Professional Experience

2024-11 – 2025-05 Department of Electronic Engineering, Tsinghua University Led research on fine-tuning diffusion and flow matching policies with online RL.

2024-07 – 2024-10 Noetix Robotics Developed algorithm for versatile and anthropomorphic humanoid locomotion via sim-to-real RL and GAN-based imitation learning.

2024-02 – 2024-09 Carnegie Mellon University Led research on distributed policy optimization theory under partial observability.

2023-07 – 2024-02 Institute for Interdisciplinary Information Sciences, Tsinghua University Led research on statistical theory of risk-sensitive partially observable RL.