real-World Omnidirectional Image Super-Resolution

Towards Consistent and Efficient Dataset Distillation via Diffusion-Driven Selection

Cross-Resolution Distribution Matching for Diffusion Distillation

RhymeFlow: Training Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling

Flow Straight to Reality: Perceptually Consistent Flow Matching for Efficient Image Restoration

FMA-Net++: Motion- and Exposure-Aware Joint Video Super-Resolution and Deblurring

Anchoring and Steering Diffusion: Enhancing the Faithfulness of Text-to-Image Generation at Inference Time

PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation

GMODiff: One-Step Gain Map Refinement with Diffusion Priors for Efficient HDR Reconstruction

Exposure Bias Can Alleviate Itself via Directional and Frequency Rectification in Flow Matching

BiSLW: Bi-Spectral Latent Watermarking for Generative Diffusion Models

EFlow: Fast Few-Step Video Generator Training from Scratch via Efficient Solution Flow

Co-evolving Representations in Joint Image-Feature Diffusion

Extreme Face Super-Resolution through Identity Fitting and Decoupling

Momentum Guidance: Plug-and-Play Guidance for Flow Models

Which Layer Causes Distribution Deviation? Entropy-Guided Adaptive Pruning for Diffusion and Flow Models

Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning

Tuning Real-World Image Restoration at Inference: A Test-Time Scaling Paradigm for Flow Matching Models

MeanTalker: Efficient and Expressive Speech-Driven 3D Facial Animation via Geometric-Aware Mean Flow

Spectral and Trajectory Regularization for Diffusion Transformer Super-Resolution

ECTraj: Enhanced Consistency Training for Multi-Agent Trajectory Prediction

Short-to-Long Functional Connectivity Transfer via Structure-Aware Latent Diffusion

RefDiT: Local Attribute Guidance in Reference-Based Image Generation

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

DTI: Dynamic Trajectory Initialization for Generative Face Video Super-Resolution

Rdm: Re-conceptualizing Distribution Matching as a Reward for Diffusion Distillation

ELT: Elastic Looped Transformers for Visual Generation

AdaBridge-SR: Adaptive Bridge Matching for Real-World Image Super-Resolution

Rethinking Token Reduction for Diffusion Models via Output-Similarity-Awareness

Beyond Prompts: Unconditional 3D Inversion for Out-of-Distribution Shapes

Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectories

Early Estimation of Language to Latent Alignment in Diffusion Models

TanGO: Training-Free 3D Editing via Tangent-Space Guidance and Optimization

Unified Backbone Refinement for Diffusion Models via Internal-Latent Analysis

FMS2: Unified Flow Matching for Segmentation and Synthesis of Thin Structures

DICT: Data Injection and Contrastive Trajectory Refinement for Conditional Image Generation with Diffusion Models

LUA: Latent Upscaling Adapter for Diffusion-Based Image Synthesis

Learning to Balance: Decoupled Siamese Diffusion Transformer for Reference-Based Remote Sensing Image Super-Resolution

Steering Diffusion Models via Class-Contrastive Influence for Few-Shot Classification

Accelerating Diffusion Transformers with Gaussian Process Rectified Feature Cache

DAPS++: Rethinking Diffusion Inverse Problems with Decoupled Posterior Annealing

One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policies

Generative Manifold Distillation: Aligning Restoration Trajectories with the Natural Image Prior

Wavelet-Driven Cross-Domain Consistency for Mixed-Supervised 3D Tumor Segmentation

Thermo-JEPA: Learning a Geometry-Grounded Thermal World Model via Cross-Modal Privileged Masking

Cross-token Guidance Transformer for Weakly Supervised Object Localization

Adaptive Spectrum-Aware Feature Disentangled Network for Small Object Detection

ScanFocus: A Coarse-to-Fine Framework for Spatio-Temporal Video Grounding

OpenPanoD: Aligning Multimodal Prompts and Spherical Representations for Open-Vocabulary Panoramic Detection

Multi-modality Image Fusion under Adverse Weather: Mask-Guided Feature Restoration and Interaction

CoT-PL: Chain-of-Thought Pseudo-Labeling for Open-Vocabulary Object Detection

LGD-Net: Leader-Guided Cross-Modal Dynamics for Hyperspectral and Panchromatic Image Fusion

RT-SDGOD: Real-Time Single-Domain Generalized Object Detection

A Dual-space Patch-driven Complementary Learning Framework for Semi-supervised Multi-organ Segmentation

Selective Synergistic Learning for Video Object-Centric Learning

Segmenting Visuals With Querying Words: Language Anchors For Semi-Supervised Image Segmentation

Disentangling and Reusing Interaction Cues for Zero-Shot HOI Detection

BEVOpen3D: Towards Open-World 3D Object Detection in Bird's-Eye-View

SGP2: Coarse-to-Fine Controllable Multimodal Remote Sensing Image Generation

CloSeR: Unified Relational Distillation from Closed-Set Teachers for Category Discovery

UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation

Degradation-Agnostic Clarity Learning for Unpaired Image Dehazing

HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-training

Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition

ReMoMask: Retrieval-Augmented Masked Motion Generation

Decoding Multimodal Causality: End-to-End Multimodal Mediation Pathways Inference

T-REN: Learning Text-Aligned Region Tokens Improves Dense Vision-Language Alignment and Scalability

VarProtoAD: Variational Prototype-Conditioned Prompting for Zero-Shot Anomaly Detection

What Images Cannot Say: Language-Guided Olfactory Representation Learning

Explicit Semantic–Spatial Alignment for Open-Vocabulary Object Detection

Distribution-Aware Feature Selection for Post-hoc Out-of-Distribution Detection

Incentive Noise and Structural Prior Infusion for Multi-Modal Object Re-Identification

DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognition

FSD-Net: Foundation-Guided Spatiotemporal Distillation for Video Polyp Segmentation

CMDS-AD: Cross-Modal Dual-Stream Decoupling for Few-Shot Anomaly Detection

From Visual Primitives to Semantic Masks: Fine-Grained Visual-Linguistic Alignment for Open-Vocabulary Remote Sensing Image Segmentation

PhysFlowNet: Learning Canonical Latent Manifolds via Spatio-Spectral Physics Priors for Underwater Object Detection

UniStitch: Unifying Semantic and Geometric Features for Image Stitching

DA-F2F: Domain-Adaptive Object Detection with Feature-to-Feature Modulation and Alignment

Intra-Class Consistency Guided Class-Agnostic Event Segmentation

Rethinking IRSTD: Single-Point Supervision Guided Encoder-only Framework is Enough for Infrared Small Target Detection

Towards Unsupervised Multi-modal Semantic Segmentation

XSemanticFlow: Cross Object Semantic Alignment for Zero-shot Manipulation

FD²: A Dedicated Framework for Fine-Grained Dataset Distillation

Progressively Spiral Mamba Fusion for Multimodal Tracking

DINOde: Continuous Vision-Text Alignment for Open-Vocabulary Semantic Segmentation

From Predictions to Embeddings: Dual Knowledge Distillation for Instance-Dependent Partial Label Learning

Safe Generalization: Mitigating Catastrophic Forgetting in Single-Source Multi-Organ Segmentation via Collaborative Causal Learning

DecepGPT: Schema-Driven Deception Detection with Multicultural Datasets and Robust Multimodal Learning

Online Versatile Incremental Learning: Towards Class and Domain-Agnostic Adaptation at Any Time

Multi-scale Object-Aware Gaze Estimation via Geometric Reasoning

CHIMERA: Adaptive Cache Injection and Semantic Anchor Prompting for Zero-shot Image Morphing with Morphing-oriented Metrics

When Specialists Meet Generalists: Segmenter-Coordinated Asymmetric Learning for Label-Deficient Concealed Object Segmentation

Enhancing prompt-image alignment evaluations via cyclic mutual information maximization

Learning Accurate Segmentation Purely from Self-Supervision

InfraNet: Quality-Aware RGB Guidance for Infrared Object Detection

DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection

Hierarchical Style Aggregation for Versatile Chinese Handwriting Generation

Fragmented Text Is Insufficient for Image Representation: Fine-Grained Correspondence in Multimodal Dataset Distillation

RA-SOD: Reliability-Aware RGB-T Salient Object Detection under Modality Degradation

NegAS: Negative Label Guided Attention and Scoring for Out-of-Distribution Object Detection with Vision-Language Models

Recurrent Cross-View Object Geo-Localization

MoMCE: Mixture of Modality and Cue Experts for Multimodal Deception Detection

Prototype-Conditioned Imagination for Compositional Zero-Shot Learning

Open-Vocabulary 3D Object Detection with Co-Distillation Discovery and Dual Guidance Robust Training

