I am a senior principal research manager at Microsoft Research, New York City. Previously, I spent two years as an assistant professor in the College of Information and Computer Sciences at the University of Massachusetts, Amherst and a year as a postdoctoral researcher at Microsoft Research, NYC. Before that, I completed my PhD in the Computer Science Department at Carnegie Mellon University, advised by Aarti Singh. I received my undergraduate degree in EECS at UC Berkeley. My research interests are in machine learning and statistics. I am most excited about interactive learning, or learning settings that involve feedback-driven data collection. My recent interests revolve around decision making with limited feedback, including contextual bandits and reinforcement learning, and how these frameworks manifest in language modeling and generative AI. We are organizing a Workshop on the Foundations of Post-Training on June 30th, 2025 as part of COLT in Lyon, France. Abstract submission are due May 19th. Selected PapersSelf-improvement in language models: The sharpening mechanism. Transformers learn shortcuts to automata. Efficient first order contextual bandits: Prediction, allocation, and triangular discrimination. FLAMBE: Structural complexity and representation learning of low rank MDPs. Kinematic state abstraction and provably efficient rich-observation reinforcement learning. Disagreement-based combinatorial pure exploration: Sample complexity bounds and an efficient algorithm. Tongyi Cao and Akshay Krishnamurthy. Contextual decision processes with low Bellman rank are PAC-learnable. Low-rank matrix and tensor completion via adaptive sampling. |