|
|
||||||||||
I am an Assistant Professor at NYU Courant and a Staff Research Scientist at Google DeepMind. I research in machine learning with a focus on reinforcement learning and generative modeling.
Recently, I am interested in problems at the intersection of foundation models and decision making, such as learning world models and agents, and their applications in robotics and AI for science.
Prior to this, I was a post-doc at Stanford working with Percy Liang. I obtained my Ph.D. from UC Berkeley advised by Pieter Abbeel, and my B.S. and M.Eng. from MIT.
05/2026: We released CrystalReasoner, a reasoning model for crystal structure generation with LLMs and property-conditioned generation through RL.
02/2026: We released World-Gymnast, showing RL in a world model improves VLA policies for real robot.
02/2026: We talked about World Models as an Intermediary between Agents and the Real World in a position paper.
10/2025: We released WorldGym, a world model for evaluting robot policies (e.g., OpenVLA, Octo).
-
05/2024: Our work UniSim: Learning Interactive Real-World Simulators received the Outstanding Paper Award at ICLR 2024.