Qinghua Liu

I'm a researcher in (mid, post]-training at OpenAI.

I'm privileged to be part of an amazing team working on the critical path to shipping Codex and ChatGPT, including GPT-5.5, GPT-5.6, and the next generation of models. I also very indirectly contributed to specialized models such as GPT‑5.5‑Cyber and GPT‑Rosalind. Earlier, I worked on model personalities, which was integrated into GPT-5 and GPT-5.1.

I received Ph.D. from Princeton, advised by Chi Jin. My PhD works focused on RL theory, including partially observable RL (POMDP, PSR, Survey), multi-agent RL (Stochastic Game), and RL with large state spaces (Function Approximation). During PhD, I've interned at DeepMind London with Csaba Szepesvári. After PhD, I spent a wonderful year as a postdoctoral researcher at Microsoft Research NYC.

Even earlier, I received a B.E. in Electrical Engineering and a B.S. in Mathematics from Tsinghua University.

Google Scholar, Twitter