Welcome! I'm currently a first-year Ph.D. student of computer science at UNC-Chapel Hill, advised by Prof. Tianlong Chen. I also work closely with Dr. Hanrui Wang. Before that, I received my B.E. in CS from USTC. This summer, I have been a research intern at Apple AI/ML, working with the Foundation Model team. Feel free to reach out if you'd like to chat about exciting topics about LLM reasoning!

I like simple and useful things. I am broadly interested in 1) efficient AI computing, 2) ML for science and vice versa. I also enjoy building systems and putting thoughts into reality.

To find out more, you can check out my Twitter, Last.fm, or Instagram.

Selected Publications

(* = equal contribution) (^ = equal supervision)

Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training and Inference
Shuqing Luo, Pingzhi Li, Jie Peng, Hanrui Wang, Yu Cheng, Tianlong Chen
ICML 2025 / arXiv / Code

Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert Parallelism Design
Mohan Zhang*, Pingzhi Li*, Jie Peng, Mufan Qiu, Tianlong Chen
NAACL 2025 (SAC Award) / arXiv / Code

Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild
Xinyu Zhao*, Guoheng Sun*, Ruisi Cai*, Yukun Zhou*, Pingzhi Li*, Peihao Wang*, Bowen Tan, Yexiao He, Li Chen, Yi Liang, Beidi Chen, Binhang Yuan, Hongyi Wang^, Ang Li^, Zhangyang Wang^, Tianlong Chen^
NeurIPS 2024 / arXiv / Code

Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark
Yihua Zhang*, Pingzhi Li*, Junyuan Hong*, Jiaxiang Li*, Yimeng Zhang, Wenqing Zheng, Pin-Yu Chen, Jason D. Lee, Wotao Yin, Mingyi Hong, Zhangyang Wang, Sijia Liu, Tianlong Chen
ICML 2024 / arXiv / Code / Tutorial

Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy
Pingzhi Li, Zhenyu Zhang, Prateek Yadav, Yi-Lin Sung, Yu Cheng, Mohit Bansal, Tianlong Chen
ICLR 2024 (Spotlight) / arXiv / Code

Awards

Resume

Here is my Resume (last updated May 2025).