About Me

I am a Research Scientist at Meta AI. I received my PhD in Computer Science from University of Toronto, where I was advised by Yang Xu.

My current research is focused on training Large Language Model (LLM)-based AI Agents on computing devices, by employing methods in reinforcement learning, world modeling, and multimodal reasoning. I also conduct research on the mechanistic interpretability and safety alignment of generative AI systems.

During my PhD, I studied automated understanding and generation of creative language use, and I was fortunate to intern at Meta FAIR and Google Research.