Hello! I am an Assistant Professor in the Computer Science (CSD) and Machine Learning (MLD) departments at Carnegie Mellon University (CMU). I also spend a part of my time at Google DeepMind. I finished my Ph.D. from UC Berkeley in 2023. I am interested in a number of topics pertaining to reinforcement learning (RL) and decision-making, including:
- scalable and reliable offline (and online) reinforcement learning (RL) algorithms [recent works: stop regressing, ICML 2024; scaling offline RL; ICLR 2023; value vs policy, arXiv 2024; online fine-tuning, NeurIPS 2023]
- intersection of foundation models and reinforcement learning (both on using foundation models for decision making and developing decision-making and RL tools for building better foundation models) [recent works: ArCHer, ICML 2024; RL + synthetic data => 8x, arXiv 2024; multi-turn RL for iterative improvement, arXiv 2024, inference-time adaptation outperforms more pre-training, arXiv 2024, preference fine-tuning, ICML 2024; promptable representations]
- robotic learning and control [recent works: SuSIE, ICLR 2024; V-PTR, ICRA 2024]
- Applications [recent works: DigiRL (mobile GUI agent), arXiv 2024; Promoter (biological sequence) design, arXiv 2024]
A full list of my publications can be found on my [Google Scholar]. My twitter handle is: [Twitter]