Yu-Xiong Wang

BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning

Capturing Visual Environment Structure Correlates with Control Performance

Latent Wasserstein Adversarial Imitation Learning

Unleashing Guidance Without Classifiers for Human-Object Interaction Animation

Dress&Dance: Dress up and Dance as You Like It

LongVTG-R1: Reinforcement Learning for Robust Long-Video Temporal Grounding

Dissecting Demystifying Region-Based Representations in MLLMs

One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding

3DGS-Drag: Dragging Gaussians for Intuitive Point-Based 3D Editing

Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual Perception

MR. Video: MapReduce as an Effective Principle for Long Video Understanding

Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning

Self-Guided Hierarchical Exploration for Generalist Foundation Model Web Agents

Diff-2-in-1: Bridging Generation and Dense Perception with Diffusion Models

Proposer-Agent-Evaluator (PAE): Autonomous Skill Discovery For Foundation Model Internet Agents

RTDiff: Reverse Trajectory Synthesis via Diffusion for Offline Reinforcement Learning

ReferEverything: Towards segmenting everything we can speak of in videos

Virtual Fitting Room: Generating Arbitrarily Long Videos of Virtual Try-On from a Single Image

Emerging Pixel Grounding in Large Multimodal Models Without Grounding Supervision

Latent Wasserstein Adversarial Imitation Learning

LayeredGS: Efficient Dynamic Scene Rendering and Point Tracking with Multi-Layer Deformable Gaussian Splatting

Proposer-Agent-Evaluator (PAE): Autonomous Skill Discovery For Foundation Model Internet Agents

Video Diffusion Models Learn the Structure of the Dynamic World