- October 2025: Named a Rising Star in Data Science and Robotics.
- June 2025: Published two new papers on learning to search: SAILOR (Spotlight @ NeurIPS '25) and FOREWARN (RSS '25, Outstanding Paper at ICML '25 Workshop).
- March 2025: Released an especially exciting preprint on the real value of RL in fine-tuning/RLHF and gave a talk at Cornell about it.
Research Experience
Worked on ML at SpaceX, Perception at NVIDIA, Motion Planning at Aurora, World Models at Microsoft, and LLMs at Google during summer internships.
Education
Pursuing a PhD at the Robotics Institute, Carnegie Mellon University, under the supervision of Drew Bagnell and Steven Wu; completed his B.S. / M.S. at UC Berkeley, where he worked with Anca Dragan on Learning with Humans in the Loop.
Background
Final-year PhD candidate at the Robotics Institute, Carnegie Mellon University, focusing on efficient algorithms for interactive learning (e.g., imitation/RL/RLHF). His research aims to develop robustly aligned agents that can handle unseen situations gracefully. He integrates ideas from RL and game theory to create principled and scalable algorithms for domains like robotic manipulation and language modeling.