Chenyang Wang
Researcher & Engineer
I work on reinforcement learning, from reasoning to infrastructure. I care about the theory and system that make scalable learning possible, and the behaviors that emerge when it works.
Now building and studying how agents learn to reason.
Roots
My research began at BAIR, where I had the freedom to explore a broad range of ideas in machine learning. Along the way, I’ve had the pleasure of working with and learning from Xiuyu Li, Haven Feng, Shaofeng Yin, Louis Liu, Tingle Li and many friends—all of whom have shaped how I think about research and why I enjoy doing it.
