Yuanpei Chen

On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations

Dexterous Non-Prehensile Manipulation for Ungraspable Objects via Extrinsic Dexterity

Communication-Efficient Desire Alignment for Embodied Agent–Human Adaptation

SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning

DexFlyWheel: A Scalable and Self-improving Data Generation Framework for Dexterous Manipulation

Falcon: Fast Visuomotor Policies via Partial Denoising