NeurIPS 2025 Spotlight
About
I am a researcher working on reinforcement learning and control theory, with applications in power and energy systems. I am currently an Eric and Wendy Schmidt AI in Science Postdoctoral Fellow at the AI for Science Institute and Duffield College of Engineering, Cornell University, working with Fengqi You. I received my Ph.D. in Computer Science from the Institute for Interdisciplinary Information Sciences at Tsinghua University in 2025, advised by Chenye Wu and Ran Duan. From 2023 to 2024, I was a visiting student researcher in Computing and Mathematical Sciences at Caltech, working with Adam Wierman. I received my bachelor's degree in Computer Software Engineering from Huazhong University of Science and Technology in 2020.
Research
My research develops theory and algorithms for understanding and exploiting the value of information and structure in sequential decision-making. I study imperfect predictions, decomposable dynamics, Bellman convexity, Lyapunov stability, and chance constraints, with an emphasis on sample-efficient reinforcement learning and rigorous performance guarantees.
My applied work addresses the reliable operation of power and energy systems and the integration of AI data centers with the grid.
Selected Publications
Full publication list on Google ScholarNeurIPS 2026
Learning Chance-Constrained MDPs with Bellman Distributional Certificates[PDF]
ICML 2025
Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate Factorization[PDF]
IEEE Transactions on Smart Grid, 2024
Self-Improving Online Storage Control for Stable Wind Power Commitment[PDF]
IEEE Transactions on Power Systems, 2024
Sample-Adaptive Robust Economic Dispatch With Statistically Feasible Guarantees[PDF]
IEEE Control Systems Letters, 2025
On the Optimal Deterministic Policy Learning in Chance-Constrained Markov Decision Processes[PDF]
News
Oct. 2026
National Academies Workshop
I will give an invited presentation at the Integration of Artificial Intelligence in the Electricity System workshop in Washington, DC.
Sep. 2026
NeurIPS 2026
Our paper Learning Chance-Constrained MDPs with Bellman Distributional Certificates was accepted.
Sep. 2025
Schmidt AI in Science Fellowship
I joined the AI for Science Institute and Duffield College of Engineering at Cornell University as an Eric and Wendy Schmidt AI in Science Postdoctoral Fellow.
Sep. 2025
NeurIPS 2025 Spotlight
Our work on reinforcement learning with imperfect transition predictions was accepted as a Spotlight.
Sep. 2025
IEEE LCSS
Our work on deterministic policy learning in chance-constrained Markov decision processes was accepted.
Jul. 2025
ICML 2025
Our paper on approximate factorization for reinforcement learning was presented in Vancouver.
Selected Honors and Fellowships
2025
Eric & Wendy Schmidt AI in Science Postdoctoral Fellowship
2025
IIIS Outstanding Graduate Award
2024
Toyota Outstanding Scholarship
2023
Ubiquant Outstanding Scholarship
2017
National Scholarship
Teaching
Guest lectures
- Fall 2025: AI for Science, Cornell University
- Fall 2025: AI for Energy Systems, Cornell University
- Spring 2026: Deep Learning, Cornell University
Teaching assistance
- Fall 2021: Combinatorial Mathematics, Tsinghua University
- Fall 2022: AI Research Practice, Yao Class, Tsinghua University
Professional Service
Conference reviewing: NeurIPS (Top Reviewer), ICLR, AAAI, IEEE CDC, ACC, PSCC, IEEE SmartGridComm, and ACM e-Energy.
Journal reviewing: IEEE Transactions on Automatic Control, IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Transactions on Smart Grid, and IEEE Transactions on Power Systems.
TPC membership: IEEE SmartGridComm and the ACM e-Energy poster session.