When W4A4 Breaks Camouflaged Object Detection: Token-Group Dual-Constraint Activation Quantization

VCP-DCN: Beyond Visual Concealed Property via Depth Collaborative Network for Camouflaged Object Detection

Maximum Spanning Tree Guided Confidence and Sparse Graph for Robust Noisy Label Learning

PriSM: Parsing and Style-Mixed Consistency for Unsupervised Domain Adaptation in Facial Landmark Detection

BIP: Bi-level Information Transfer and Completion Prompting for Visual Recognition with Missing Modalities

Geometric Regularization for Long-Tailed Semi-Supervised Learning via Gaussian Feature Bridges

Preserving Knowledge across Space and Time for Continual Video Deepfake Detection

ModuSeg: Decoupling Object Discovery and Semantic Retrieval for Training-Free Weakly Supervised Segmentation

Amplify, Aggregate, and Adjust: VideoMAE-based Holistic-Subtle Aggregation for Micro-Action Recognition

Local-to-global Cross-modal Coordination for Self-supervised RGB-T Tracking

Boosting Text-Driven Video Segmentation via Geometry-Aware Distillation

Beyond Alignment: A Generative Matching Paradigm via Flow Matching for Zero-Shot Skeleton-Based Action Recognition

Saber: Anchoring Semantics to Scale-Aware Kinetic Salience for Zero-Shot Skeleton Action Recognition

Path-JEPA: Path Signature Based Predictive Learning for Skeleton Action Recognition

OP3DSG: Open-vocabulary Part-aware 3D Scene Graph Generation for Real-world Environments

Mitigate Modality-Asymmetric Forgetting via Stabilizing Visual Representations in CLIP-Based Class-Incremental Learning

Towards Sparsely Annotated Open World Object Detection

MAVFusion: Efficient Infrared and Visible Video Fusion via Motion-Aware Sparse Interaction

Towards Open-World Referring Expression Comprehension: A Benchmark with Training-free Multi-task Consistency Checker

Learning Structured Visual Compositional Representations for Weakly Supervised Referring Expression Comprehension

Modality-Aware Out-of-Distribution Detection for Multi-Modal Action Recognition

Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts

Mask-guided Semantic Alignment: Robust Learning with Noisy Labels via Temporal Attention Stability

Rethinking Cross-Spectral Image Generation via Shared-Specific Representation

Dual-Margin Embedding for Fine-Grained Long-Tailed Plant Taxonomy

FSDC-DETR: A Frequency-Spatial Domain Collaborative DETR for Small-Object Detection

Purify then Guide: Rethinking Domain Generalization for Multimodal Face Anti-Spoofing

SFM: Taming State Space Models for Text-to-Motion via Spatial-Frequency Modeling

MoAKE: Toward Unified All-in-One Action Quality Assessment via Mixture of Action Knowledge Experts

ASTAD: Asymmetric Style Transfer for Synthetic-to-Real Adaptation in Autonomous Driving

Warp-free Cross-view Geo-localization via Feature-space Consensus Mining

GenHOI: Generalized Hand-Object Pose Estimation with Occlusion Awareness

Rethinking Pseudo-Labels: Multi-Granularity Supervision for Domain Adaptive Object Detection

Hierarchical Prompt Injector for Domain Generalization Segmentation

Group3D: MLLM-Guided Semantic Grouping for Open-Vocabulary 3D Object Detection

Context-Aware Joint Alignment for Cross-Scene Hyperspectral Image Classification

QST-SAM: Leveraging Cross-modal Instructions for Few-shot Referring Video Object Segmentation

ReliefSAM: A Geometry-Augmented Multi-Prior Adapter for Bas-Relief Segmentation

Beyond Isolated Objects: Relationship-aware Open Vocabulary Scene Understanding via 3D Scene Graph Analysis

GeoEdit: Geometry-Aware Object Editing via Dual-Branch Denoising

QASA: Quality-Guided K-Adaptive Slot Attention for Unsupervised Object-Centric Learning

RAG-3DSG: Enhancing 3D Scene Graphs with Re-Shot Guided Retrieval-Augmented Generation

Progressive Representation Learning for Multimodal Sentiment Analysis with Incomplete Modalities

AquaStereo: Enabling Underwater Stereo Matching via Depth-Conditioned Diffusion and Geometry Self-Distillation

Learning to Compose: Revisiting Proxy Task Design for Zero-Shot Composed Image Retrieval

HVGCD:Rethinking Generalized Category Discovery through Hypothesis–Verification

Diffusion Model as a Generalized Segmentation Learner

MOCHA: Multi-modal Objects-aware Cross-arcHitecture Alignment

SWSL: Semantic-aware Weakly Supervised Learning for 3D Motion Generation using 2D Motion Data

Liquid Fusion of Heterogeneous Representations Towards General Salient Object Detection

DGSeg: Dynamic Gating of Semantic-Spatial Guided Predictions for Reasoning Segmentation

Beyond Categorical Matching: Intra-Class Graded Relevance Estimation for Cross-Modal 3D Retrieval

SOVTrack: Open-Vocabulary Multi-Object Tracking with Self-Supervised Pseudo Labeling and Feature Distillation

SARA: Structure-Aware Riemannian-Guided Alignment for Drone Image-Text Retrieval

What is the Right Embedding Space for Contrastive Learning in Referring Expression Counting?

Iterative Refinement of Semantic and Spatial Representations for Open-Vocabulary Camouflaged Object Segmentation

HER-Count: Learning Hyper-Exemplar Representation for Generalized Zero-Shot Object Counting

FST-SAM3: Taming SAM~3 with Frequency-Spatio-Temporal Refinement for Video Polyp Segmentation

Rethinking Prototype-based Similarity Learning for Few-Shot Object Detection

Unleashing the Power of Large-Scale ViT in Zero-Shot SBIR: A Strong Baseline with Multi-Layer Feature Aggregation

InSeg: Interactive Refinement via Intent Propagation for Point Cloud Semantic Segmentation

Revisiting Deepfake Detection: BCNet for Robust Generalization Beyond Semantic Dependence

REAL-OW: Rehearsal-free Open World Object Detection with Low-Rank Adaptation and Dual-Stage Objectness Modeling

Virtual Category-Guided Continual Generalized Category Discovery

CaPCL: Caption-Preserved Continual Learning for Text-to-Image Retrieval

Label-Free Text Prototype Adaptation for Open Vocabulary Segmentation

SFKD: Spatial–Frequency Joint-Aware Heterogeneous Knowledge Distillation via Multi-Level Wavelet Spectral Interaction

Toward Robust In-Context Segmentation via Concept Guidance

CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation

HVA-Fusion:Hierarchical Velocity-Aware 4D Radar-LiDAR Fusion for Robust 3D Object Detection

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

CascadeProto: Cascaded Cross-Modal Prototype Purification via Entropy-Aware Learning for Few-Shot 3D Point Cloud Segmentation

Proposal Score Realignment Guided by Semantic Completeness for Weakly Supervised Temporal Action Localization

IP-SAM: Rethinking Prompt-Conditioned Segmentation for Prompt-Absent Deployment

DETR is Secretly a Multispectral Detector: Zero-Parameter Adaptation via Semantic Alignment

Debiased Textual Prompt Tuning for Enhancing Unknown Class Discovery

Context-Interactive Reasoning for Group Activity Detection

NegROI: Click-Centric Uncertainty-Guided Refinement with Scene-Conditioned Negative Prompts for Robust Interactive 3D Segmentation

DE2TR: Dual Evidence Detection Transformer for Video Temporal Grounding

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

P²Fusion: Prompt-based Progressive Infrared-Visible Image Fusion via Dual-Prior Distillation

DSeq-JEPA: Discriminative Sequential Joint-Embedding Predictive Architecture

Training-free Discriminative Patch Mining for Robust Few-Shot Recognition with CLIP

PASR: Pattern-Aware Scene-Conditioned Reasoning for Camouflaged Object Detection

μFlow: Leveraging Average Images for Improving Generalisation of Deepfake Faces Detectors

ORACLE-3D: Open-world Region-aligned Cross-modal Learning for Label-efficient 3D Scene Understanding

CURE: Contextual Debiasing and Unbiased Refinement for Training-Free Open-Vocabulary Semantic 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

Training-free Cross-domain Few-shot Segmentation via Robust Semantic Representation and Matching

Hierarchical Spatial and Channel Aggregation for Cross-domain Few-shot Segmentation

ReynoldsFlow: Physics-Inspired Spatiotemporal Flow Representation for Video Understanding

CRISP: Calibration-Aware Visual State Space Duality for Remote Sensing Image Segmentation

