Published papers include 'Bridging Discrete and Continuous RL: Stable Deterministic Policy Gradient with Martingale Characterization' and several preprints and conference papers. Some papers have been accepted to top conferences such as NeurIPS 2025, ICLR 2025, COLT 2024, and ICML 2024.
Research Experience
Intern at Microsoft Research Asia; Visited Tengyu Ma at Stanford.
Education
PhD in IEOR, UC Berkeley, supervised by Xin Guo; B.S. in School of Mathematical Sciences, Peking University, supervised by Cheng Zhang.
Background
Research interests span broadly in statistics, optimization, and machine learning, including multi-agent RL, language models, diffusion models, distributed optimization, sampling, and variational inference.