Hi, there! I’m Yifei, a first-year Ph.D. student affiliated with Berkeley AI Research (BAIR). I’m advised by prof. Sergey Levine.

I had the pleasure of working on problems in providing theoretical insight into various machine-learning problems so that we are confident that our algorithms can be reliable even in complicated real-world situations. These days, I am most interested in interactive decision-making/reinforcement learning with LLM/VLMs (i.e. LLM/VLM agent). In particular, I am interested in large-scale self-improvement where the agent improves itself through open-ended reinforcement learning without any human supervision.

I just graduated from Cornell as an undergrad where I have am fortunate enough to have been working with prof. Yansong Feng at Peking University, prof. Wen Sun at Cornell University, and prof. Sernam Lim at Meta AI.

Awards Received

Pauline and Irving Tanner Dean’s Scholarship

CRA Outstanding Undergraduate Researcher Award Finalist 2023