SPLIT: Training-Free AI-Generated and Partially Edited Video Detection via Spatial Patch‑Level Incoherence and Temporal Roughness

Free-Lunch Augmentation by Revisiting Diffusion-Based Data Generation for Cross-Domain Few-Shot Object Detection

Breaking the Model Forgetting Cycle in Long-Incremental 3D Object Detection

TerrainGraphNet: Terrain-Constrained Graph Reasoning for Landslide Segmentation

Fourier Self-Supervision for Fine-Grained Generalized Category Discovery

GhostPoint: Self-Supervised Representation Learning by Hallucinating Occluded LiDAR Structure

Calibrate Before Adapt: Training-Free Pseudo-Label Calibration for Semi-Supervised Cross-Domain Few-Shot Detection

Learning Structurally Consistent Representations for Multi-View Radar Semantic Segmentation

Capturing Spectral and Spatial Patterns for Federated Remote Sensing Segmentation

FAIR: Feature-Augmented Implicit Regularization for AI-generated Fake Image Detection

Noise-Robust Facial Expression Recognition via Mamba-driven Neighbor Weight Refinement

Learning to Attract and Repel: Dual Quality Margin Learning for Face Recognition (DQM-Face)

General Incomplete Multimodal Learning via Dynamic Quality Perception

From Local Geometry to Global Pseudo-Labeling for Robust Positive–Unlabeled Learning under Covariate Shift

SCDL: Synergistic Confidence-Dispersion Learning for Semi-Supervised Video Polyp Segmentation

OPAL: Orthonormal Prototype Alignment Learning for Interpretable Image Classification

Defect-aware Hybrid Prompt Optimization for Zero-Shot Multi-type Anomaly Detection and Segmentation

Bayesian Uncertainty Attribution-Guided Fine-Tuning for Open-Set Action Recognition

Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs

Can Vision Models Truly Forget? Mirage: Representation-Level Certification of Visual Unlearning

HEM: a margin-based loss for visual categorisation tasks

Beyond Disjoint Tasks: Towards More Natural Continual Learning for Vision-Language Models

The Label Imitation Game: Turing Test Network for Zero-Shot Pseudo-Label Pruning

FaceMoE: Mixture of Experts for Low-Resolution Face Recognition

An Inverse-Adversarial and Difficulty-Adaptive Robust Vision-Language Model

Dual-Generalization-aware Minimization for Continual Fine-Tuning of Vision-Language Models

Orthogonal Knowledge Refreshing for Domain-Incremental Object Detection

Graph Coloring for Multi-Task Learning

S2-FracMix: Self-Saliency Fractal Mixup

SAM+D: Parameter-Efficient Dimensional Lifting of SAM-Family Models via Depth-Routed LoRA and Depth Shifting

FedNASP: Federated Vision-Language Navigation with Adaptive Step-wise Personalization

OrthoTailor: Geometric Orthogonalization for Conflict-Free Unified Fashion Generation

Shared LoRA Subspaces for almost Strict Continual Learning

Improving Adversarial Robustness via Activation Amplification and Attenuation

Capacity Overflow: A Blind Spot for Backdoor Attacks in Vision MoE

MixCompress: Mixture of Experts for Variable Rate Learned Image Compression

Path-level Hindsight Instructions for Semantic Exploration in Vision-Language Navigation

SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing

Learning to Recover Task Experts from a Multi-Task Merged Model

Tri-Efficient Transfer Learning for Point Cloud Videos

Focusing on What Matters: Saliency-Harnessing Accurate Routing for Diffusion MoE

Residual-Guided Expert Specialization for Incomplete Multimodal Learning

On the Vulnerability of Parameter-Level Defenses to Model Merging

Unified Multi-Layer Subspace Modeling for Cross-Domain OOD Detection

GCMRD: Global Consistency Multi-teacher Robustness Distillation

Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation

DriveFine: Refining-Augmented Masked Diffusion VLA for Accurate and Robust Driving

Prefill-Time Interventions against Adversarial Attacks on Large Vision-Language Models

Benchmarking Federated Learning & Knowledge Distillation for Point Cloud Classification

VLOD-TTA: Test-Time Adaptation of Vision-Language Object Detectors

CL-Anomaly: Layer-Adaptive Mixture-of-Experts with Multimodal Large Language Model for Continual Learning in Anomaly Detection

Towards Purified Multi-Label Test-Time Adaptation of Vision-Language Models

VLMSysTrojan: Stealthy System-Aware Backdoor Attacks Against Vision-Language Models

Holistic Optimal Label Selection for Robust Prompt Learning under Partial Labels

Rethinking Adversary in Semantic Segmentation: An Out-of-Distribution Perspective

RT-DETRv4: Painlessly Furthering Real-Time Object Detection with Vision Foundation Models

Dive into the implicit biases of low-rank vision-language alignment

TooBad: Backdoor Diffusion Models with Ultra-Low Poison Rate and Imperceptible Trigger

Neural Collapse-Inspired Multi-Label Federated Learning under Label-Distribution Skew

MagicPrompt: Ultra-Lightweight Prompt Tuning for Video Generation

CollectionLoRA: Collecting 50 Effects in 1 LoRA for Deployment

VisNec: Measuring and Leveraging Visual Necessity for Multimodal Instruction Tuning

Learning 1-Bit LiDAR-based Localization with Auxiliary Objective

Task-Agnostic Incremental Vision-Language Object Detection via Prompt Augmentation and Distribution-Aware Fusion

Point Ladder Tuning: Parameter-Efficient Hierarchical Adaptation for 3D Point Cloud Understanding

SLER-IR: Spherical Layer-wise Expert Routing for All-in-One Image Restoration

FedMental: Topology-Aware Federated Prototype Learning for Polymorphic Multimodal Psychiatry

AnchorGUI: Asymmetric Memory for Dual-Scale Learning in GUI Navigation

Prevention over Correction: Learning Aligned Representations in One-shot Federated Learning

TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction

MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation

MED-LCDS: Multi-Expert-Domain CLIP Classification via Logit Calibration

Training-Free Task Classification for Multi-Task Model Merging

Rank-Aware Hyperbolic Alignment for Vision–Language Dataset Distillation

Attention Misses Visual Risk: Risk-Adaptive Steering for Multimodal Safety Alignment

Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging

SegPAR: Class-Centric Decision-Based Sparse Attack for Semantic Segmentation

SUM: Unified Geometric Surgery on Spatio-Temporal Adaptation Vectors for Federated Class Incremental Learning

FeDepth: Federated Learning for Depth Estimation under Robot Heterogeneity

DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM Agents

Distill on a Diet: Efficient Knowledge Distillation via Learnable Data Pruning

Why Feature Magnitude Deceives OOD Detectors: An Angular Separation Perspective

SIMPLER: Efficient Foundation Model Adaptation via Similarity-Guided Layer Pruning for Earth Observation

Fisher-Routed Mixture of Experts for Federated Class-Incremental Learning

Comprehensive Robustness Analysis of LiDAR-based 3D Object Detection in Autonomous Driving

SCoT: Similarity-guided Conflict-aware Task Consolidation for Continual VQA

Zero-Shot Quantization for Object Detectors using Off-the-Shelf Generative Models

DA-MergeLoRA: Hypernetwork-Based LoRA Merging for Few-Shot Test-Time Domain Adaptation

Importance-Aware Low-Rank Distillation of Diffusion Transformers

MixTTA: Low-Rank Cross-Channel Mixing for Reliable Test-Time Adaptation

BATQuant: Outlier-Resilient MXFP4 Quantization via Learnable Block-wise Optimization

Molecular Identifier Visual Prompting and Verifiable Reinforcement Learning for Chemical Reaction Diagram Parsing

Prototype Normalization: Optimizing Prototype Separation for Heterogeneous Federated Learning

ReTarget: Representation Transformation via Adversarial Regularization for Geometric Misalignment

Flash-DD: An Ultra Parameter-Efficient Approach to Dataset Distillation

Accurate Zero-shot Quantization via Hierarchical Teacher-Assistant Distillation

DroneFINE: Domain-Aware Parameter-Efficient Fine-Tuning of Vision-Language Detectors for Drone Images

MUSE: Unlocking Timestep as Native Task Steering for One-Step Dense Prediction

RUTaL: Residual Upcycling with Task Ladder for Efficient Multi-Task Learning

Learning from Reliable Negatives: Confidence-Anchored Test-Time Adaptation for GUI Grounding

Neutralizing Token Aggregation via Information Augmentation for Efficient Test-Time Adaptation

SPDA: Efficient Online Test-Time Adaptation for Promptable Medical Segmentation

Unified Prediction and Planning via Conflict-Aware Disjoint Parameter Training

One Trap to Block Them All: Defending Encoder Stealing via Isotropic Uniformity

Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptation

TextDS: Parameter-Efficient Representation Alignment for Scene Text Detection under Distribution Shifts

