Publications: 'When Can Model-Free Reinforcement Learning be Enough for Thinking?' awarded Most-Thought-Provoking Paper at Finding the Frame Workshop @ RLC 2025 (Oral); 'AutoMixAlign: Adaptive Data Mixing for Multi-Task Preference Optimization in LLMs' accepted at ACL 2025 Main Conference; 'Centralized Adaptive Sampling for Reliable Co-training of Independent Multi-Agent Policies' under review. Awards: Top Review Award at NeurIPS 2024; Sandia Employee Recognition Award.
Research Experience
Research intern at Amazon's Rufus team (working on multi-objective alignment for LLMs); Research intern at Sandia National Laboratories (working on RL for power grid management); Worked in databases with Jignesh Patel during the first year of his Ph.D.
Education
Ph.D. in Computer Sciences from the University of Wisconsin-Madison, advised by Josiah Hanna; BPhil in Physics and B.S. in Mathematics from the University of Pittsburgh, studied with Vladimir Savinov.
Background
Research Interests: Improving the data efficiency of reinforcement learning (RL) algorithms by designing better data collection strategies. Field: Computer Sciences.
Miscellany
Looking for postdoc or research scientist opportunities starting Summer/Fall 2026.