Hello! I am a final year student of Yao Class at IIIS, Tsinghua University. I will join Carnegie Mellon University (CMU) as a Ph.D. student in Electrical and Computer Engineering (ECE), starting from Fall 2024.

My research passion lies in designing scalable and efficient algorithms for practical machine learning systems. For this aim, I am interested in a broad spectrum of topics, including but not limited to large language models, distributed machine learning and reinforcement learning. During my undergraduate studies, I focused on reinforcement learning, developing algorithms that integrate rigorous theoretical foundations with real-world practicality.

I am open to collaborations. If you have any ideas which we both might be interested in, please feel free to reach out!

Selected Research

Model-based return-conditioned supervised learning

Research intern at UW (Feb. 2023 - Aug. 2023).

Supervisor: Simon S. Du.

We proposed model-based return-conditioned supervised learning (MBRCSL), a novel offline RL framework that is able to do trajectory stitching while retaining the strength of return-conditioned supervised learning (RCSL) to avoid Bellman completeness requirements. [website]

Networked Markov Potential Games

Remote research intern at Caltech (Feb. 2022 - Feb. 2023).

Supervisor: Adam Wierman.

We proposed networked Markov potential games (NMPG) as a more practical relaxation of Markov potential games (MPG), and designed a localized actor-critic algorithm with provable finite-sample bound. [arXiv]

News

• Jan 2024: One paper accepted by ICLR 2024!
• Nov 2023: One paper accepted by NeurIPS 2023 FMDM workshop (oral)! Thanks for efforts from all collaborators!
• Aug 2023: Participate in UAI 2023.
• May 2023: One paper accepted by UAI 2023! Thanks for generous support from Dr. Zaiwei Chen, Yiheng Lin and Prof. Adam Wierman.
• Feb 2023: Begin my spring visit at UW. Look forward to cooperation with Prof. Simon Shaolei Du.