Andre He

I’m a second-year Ph.D. student in the Language Technologies Institute at CMU, co-advised by Prof. Sean Welleck and Prof. Daniel Fried. Before coming to CMU, I completed my undergraduate studies at UC Berkeley. I had the privilege of working with Nicholas Tomlin and Prof. Dan Klein in the Berkeley NLP Group and with Kuan Fang and Prof. Sergey Levine in RAIL. More recently, I completed an internship at AWS, where I was mentored by Nathaniel Weir and Kaj Bostrom.

My research interests lie in Reasoning and Reinforcement Learning. I’m particularly interested in how “intelligent behaviors” emerge, and what forms they take, when interacting with environments such as games, mathematics, and discourse (e.g. trying to convince a reader).

My most recent work was on reinforcement learning for theorem proving, and I am currently exploring the potential for inference scaling in text diffusion models. In the past, I have worked on language-conditioned robotics, interpretability, and computational linguistics.