Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
Published multiple papers, including but not limited to: 'Sample-Optimal Agnostic Boosting with Unlabeled Data', 'A shared-revenue Bertrand Game', 'Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models', etc. 'Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models' was accepted to ICLR 2025 and presented orally; 'A Regret Minimization Approach to Multi-Agent Control' was accepted to ICML 2022 and GMAS Workshop @ ICLR 2022, and won the Best Poster award.
Research Experience
Working in the AWS Automated Reasoning Group, previously applied RL to Amazon's supply chain.
Education
Ph.D. in Computer Science from Princeton University, supervised by Prof. Elad Hazan. Also worked as a student researcher at Google Brain. B.S. in Computer Science from Caltech. Previously a software engineer at IMC Trading.
Background
Senior Machine Learning Scientist in the AWS Automated Reasoning Group, working on the intersection of LLMs, reinforcement learning, and automated reasoning. Interested in the theory and algorithms for machine learning, particularly reinforcement learning, control, optimization (convex and non-convex), and online learning.