Interference-Aware Continual Vision–Language Learning via Instance-Level Expert Routing

Diffusion to Obfuscation: Time-Adaptive Synthesized Generation Against Gradient Leakage Attacks in Federated Learning

Identifiable Gated Residual Personalization for Federated Parameter-Efficient Fine-Tuning

TSEmbed: Unlocking Task Scaling in Universal Multimodal Embeddings

DiscoVL: Unveiling Disentangled Cross-Modal Representation Learning via Orthogonal Adversarial Regularization for Vision-Language Models

Curvature-Guided Mixing for MLLM Adaptation

PACO: Stabilizing Vision Embeddings along Local Paths for Robust Vision-Language Models

SlowBA: An efficiency backdoor attack towards VLM-based GUI agents

Aggregating Cross-Domain Knowledge via Learnable Tokens for Multi-Teacher Distillation

TIR-Agent: Training an Explorative and Efficient Agent for Image Restoration

Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts

CaRe: Critical Parameter Rectification for Efficient Visual Modeling

R2M: Real-Aware Residual Model Merging for Robust and Generalizable Deepfake Detection

BioMedVR: Confusion-Aware Mixture-of-Prompt Experts for Biomedical Visual Reprogramming

Robust Trajectory Distillation: Hybrid Reweighting Meets Teacher-Inspired Targets

ViQ: Text-Aligned Visual Quantized Representations at Any Resolution

SiGMA: Sign-Guided Merging and Adaptation framework for Multimodal Continual Instruction Tuning

COVERT: Privacy-Preserving Covariant Obfuscation for VLMaaS via Exact Reparameterization and Tailored Tuning

Symbiotic-MoE: Unlocking the Synergy between Generation and Understanding

VD-LoRA: Adaptive Reuse of Low-Rank Directions for Continual Learning

Going Deep: Deep Visual Prompting with LoTeP

Probe, Anchor, and Amend: Active Test-Time Adaptation of Vision-Language Models

Robust onion: Peeling Open Vocab Object Detectors Under Noise

Foundation Model Selection for Remote Sensing via a Constraint-Aware Agent

Multi-Hypothesis Test-Time Adaptation to Mitigate Underspecification

COLA: Continual Orthogonal Low-Rank Adaptation for Class-Incremental Learning

Stealthy Multi-task Adversarial Attacks

SAMPLe: A Sharpness Aware Minimization based Optimizer for Prompt Learning in Vision-Language Models

GeMoE: Gating Entropy is All You Need for Uncertainty-aware Adaptive Routing in MoE-based Large Vision-Language Models

LDC-MTL: Balancing Multi-Task Learning through Scalable Loss Discrepancy Control

Locality-Aware Continual Unlearning for Diffusion Models

Detecting Backdoors in Object Detection via Pre-NMS Prediction Distribution Shift

Exploiting Local Flatness for Efficient Out-of-Distribution Detection

FedDO: Dynamic Client Optimization for Adaptive Federated Learning

Indelible Backdoors: On the Limits of Post-Training Defenses

Attention-Logit Steering to Compositional Generalization for Continual VQA

Preventing Expert Collapse in MoE-dVLMs via Modality-Wise Norm Alignment

H-SFP: Hierarchical Federated Learning with Decoupled Split-Model Prototyping

Condensing Large-Scale Datasets Directly with Minimal Information Loss

Isotropic Embedding Perturbations for Robust Vision Language Encoders

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

Token-level Response-visual Attention Guidance for Multimodal LLMs Knowledge Distillation

Prune Once: Retraining-Free Task-Agnostic Pruning for Vision-Language Models

KATANA: Knowledge-Aligned Topology-Aware Neural Agents for RL-Driven Vision-Language Model Compression

Breaking Rigidity in Adversarial Patch Attacks

LANCE: Low Rank Activation Compression for Efficient On-Device Continual Learning

Low-Rank Ternary Adaptation for Fine-Tuning Transformers

Data-Free Client Contribution Estimation via Logit Maximization for Federated Learning

(ends 12:30 PM)

noon

Lunch:

Lunch

(ends 1:30 PM)

1:30 p.m.

Embodied AI, Robotics & Autonomous Driving [1:30-3:00]

Spotlights 1:30-2:40

[1:30] SPEAR: A Simulator for Photorealistic Embodied AI Research

[1:35] Predicting Consequences and Reinforcing Navigation Policies with Latent World Models

[1:40] Unordered Landmark Visual Navigation

[1:45] R3DP: Real-Time 3D-Aware Policy for Embodied Manipulation

[1:50] Humanoid Whole-Body Manipulation via Active Spatial Brain and Generalizable Action Cerebellum

[1:55] Physically Grounded 3D Generative Reconstruction under Hand Occlusion using Proprioception and Multi-Contact Touch

[2:00] Cooking beyond Frames: A Stereo Event Camera Dataset in the Kitchen

[2:05] TriO: Tri-Modal Unsupervised Occupancy World Model for Anything Perception

[2:10] VOCA: Visual Odometry with Codec Awareness

[2:15] PriorEye: Geospatial Visual Priors for End-to-End Autonomous Driving

[2:20] Generative Lane Topology Reasoning via Autoregressive Model with Geometry Prior

[2:25] MV2GF: Multi-view Pedestrian Detection with a Visual Geometric Foundation Model

[2:30] CooperScene: Multi-Modal Cooperative Autonomy Benchmark with C-V2X Communication Characterization

[2:35] VIPS: Vehicle-Infrastructure Cooperative Planning Benchmark via Pseudo-Simulation

(ends 3:00 PM)

Multimodal, Video & Document Understanding [1:30-3:00]

Spotlights 1:30-2:45

[1:30] DoCoG: Mask-based Multi-Type Grounded Chain-of-Thought for Document QA

[1:35] Invoice Haystack: Benchmarking Document Retrieval and Visual Question Answering Under Strong Visual Homogeneity

[1:40] SyntheticDoc: A Large Synthetic Dataset for Document Unwarping and Illumination Correction

[1:45] PanoRec: Spatially-Structured Sequence Modeling for Multi-Granularity Panoramic Retrieval

[1:50] NarrativeTrack: Evaluating Entity-Centric Reasoning for Narrative Understanding

[1:55] Incentivizing Vision Language Models to Search for Long Video Question Answering

[2:00] Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing

[2:05] HumanOmni-Speaker: Identifying Who said What and When

[2:10] UniTac: A Unified Multimodal Model for Cross-Sensor Tactile Understanding and Generation

[2:15] See & Sniff: Learning Visuo-Olfactory Representations

[2:20] Bridging Vision and Language Concepts through Optimal Transport Semantic Flow

[2:25] CoverPrune: Coverage-Driven Token Pruning for 3D VLMs via Optimal Transport

[2:30] When Sinks Help or Hurt: Unified Framework for Attention Sink in MLLMs

[2:35] How to Teach Large Multimodal Models New Skills

[2:40] Event-Driven Video Generation

(ends 3:00 PM)

3D Reconstruction, Registration and Scene Modeling [1:30-3:00]

Orals 1:30-3:00

[1:30] Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching

[1:45] Geometric Context Transformer for Streaming 3D Reconstruction

[2:00] LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows

[2:15] GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation

[2:30] Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding

[2:45] Seeing Through the Weights: Privacy Leakage in Scene Coordinate Regression

(ends 3:00 PM)

3 p.m.

