I am an Assistant Professor in the Grado Department of Industrial and Systems Engineering at Virginia Tech. Previously, I was an AI Research Scientist at Meta and a postdoctoral associate at the University of Minnesota (ECE), mentored by Mingyi Hong and Shuzhong Zhang. I received my Ph.D. in Applied Mathematics from UC Davis (Mathematics), advised by Krishna Balasubramanian and Shiqian Ma, and my B.S. in Mathematics from Zhejiang University.
My research bridges optimization, operations research, and AI. I develop mathematical foundations and algorithms for efficient foundation-model training and agentic AI alignment, while exploring how AI can advance optimization and applied mathematics.
Fully funded Ph.D. openings — Fall 2027. I am recruiting 1–2 Ph.D. students to work with me in these areas. Applicants interested in related areas of theoretical or applied AI are also welcome. Our group actively collaborates with researchers at Meta, Amazon, and Microsoft, creating opportunities for joint research and large-scale experimentation. Please email me your CV and research interests.
News
- October 2026Our paper Why Muon Outperforms Adam: A Curvature Perspective has been accepted to NeurIPS 2026. Congratulations to all my collaborators! I will travel to Atlanta in December for the conference. If you'll be there too, feel free to reach out—I'd love to catch up!
- October 2026I will be back in San Francisco attending the INFORMS Annual Meeting from October 31 to November 4. Feel free to reach out for coffee or a chat!
- August 2026Starting my new position as an Assistant Professor in the Grado Department of Industrial and Systems Engineering at Virginia Tech!
- June 2026Paper Adaptive Rank Control for Robust Reinforcement Learning is accepted by Transactions on Machine Learning Research. Congratulations to all my collaborators!
- May 2026Two papers are accepted by ICML 2026. Congratulations to all my collaborators!
- A minimalist optimizer design for LLM pretraining
- A Tale of Two Problems: Multi-Task Bilevel Learning Meets Equality Constrained Multi-Objective Optimization
- January 2026Paper Muon Outperforms Adam in Tail-End Associative Memory Learning is accepted by ICLR 2026. Congratulations to all my collaborators!
- August 2025Starting my new job as Research Scientist at Meta!
- February 2025Paper Problem-Parameter-Free Decentralized Nonconvex Stochastic Optimization is accepted by Pacific Journal of Optimization.
- January 2025Paper Joint Demonstration and Preference Learning Improves Policy Alignment with Human Feedback is accepted by ICLR 2025 (Spotlight). Congratulations to all my collaborators!
- January 2025Paper Riemannian Bilevel Optimization is accepted by Journal of Machine Learning Research!
- November 2024Paper A Riemannian ADMM is accepted by Mathematics of Operations Research!
- September 2024Two papers are accepted by NeurIPS 2024. Congratulations to all my collaborators!
- Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment
- SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining
- August 2024I'm very happy to receive the INFORMS Computing Society Prize!
- August 2024Paper Zeroth-order Riemannian Averaging Stochastic Approximation Algorithms is accepted by SIAM Journal on Optimization!
- July 2024A new grant Bi-Level Optimization for Hierarchical Machine Learning Problems: Models, Algorithms and Applications is awarded from NSF. I'm excited to be the co-PI of this project with Prof Hong!
- May 2024Paper Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark is accepted by ICML 2024. Congratulations to all my collaborators!