Postdoc, Tsinghua University, Tsinghua University
3 papers at NeurIPS 2025
We conduct an empirical study to evaluate the generalization benefits of reinforcement learning fine-tuning versus supervised fine-tuning for vision-language-action models and provide some findings and analyses.
We introduce VolleyBots, a new testbed where multiple drones cooperate and compete in the sport of volleyball under realistic physical dynamics.
We propose an online reinforcement learning technique to fine-tune a family of flow matching policies for robot learning.