Poster Session 6 [3:00-5:00]

Posters 3:00-5:00

AnyGround3D: Towards Grounding Any 3D Object in the Wild via 2D-to-3D Lifting

OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder

LaMP: Learning Vision-Language-Action Policies with 3D Scene Flow as Latent Motion Prior

GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generation

Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding

LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

UBone3D: Physics-Rectified Conditional Flow Matching for Anatomical 3D Shape Completion from Ultrasound

Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes

Taming LLMs for Codematic Indoor Scene Generation

TORA: Topological Representation Alignment for 3D Shape Assembly

LiFlow: Flow Matching for 3D LiDAR Scene Completion

Event-LiDAR: 3D Eventification for Efficient Point Cloud Processing

CanoVerse: 3D Object Scalable Canonicalization and Dataset for Generation and Pose

OCA: ODE-Driven Cross-Attention for Image-to-Point-Cloud Registration

SuperFlex: Deformable Superquadrics for Point Cloud Decomposition

FDR-Occ: Factorized Dense Routing for Full-Spectrum 3D Occupancy Prediction

MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos

Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs

GraphCPD: Coherent Point Drift for Point Cloud Registration via Graph Signal Processing

LangLoc: “Tell Me What You See”

Unsupervised Point Cloud Registration via Training-Time Semantic Guidance

MSVS-VAE: Multi-Scale Anchored VecSet for High-Fidelity 3D Reconstruction

Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding

DepWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priors

PGCR: Pose–Geometry Coupled Reasoning for Image-to-Point Cloud Registration

Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels

CasaMaestro: Multi-View Panoramas for House-Scale 3D Reconstruction

Geometric Context Transformer for Streaming 3D Reconstruction

SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion

RGB-Pointmap Pretraining for Unified 3D Scene Understanding

SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers

Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformer

YouTube-Occ: Learning Indoor 3D Semantic Occupancy Prediction from YouTube Videos

Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention

Ex-Sim(3)-Reg: 2D-3D Correspondence Pruning via Extended Sim(3) Registration

Attention-DP3: Spatially Object-aware 3D Diffusion Policy via Geometry-aligned Attentional Conditioning

Hierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spaces

Vulnerability of Privacy-Preserving Visual Localization against Diffusion-based Attacks

Pose Anything Anywhere: Model-free Object Poses from Arbitrary References

HHA: Hierarchical Hyperbolic Constraints for Imperceptible Point Cloud Attacks

SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation

LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows

Fixed Reality, Diffused Possibility: Disentangling Stochastic and Deterministic Latent for Cluttered Grasping

TabletopGen: Tabletop Scene Generation and Interactive Simulation for Robotic Manipulation

TouchAnything: Diffusion-Guided 3D Reconstruction from Sparse Robot Touches

GridFlow: Structured Latent Flow for Seamless City-Scale 3D Point Cloud Generation

SNOW: Spatio-Temporal Scene Understanding with World Knowledge for Open-World Embodied Reasoning

E-M3RF: An Equivariant Multimodal 3D Re-assembly Framework

UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction

Seen2Scene: Completing Realistic 3D Scenes with Visibility-Guided Flow

WorldFlow3D: Flowing Through 3D Distributions for Unbounded World Generation

SceneOrchestra: Efficient Agentic 3D Scene Synthesis via Full Tool-Call Trajectory Generation

RayMap3R: Inference-Time RayMap for Dynamic 3D Reconstruction

RegVGGT: Sustainable Visual Geometry Grounding for Streaming via Regulated Memory

Scale3D: Autoregressive Modeling for Large Outdoor Scene Generation

Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction

FILT3R: Latent State Adaptive Kalman Filter for Streaming 3D Reconstruction

GeoMix: Descriptor-Free Visual Localization via Global Context and Multi-Detector Training

Scene Generation at Absolute Scale: Utilizing Semantic and Geometric Guidance From Text for Accurate and Interpretable 3D Indoor Scene Generation

Mitigating Positional Leakage in 3D Masked Autoencoders for Robust Representation Learning

White Aggregation and Restoration for Few-shot 3D Point Cloud Semantic Segmentation

NaLA: A 3D Native LLM Layout Agent for High-quality 3D Scene Generation

GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation

On Geometric Understanding and Learned Priors in Feed-forward 3D Reconstruction Models

TASE: Truncation-Aware Semantic Embeddings for 3D Scene Understanding and Editing

Pano3D: Unified 3D Reconstruction and Panoptic Segmentation

Revisiting Scene Graph Generation from the Perspective of Detector-Conditioned Reachability

UniQueR: Unified Query-based Feedforward 3D Reconstruction

SEM-ROVER: Semantic Voxel-Guided Diffusion for Large-Scale Driving Scene Generation

LESV:Language Embedded Sparse Voxel Fusion for Open-Vocabulary 3D Scene Understanding

SHReg: Strictly Rotation-Equivariant Point Cloud Registration via Spherical Harmonics

Think While You Map: Asynchronous Vision-Language Agents for Incremental 3D Scene Graphs

Map2World: Segment Map Conditioned Text to 3D World Generation

Towards Practical Lossless Neural Compression for LiDAR Point Clouds

BitRIC: Efficient Neural Compression of LiDAR Range Images via Hierarchical Bitplanes

Uncertainty-Driven Gaussian Sphere Propagation for 3D Semantic Segmentation

Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding

PUF: Plug-and-Play Uncertainty-Aware Fusion for Online 3D Scene Graph Generation

Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training

Zero-Shot Novel Depth Synthesis Using Foundation Models Scene Representations

SLAM-Former: Putting SLAM into One Transformer

Pixel-wise Geo-registration of Drone and Satellite Images

G2P: Gaussian-to-Point Attribute Alignment for Boundary-Aware 3D Segmentation

MessyKitchens: Contact-rich object-level 3D scene reconstruction

MARché: Fast Masked Autoregressive Image Generation with Cache-Aware Attention

Occlusion-Resilient Category-Agnostic Pose Estimation with Conditional Flow Matching

PrintAnything: Learning Geometric Plan Map for 3D Printing G-code Generation from Unoriented Point Clouds

Abstract the Layout, Focus the Detail: A Dual-Granularity Representation Framework for Zero-Shot 3D Visual Grounding

SEAR: Simple and Efficient Adaptation of Visual Geometric Transformers for RGB+Thermal 3D Reconstruction

Sparse-Aware Vector Quantization for Bandwidth-Efficient Collaborative 3D Semantic Occupancy Prediction

Point Diffusion Mamba: Unified Diffusion-State-Space Modeling for Single-View 3D Reconstruction under Data Scarcity

FUSE: A Flow-based Mapping Between Shapes

Horizon3D: Sparse Radar-Camera Fusion for Long-Range 3D Perception in Autonomous Driving

Bootstrapping Articulated 3D Reconstruction from 2D Image Collections

Mind2Cloud: EEG-to-Point Cloud Generation with Two-Granularity Diffusion Decoding

DRS-VPT: Directly Re-localizing in Scenes using a Vision and Point Transformer

DisentangledTMR: Privacy-Preserving Skeleton Motion Retargeting via Factorized Transformers

Seeing Through the Weights: Privacy Leakage in Scene Coordinate Regression

SegFly: A 2D-3D-2D Paradigm for Aerial RGB-Thermal Semantic Segmentation at Scale

Transferability Between Understanding and Generation in Unified Multimodal Models

Unfold The World: Factorize 4D Properties in Reinforcing Spatial Understanding

What You Ask is What You Ground: Bridging Question Intent to Temporal Evidence for Grounded VideoQA

Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding

A First Exploration of Neuromorphic OT-CFM for Multi-Speaker VSR

SyncLoop: A Multimodal Dual-Loop Framework for Self-Improving Mathematical Reasoning

ReGRPO: Reflection-Augmented Policy Optimization for Tool-Using Agents

Towards Interactive Global Geolocation Assistant

Vero: Open Reinforcement Learning Recipes for Visual Reasoning

SWIFT: Spatial-Window Integrated Frequency-aware Token Pruning for Efficient MLLMs on Edge Devices

PhysAlign: Learning Physical Priors for Dynamical Event-Driven Video Generation via Representation Alignment

MarineEVT: Advancing Event-Centric Marine Video Understanding via Visual Tool Reasoning

DoCoG: Mask-based Multi-Type Grounded Chain-of-Thought for Document QA

SpaMEM: Benchmarking Dynamic Spatial Reasoning via Perception–Memory Integration in Embodied Environments

LASER: A Corrective Lens for LVLMs via Visual Attention Preservation and Sink Suppression

FlowCIR: Semantic Transport via Flow Matching for Zero-Shot Composed Image Retrieval

OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning

Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagrams

Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics

Invoice Haystack: Benchmarking Document Retrieval and Visual Question Answering Under Strong Visual Homogeneity

MG2-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation

AMCI: Unlock the Potential of Large Multimodal Models for Fine-grained Open-world Classification via Adaptive Memory Context Injection

Multiple Images Distract Large Multimodal Models via Attention Fragmentation

OmniSch: A Multimodal PCB Schematic Benchmark For Structured Diagram Visual Reasoning

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models

Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings

ATP-Bench: Towards the Agentic Tool Planning for MLLM Interleaved Generation

RAGrasp: A Retrieval-Augmented Framework with Diversity-Aware Modeling for Dexterous Grasp Generation

Combating Textual Noise and Redundancy: Entropy-Aware Dense Visual Token Pruning

Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning

Spectral Evolution-Guided Token Pruning in Large Multimodal Models

Dense Video Understanding with Inter-tokenization Acceleration

HERO: Enhancing Multimodal Faithfulness via Dynamic Entropy-Aware Reinforcement Learning

SyntheticDoc: A Large Synthetic Dataset for Document Unwarping and Illumination Correction

Video-Text Alignment Model for Sign Language Translation

Evidence-Backed Video Question Answering

From Hallucination to Grounding: Diagnosing Visual Spatial Intelligence via CRISP

Enhancing Interpretability in CLIP with Optimal Transport-based Submodular Optimization for Ophthalmic Imaging

Learning Active Perception for Pixel-Space Reasoning via Visual-Intent Stratified GRPO

Semantic Generative Tuning for Unified Multimodal Models

MultiHaystack: Benchmarking Multimodal Retrieval and Reasoning over 40K Images, Videos, and Documents

Counting Trees from Satellite Imagery with Noisy Supervision

Towards Spatial Supersensing in the Wild

ForeSea: AI Forensic Search with Multi-modal Queries for Video Surveillance

Toward Interpretable Analysis of Whole-slide Pathology Images via Large Language Model-based Agentic Reasoning

ViTexQA: A Multi-Frame Temporal Perception Dataset for Video Text Question Answering

GeoSolver: Scaling Test-Time Reasoning in Remote Sensing with Fine-Grained Process Supervision

PanoRec: Spatially-Structured Sequence Modeling for Multi-Granularity Panoramic Retrieval

Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision

HippoCamp: Benchmarking Contextual Agents on Personal Computers

CoCo-IR: Conversational Composed Image Retrieval

LiveK12Bench: Have Large Multimodal Models Truly Conquered High School-level Examinations?

