Jingya Wang

Human-Object Interaction via Automatically Designed VLM-Guided Motion Policy

MIMIC: Mask-Injected Manipulation Video Generation with Interaction Control

UniHM: Unified Dexterous Hand Manipulation with Vision Language Model

Flow Connecting Actions and Reactions: A Condition-Free Framework for Human Action-Reaction Synthesis

Diffusion Bridge or Flow Matching? A Unifying Framework and Comparative Analysis

Conformal Reliability: A New Evaluation Metric for Conditional Generation

Humanoid-LLA: Open-Vocabulary Humanoid Whole-Body Control with Large Language Action Model

Bridge Policy: Visuomotor Policy Learning via Stochastic Optimal Control

FLEx: Personalized Federated Learning for Mixture-of-Experts LLMs via Expert Grafting

UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control

OpenHOI: Open-World Hand-Object Interaction Synthesis with Multimodal Large Language Model

GenPO: Generative Diffusion Models Meet On-Policy Reinforcement Learning

TokMan:Tokenize Manhattan Mask Optimization for Inverse Lithography

SeqAfford: Sequential 3D affordance reasoning via Multimodal Large Language Model