PhD student, Harvard University
3 papers at NeurIPS 2025
We propose a flow matching method for reinforcement learning with shifted-dynamics data.
We propose the first deep menu-based method for single-bidder combinatorial auctions that is dominant-strategy incentive compatible and revenue-optimizing, by adapting continuous flow matching for optimization problems.
We develop a policy for adaptive exploration on a graph under frontier constraint that is optimal for trees based on Gittins index, and show how we can apply it to network-based testing in public health settings