Starve to Perceive: Taming Lazy Perception in VLMs with Constrained Visual Bandwidth

GroundSet: A Cadastral-Grounded Dataset for Spatial Understanding with Vector Data

Staying VIGILant: Mitigating Visual Laziness in MLLMs via Information-Theoretic Alignment

Co-Steer: Cross-Modal Collaborative Steering for Jailbreaking MLLMs

360° Image Perception with MLLMs: A Comprehensive Benchmark and a Training-Free Method

GradingBench: Evaluating End-to-End Compositional Reasoning of MLLMs for Automated Exam Grading

AnchorPrune: Relevance-Anchored Contextual Expansion for Visual Token Pruning

AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution

VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs

NarrativeTrack: Evaluating Entity-Centric Reasoning for Narrative Understanding

EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models

When Thinking Hurts: Mitigating Visual Forgetting in Video Reasoning via Frame Repetition

Ground3D-LMM: Fine-Grained 3D Point Grounding and Spatial Reasoning with LMM

Parallel Vision Token Scheduling for Fast and Accurate Multimodal LMMs Inference

MMAgent-R2: Learning to Rerank and Reject for Agentic mRAG

Knowledge-Centric Agents for Workflow Generation in ComfyUI

Incentivizing Vision Language Models to Search for Long Video Question Answering

TIR-Bench: A Comprehensive Benchmark for Agentic Thinking-with-Images Reasoning

Learning Sample-wise Rank-Aware Interpolation Weights for Composed Visual Data Retrieval

Beyond Description: Cognitively Benchmarking Fine-Grained Action for Embodied Agents

SafeGuard: A Multi-Agent Perception-Reasoning Framework for Social-Risk AI-Generated Video Detection

IQA-T1: Tool-based Visual Evidence Reasoning for Image Quality Assessment

OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents

Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation

Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding

ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning

Mixture of Specialized Vision Experts: Unlocking Complementary Visual Insights for Faithful MLLM Reasoning

Paying More Attention to Visual Tokens in Self-Evolving Large Multimodal Models

Experts-Guided Unbalanced Optimal Transport for ISP Learning from Unpaired and/or Paired Data

AdaThinking-E: One-Token Entropy Regulation for Adaptive Thinking

Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing

Constructing and Interpreting Digital Twin Representations for Visual Reasoning via Large Language Models and Reinforcement Learning

StrucTab: A Structured Optimization Framework for Table Parsing

MindBlock: Probing Spatial Assembly and Structure in Unified Multimodal Models

VERDICT: Training-Free Step-Wise Verification of Multimodal Reasoning via Disagreement-Aware Consensus

EGVLR: Evidence-Grounded Vision–Language Reinforcement for Anomaly Reasoning

Visual Spatial Tuning

HumanOmni-Speaker: Identifying Who said What and When

BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoning

Unbalanced Optimal Transport for Efficient Visual Document Retrieval

Together, Then Apart: Balancing Alignment and Distinctiveness for Multimodal Survival Analysis

Looking Back and Forth: Cross-Image Attention Calibration and Attentive Preference Learning for Multi-Image Hallucination Mitigation

Enhancing Alignment for Unified Multimodal Models via Semantically-Grounded Supervision

DocLayout-VL: A Foundational Model for Hierarchical, Open-set, and Promptable Document Layout Segmentation

FlashVLM: Text-Guided Visual Token Selection for Large Multimodal Models

MotionChain: Fine-Grained Video Motion Understanding via Structured Decomposition

ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance

VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning

LightSTAR: Efficient Visual Document Retrieval via Lightweight Selection with Vision-Adaptive Refinement

Generalize LMMs to Versatile Visual Modalities via Fabricated Modality Synthesis

ViewFusion: Structured Spatial Thinking Chains for Multi-View Reasoning

UniTac: A Unified Multimodal Model for Cross-Sensor Tactile Understanding and Generation

MotionAtlas: A High-Quality Dataset and Benchmark for Dense Motion Captioning

Beyond Final Answers: CRYSTAL Benchmark for Transparent Multimodal Reasoning Evaluation

Improving Reasoning in Vision-Language Models via Perception Verified Self-Training

VisCritic: Visual State Comparison as Process Reward for GUI Agents

Spotlight: Identifying and Localizing Video Generation Errors Using VLMs

SVGEval: A Vision-Grounded Framework for Perceptual-Quality Benchmarking and Evaluation in Text-to-SVG Generation

Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction

ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs

EatVid-Bench: A Multimodal Fine-Grained Eating Behavior Video Dataset

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs

Multi-label Instance-level Generalised Visual Grounding in Agriculture

SEERBench: A Spatial Ego-Exo Reasoning Benchmark for MLLMs with a Simple Yet Effective Baseline

CRAG-MM-Diagnostics: Enabling Stage-Wise Analysis of Knowledge-Intensive VQA

See & Sniff: Learning Visuo-Olfactory Representations

Memory Tree Guided Key Frame Querying for Efficient 3D Question Answering

Personalizing MLLMs via Reinforced Multimodal Reference Game

Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection

Global-Local Dual Perception for MLLMs in High-Resolution Text-Rich Image Translation

P-MTP: Efficient Document Parsing via Multi-Token Prediction with Progressive Depth Scaling

HSD: Training-Free Acceleration for Document Parsing Vision-Language Models with Hierarchical Speculative Decoding

VLZip: Unified Visual and Textual Compression for Interleaved Long-Context Modeling

SAFE-EQA: Semantic-Aware Efficient Exploration for Embodied Question Answering

CMDR: Contextual Multimodal Document Retrieval

UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameters

RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios

RegRet: Enhancing Region-Level Retrieval in Large Multimodal Models

HighlightBench: Benchmarking and Diagnosing Markup-Driven Table Reasoning in Scientific Documents

Bridging Vision and Language Concepts through Optimal Transport Semantic Flow

The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models

COMPASS: Grounding Composition-Intent Guidance in Unified Multimodal Models

From Illusion to Intention: Visual Rationale Learning for Reliable Evidence Acquisition

Falcon: Functional Assembly and Language for Compositional Reasoning in X-ray

On the Faithfulness of Post-Hoc Concept Bottleneck Models

InstrAct: Towards Action-Centric Understanding in Instructional Videos

CoverPrune: Coverage-Driven Token Pruning for 3D VLMs via Optimal Transport

NAPA: Natively Multimodal Autoregressive Perception Architecture

Efficient Document Tampering Localization with Multi-Level Discrepancy Features and Unified DCT–Quantization Embedding

Information-Regularized Attention for Visual-Centric Reasoning

Eliciting Self-Verification in Multimodal Reasoning Agents with Reinforcement Learning

Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decoding

Mitigating Sycophancy in Multimodal Chart Understanding via Vision-Grounded Verification

Beyond Where to Look: Trajectory-Guided Reinforcement Learning for Multimodal RLVR

ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval

Transport Discrepancy as a Reliability Signal for Vision-Language-Action Models

Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs

EpiBench: Benchmarking Multi-turn Research Workflows for Multimodal Agents

Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs

ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering

When Sinks Help or Hurt: Unified Framework for Attention Sink in MLLMs

The Telephone Game: Evaluating Semantic Drift in Unified Models

Wavelet-based Intra-video Counterfactual Reasoning for Video Question Grounding

How Far Are Video Models from True Multimodal Reasoning?

