Yong-Lu Li

Beyond Static Vision: Scene Dynamic Field Unlocks Intuitive Physics Understanding in Multi-modal Large Language Models

SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning

RoboHiMan: A Hierarchical Evaluation Paradigm for Compositional Generalization in Long-Horizon Manipulation

Tired Actor: Fatigue-Informed Character Control

ImDy: Human Inverse Dynamics from Imitated Observations

The Labyrinth of Links: Navigating the Associative Maze of Multi-modal LLMs