David Xia 夏锦源

My research centers on the theory of sequential decision-making: reinforcement learning, online learning, and function approximation in Markov decision processes. I'm drawn to questions of sample and computational complexity — when efficient learning is provably possible, and the algorithms that achieve it. Alongside this core focus, I've worked across combinatorics, adversarial machine learning, and human-centered evaluation of large language models.

• May 2026 Started a research internship at Northwestern University with Prof. Zhaoran Wang on agentic reinforcement learning.
• Apr 2026 Presented our LLM-journalism audit at the HEAL workshop at CHI 2026 in Barcelona.
• Jun 2026 RSK linear operators and the Vershik–Kerov–Logan–Shepp curve was accepted — to appear in the Electronic Journal of Combinatorics.
• Feb 2026 Joined the iDEA-iSAIL Lab at UIUC with Prof. Hanghang Tong, working on theoretical RL.
• May 2025 EveGuard appeared at the IEEE Symposium on Security and Privacy 2025.
• Jan 2025 Presented sports-predictability research at the Joint Mathematics Meetings.