Chihan Cui

chihan [dot] cui [at] wisc [dot] edu

I am a first-year Ph.D. student in Computer Science at the University of Wisconsin-Madison, advised by Ming Liu. I received my B.S. in Computer Science from the University of Toronto (St. George Campus), where I was advised by Qizhen Zhang and Phil Bernstein.

My research interests lie in MLSys, efficient ML, and GPU communication. I have contributed to UCCL-EP GitHub stars (portable expert-parallel communication for LLMs), and Sirius GitHub stars (GPU-accelerated SQL engine). I am always open to new ideas and collaborations – feel free to reach out!

news

Jul 15, 2026 Our paper Expert-Choice Routing Enables Adaptive Computation in Diffusion Language Models has been accepted to COLM 2026!
Mar 26, 2026 Our paper UCCL-EP: Portable Expert-Parallel Communication has been accepted to OSDI 2026!
Dec 15, 2025 Sirius achieved #1 on the ClickBench benchmark!
Sep 01, 2025 Joined the University of Wisconsin-Madison as a Ph.D. student in Computer Science, advised by Ming Liu.
Apr 07, 2025 Our paper dpBento: Benchmarking DPUs for Data Processing is now available on arXiv.

selected publications

  1. COLM ’26
    Expert-Choice Routing Enables Adaptive Computation in Diffusion Language Models
    Shuibai Zhang*, Caspian Zhuang*, Chihan Cui*, Zhihan Yang, Fred Zhangzhi Peng, Yanxin Zhang, Haoyue Bai, Zack Jia, Yang Zhou, Guanhua Chen, and Ming Liu
    In Conference on Language Modeling (COLM), 2026
  2. OSDI ’26
    UCCL-EP: Portable Expert-Parallel Communication
    Ziming Mao, Yihan Zhang, Chihan Cui, Kaichao You, Zhongjie Chen, Zhiying Xu, Scott Shenker, Costin Raiciu, Yang Zhou, and Ion Stoica
    19th USENIX Symposium on Operating Systems Design and Implementation (OSDI), 2026
  3. arXiv
    dpBento: Benchmarking DPUs for Data Processing
    Jiasheng Hu, Chihan Cui, Anna Li, Raahil Vora, Yuanfan Chen, Philip A. Bernstein, Jialin Li, and Qizhen Zhang
    arXiv preprint arXiv:2504.05536, 2025