SE-DETR: Explicit Semantic Exploration for Generalizability and Distinguishability in Video Temporal Grounding

MV-STRIDE: Enabling MLLMs to Master Multi-View Spatial Reasoning via Hierarchical Capability Modeling

From Reasoning to Pixels: Grounded Medical Multimodal LLMs for VQA and Segmentation

How to Teach Large Multimodal Models New Skills

Towards High-Resolution Visual Perception via Hierarchical Entity Exploration

HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task

Real5-OmniDocBench: A Full-Scale Physical Reconstruction Benchmark for Robust Document Parsing in the Wild

GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding

BaFCo: A Document Understanding Benchmark for Complex Bangla Form Comprehension

Iterative Perceptual Alignment for VLMs via Deterministic Reconstruction Feedback

HART: High-Resolution Annotation-Free Reasoning Technique through a Closed-loop Framework

Caption Bottleneck Models

Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detection

CogniCred: A Dataset and Benchmark for Cognitive Credential Forgery Detection

Error-Driven Scene Editing for 3D Grounding in Large Language Models

GridVQA-X: A Diagnostic Framework for Evaluating Multimodal Explainability Methods

Identifying and Resolving Pitfalls of Knowledge-Based VQA Benchmarks: Auditing, Repairing, and Augmenting

Event-Driven Video Generation

Structured Redundancy Modeling for Efficient Visual Token Pruning in High-Resolution MLLMs

Geo-DPO: Aligning Semantic Intent with Geometry for 3D Affordance Segmentation

CiQi-Agent: Aligning Vision, Tools and Aesthetics in Multimodal Agent for Cultural Reasoning on Chinese Porcelains

ViTAL‑X: Video-Text Alignment with Cross‑Modal Temporal Edits

Learning Spectral and Polarimetric Clues for One-to-Multimodal Novel View Synthesis

BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Models

LatentPilot: Scene-Aware Vision-and-Language Navigation by Dreaming Ahead with Latent Visual Reasoning

Beyond Dense Futures: World Models as Structured Planners for Robotic Manipulation

OmniNWM: Unifying the State-Action-Reward Triad for Closed-Loop Panoramic Driving Navigation World Models

ChronoFlow Policy: Unifying Past-Future Interaction Flow in Visuomotor Policy Learning

HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving

DriveVA: Video Action Models are Zero-Shot Drivers

RoMan-4D: Learning Robot Arm Manipulation from 4D World Models

SPEAR: A Simulator for Photorealistic Embodied AI Research

OmniFit: Multi-modal 3D Body Fitting via Scale-agnostic Dense Landmark Prediction

Plug-and-Play Traffic Element Awareness for End-to-End Autonomous Driving

Panoramic Affordance Prediction

HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human–Scene Interactions

CabinSI: Omni-Cabin Spatial Reasoning through Explicit Visual Cognitive Maps

Towards Generalizable Robotic Manipulation in Dynamic Environments

EffiDINO: Task-Specific Model Pruning via Gram Anchoring Subspace Consistency

Spatial Amsan: A Benchmark for Perception-Grounded Spatial Reasoning and Action Evaluation in Egocentric Manipulation

DriveWeaver: Point-Conditioned Video Inpainting for Controllable Vehicle Insertion in Autonomous Driving Simulation

OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams

ASSCG: Just-Right Gating over Chattering for Fast–Slow LLM Planning in Autonomous Driving

Dual-Anchoring: Addressing State Drift in Vision-Language Navigation

Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives

Predicting Consequences and Reinforcing Navigation Policies with Latent World Models

S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresight

MOJITO: Modal Joint Learning for Unified End-to-End Autonomous Driving

XYZ-IBD: Benchmarking Robust 6D Object Pose Estimation under Real-World Industrial Complexity

ESTANet: Efficient Online Error Detection in Procedural Videos via Prediction Inconsistency

A scalar per patch from pre-trained ViTs enables fast moving navigation in the real world

ORION: Ordinal Neural Collapse as a Representation Prior for Visual Navigation

Grasp-Oriented Non-Prehensile Manipulation via Learning a Graspability Field

ConTrack: Constrained Hand Motion Tracking with Adaptive Trade-off Control

Understanding Cross-Rig Generalization in Automotive Perception: a Multi-Rig Benchmark and Rig Variation Metrics

VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model

CoMind: Understanding Collaborative Human Activity from Multiple Minds and Views

SparseDriveV2: Scoring is All You Need for End-to-End Autonomous Driving

Learning Transferable Dynamics Priors from Action to World Modeling

Unordered Landmark Visual Navigation

Masked Depth Modeling for Spatial Perception

AgentVLN: Towards Agentic Vision-and-Language Navigation

CoMaTrack: Competitive Multi-Agent Game-Theoretic Tracking with Vision-Language-Action Models

Walk through Paintings : Ego-centric World models from Internet Priors

TEX-Drive: Temporal Perception Meets Experience-Guided Mixture-of-Experts for End-to-End Autonomous Driving

CausalDrive: Real-time Causal World Models for Autonomous Driving

Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout

VGGT-World: Transforming VGGT into an Autoregressive Geometry World Model

RoboStream: Weaving Spatio-Temporal Reasoning with Memory in Vision-Language Models for Robotics

QuantV2X: A Fully Quantized Multi-Agent System for Cooperative Perception

PixelPilot: Scalable Vision-Language-Action Models for End-to-End Autonomous Driving

Doe-2: 3D Representation World Model for Unified Driving Scene Forecasting

PersonaDrive: Controllable Trajectory Prediction with Multi-Dimensional Driving Personas

R3DP: Real-Time 3D-Aware Policy for Embodied Manipulation

SegDiff: Segmented Trajectory Diffusion for Consistent and Adaptive Robot Manipulation

CoGoal3D: Collaborative 3D Object Detection with 3D-Aware Fusion and Refinement

XDen-1K: A Density Field Dataset of Real-World Objects

NavWM: A Unified Navigation World Model for Foresight-Driven Planning

FlowDec: Temporal Conditional Flow Decorruptor for Robust Continuous Vision-Language Navigation

Stabilizing Real-World Visual Active Tracking with Action-Smooth Test-Time Adaptation

RelAfford6D: Relational 6D Affordance Graphs for Constraint-Driven Robotic Manipulation

MobileManiBench: Simplifying Model Verification for Mobile Manipulation

Agentic Collaborative Cognition for Zero-Shot 3D Understanding

Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces

DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving

When the City Teaches the Car: Label-Free 3D Perception from Infrastructure

UniDrive-WM: Unified Understanding, Planning and Generation World Model For Autonomous Driving

Humanoid Whole-Body Manipulation via Active Spatial Brain and Generalizable Action Cerebellum

BEVLM: Distilling Semantic Knowledge from LLMs into Bird's-Eye View Representations

DeGuNet: Depth-Guided Ultra-Compact Backbones for Efficient LiDAR-Camera 3D Detection

StreamSpatial: A Benchmark and Framework for Streaming 3D Visual-Spatial Reasoning

ZTRS: Zero-Human Demonstration End-to-end Autonomous Driving with Trajectory Scorer

Driving like yourself: A Benchmark for Closed-Loop Personalized End-to-End Autonomous Driving

RAF: Reliability-Aware Fusion of Camera, LiDAR, and 4D RADAR for Robust 3D Object Detection in Adverse Weather

SIGMA-Lane: Scale-pyramId Gated MAmba for Temporally Consistent Video Lane Detection

PriorMaskMap: Robust Online Vectorized Map Construction with Biased Priors

UniTeD: Unified Temporal Diffusion for Joint Perception and Planning in Autonomous Driving

StructPolicy: Structure-Guided Imitation Learning Robust to Visual Domain Shifts

RadarGen: Automotive Radar Point Cloud Generation from Cameras

MA-VLA: Multi-Arm Vision-Language-Action Model for Collaboration and Compositional Generalization

ESCAPE: Episodic Spatial Memory and Adaptive Execution Policy for Long-Horizon Mobile Manipulation

Physically Grounded 3D Generative Reconstruction under Hand Occlusion using Proprioception and Multi-Contact Touch

Robobench: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models as Embodied Brain

World-in-Loop: Online Correction via Event-Triggered World Models for Robust VLA Policies

Thinking Ahead: Foresight Intelligence in MLLMs and World Model

UniDriveDreamer: A Single-Stage Multimodal World Model for Autonomous Driving

SGC-Lane: Monocular 3D Lane Detection with Standard-Definition Map Guidance and Lane Completion

WALL-EVE: World Alignment with Rule Learning in Visual Environments

DiNBV-Grasp: Real-Time Distance-Aware Two-Stage Next-Best-View for Robotic Grasping

C2E: Boosting Ego-Only 3D Object Detection via Multi-Teacher Contrastive Knowledge Distillation

Describe-Then-Act: Proactive Agent Steering via Distilled Language-Action World Models

NeSy-Route: A Neural-Symbolic Benchmark for Constrained Route Planning in Remote Sensing

SP-TransientBench: A Real-Captured Single Photon Perception Benchmark

Guide, Think, Act: Interactive Embodied Reasoning for Vision-Language-Action Model

Noise is a Good Teacher: A Noise-Driven Framework for Robust Collaborative Perception

Cooking beyond Frames: A Stereo Event Camera Dataset in the Kitchen

PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation

ReconDreamer-RL: Enhancing Reinforcement Learning via Diffusion-based Reconstruction

TraversRL: Traversable Pedestrian Pathway Generation With Reinforcement Learning

Boxer: Robust Lifting of Open-World 2D Bounding Boxes to 3D

RESOLVE: A Multi-Resolution and Multi-Modal Dataset for Roadside Cooperative Perception

CoReLIN: Constraint-based Reasoning for Zero-shot Lifelong Interactive Navigation

E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenes

DiverseAD: A Large-Scale Driving Dataset with Diverse Atmospheric Conditions

Sen-Cap: Sensor-Flexible and Noise-Resilient Human Motion Capture via LiDAR-Camera Integration

Markov-Renewal Single-Photon LiDAR Simulator

OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence

MolmoWeb: Open Visual Web Agent and Open Data for the Open Web

MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning

DVG-WM: Disentangled Video Generation Enables Efficient Embodied World Model for Robotic Manipulation

What if? Emulative Simulation with World Models for Situated Reasoning

TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction

SIMON: SImultaneous Multi-Object Navigation

Reflection-Aware Reasoning for Non-Line-of-Sight Pedestrian Localization

3DWay: Generalizing Robot Manipulation via 3D Consistent Waypoints

Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresight

TriO: Tri-Modal Unsupervised Occupancy World Model for Anything Perception

VVSim: A Large-Scale Aerial-Ground Dataset and Benchmark for Cooperative Perception

MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning

Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification

LEO-Fuse: A Modality- and Task-Agnostic Universal Framework for Multimodal Human Sensing

UniBYD: A Unified Framework for Learning Robotic Manipulation Across Embodiments Beyond Imitation of Human Demonstrations

OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial Agents

E-VLA: Event-Augmented Vision-Language-Action Model for Dark and Blurred Scenes

SwiftWA: An Efficient Action-Centered World-Action Model

LaGen: Towards Autoregressive LiDAR Scene Generation

Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models

Two-Way Street: Efficient VSLAM using Collaborative In-Sensor and Off-Sensor processing

ContextFlow: In-Context Flow Matching for Robot Manipulation

Boba: Batched Simulation for Physics-Based Gaussian Digital Twins

VOCA: Visual Odometry with Codec Awareness

Lifting Ego World Models for Planning and Control

Sentinel: Embodied Cooperative Spatial Reasoning and Planning

FindingDory: A Benchmark to Evaluate Memory in Embodied Agents

Agent-OBJ: Prompt-Driven 3D Adversaries for Multi-Modal Perception

RAE-NWM: Navigation World Model in Dense Visual Representation Space

WildCity: A Real-World Dataset for City-Scale Rendering and Beyond

VPA-WM: Vision-Priors-Aligned World Models for Robust Visual Reinforcement Learning

GameWorlds: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents

HSDF-Lane: Height-Aligned Signed Distance Field with Semantic Lane Prior for 3D Lane Detection

Self-Evolving Just-In-Time Memory for Proactive Embodied Safety

Drive2Danger: Deceive End-to-End Autonomous Driving with Risky Instance Recognition

STEP: Spatial Thinking and Egocentric Pointing for Embodied Instruction Following

Tac2Real: Reliable and GPU Visuotactile Simulation for Online Reinforcement Learning and Zero-shot Real-World Deployment

PriorEye: Geospatial Visual Priors for End-to-End Autonomous Driving

Hypothesis Graph Refinement: Hypothesis-Driven Exploration with Cascade Error Correction for Embodied Navigation

Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation

360CityArena: A Realistic Virtual Urban Navigation Benchmark for Embodied Agents

AMCoNav: Asynchronous Multi-module Collaborative Framework for Embodied Visual Navigation

LMGenDrive: Bridging Multimodal Understanding and Generative World Modeling for End-to-End Driving

NutriBench-Kitchen: Benchmarking Embodied AI for Nutrition Management

HitMem: Hierarchical Temporal 3D Memory with Multi-Modal Context-Aware Retrieval for Dynamic Environments

HiPolicy: Hierarchical Multi-Frequency Action Chunking for Policy Learning

Grounding Sim-to-Real Generalization in Dexterous Manipulation: An Empirical Study with Vision-Language-Action Models

The Language of Visual Attention: Modeling Scanpaths via Autoregressive Token Prediction

WebRetriever: A Large-Scale Comprehensive Benchmark for Efficient Web Agent Evaluation

EvoWorld: A World-Model-Centric Framework for Continuous Self-Evolution of Modular Embodied Skills

WildWorld: A Large-Scale Dataset for Action-Conditioned World Modeling with Explicit State Annotations

Generative Lane Topology Reasoning via Autoregressive Model with Geometry Prior

RGBT-GroundBench: Visual Grounding Beyond RGB in Complex Real-World Scenarios

CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates

Fast and Scalable LiDAR Data Generation for Autonomous Driving Simulation without Raycasting

MobileOcc: A Human-Aware Semantic Occupancy Dataset for Mobile Robots

SkillSpotter: Pose-Aware Multi-View Skilled Action Detection and Grading in Ego-Exo Videos

Stand Up and Move: Benchmarking Interactive Spatial Intelligence in WalkerBench

HERO: Heterogeneous Evidential Robust Object-Level Collaborative Perception

RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures

Hi-Nav: Hierarchical Framework for Continuous Vision-Language Navigation via Map Guidance and Waypoint Reasoning

UECP: Uncertainty-Enhanced Collaborative Perception

World Models for Learning Dexterous Hand-Object Interactions from Human Videos

Hierarchical 3D Scene Graph Construction and Belief-based Planning for Semantic Navigation

Driving is a Game: Combining Planning and Prediction with Bayesian Iterative Best Response

MV2GF: Multi-view Pedestrian Detection with a Visual Geometric Foundation Model

Twin-DAgger: Synergizing Digital Twins and Human Corrections for Efficient Robot Manipulation

LiSTAR: Ray-Centric World Models for 4D LiDAR Sequences in Autonomous Driving

CausalVAE as a Plug-in for World Models: Towards Reliable Counterfactual Dynamics

Unpaired Geometry-Guided Sim2Real Translation for Autonomous Driving

SAFER-Activities: A Dataset for Smart Assessment of Fall Events and Routine Activities

What Matters in RL-Based Methods for Object-Goal Navigation? An Empirical Study and A Unified Framework

Thinking from the Robot’s View: The CoT-HRC Benchmark for Human Intent Reasoning in Embodied Collaboration

Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation

Towards Metric-Agnostic Trajectory Forecasting

DH-VLM: Dual-Horizon Cooperative Latent Reasoning for Autonomous Driving

SynVAR: Synergizing Spatial and Semantic Alignment in Visual Autoregressive Model

Geometry-Aware Spatio-Temporal Context Modeling for 4D Occupancy Forecasting

AeroVLA: A Vision-Language-Action Model for UAV Navigation via Minimalist End-to-End Control

CooperScene: Multi-Modal Cooperative Autonomy Benchmark with C-V2X Communication Characterization

One Demonstration Is Enough for Real-World Robotic Reinforcement Learning

KineBench: Benchmarking Embodied World Models via IDM-Free Kinematic Grounding

ZAP: Zero-Shot Assembly Planning with Large Language Models

RECO: Region-Aware Compensation for Extrinsic Perturbations in Roadside 3D Detection

AdaDexGrasp: Adaptive Dexterous Grasping via 3D Visuo-Tactile Representation Fusion

EchoVLA: Robotic Vision-Language-Action Model with Synergistic Declarative Memory for Mobile Manipulation

Multi-scale Mixture of World Models for Embodied Agents in Evolving Environments

Persistent Robot World Models: Stabilizing Multi-Step Rollouts via Reinforcement Learning

Tactile Modality Fusion for Vision-Language-Action Models

EgoTraj: Real-World Egocentric Human Trajectory

Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising

BeyondSight: Object Permanence for End-to-End Autonomous Driving

ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving

VIPS: Vehicle-Infrastructure Cooperative Planning Benchmark via Pseudo-Simulation

(ends 5:00 PM)

Demo Session 6 [3:00-5:00]

(ends 5:00 PM)