Yuxi Liu

Ph.D. Student in Data Science at Peking University.

prof_pic.jpg

Center for Machine Learning Research

Peking University

Beijing, China

Hi! I am Yuxi Liu (刘ē¦¹åøŒ). I am currently a 3th-year Ph.D. student in Data Science at the Center for Machine Learning Research, Peking University (2023-2028), under the supervision of Prof. Kun Yuan. Prior to this, I obtained my B.S. degree in Mathematics from Wuhan University (2019-2023), ranking 2/32 in the Mathematics Base Class.

My research mainly focuses on efficient training and inference frameworks/algorithms for LLM/DiT. I have served as a reviewer for top-tier conferences including ICML, NeurIPS, ICLR, and CVPR.

Iā€™m always open to research discussions and collaborations. Feel free to contact me if you are interested.

šŸ“– Education

  • Ph.D. in Data Science, Peking University, 2023 - 2028
  • B.S. in Mathematics, Wuhan University, 2019 - 2023

šŸ† Honors and Awards

  • Excellent Research Award, Peking University, 2025
  • Outstanding Graduate, Wuhan University, 2023
  • National First Prize (1st in Hubei Province), Contemporary Undergraduate Mathematical Contest in Modeling (CUMCM), 2021
  • Meritorious Winner (M Prize), Mathematical Contest in Modeling (MCM/ICM), 2021
  • Second Prize (Hubei Province), Chinese Mathematics Competitions (CMC), 2021
  • Excellent Scholarship for Math Majors (Class I), Wuhan University, 2021
  • First-class Scholarship, Wuhan University, 2020
  • Bronze Medal, Chinese Mathematical Olympiad (CMO), 2018
  • Gold Medal, China Southeast Mathematical Olympiad (CSMO), 2017

selected publications

  1. Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers
    Yuxi Liu, Y. Hu, Z. Zhang, and 2 more authors
    In International Conference on Machine Learning (ICML), 2026
  2. CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure
    B. Kong, J. Liang, Yuxi Liu, and 2 more authors
    In International Conference on Learning Representations (ICLR), 2026
  3. MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling
    Yuxi Liu, R. Deng, Y. He, and 3 more authors
    In The Conference on Neural Information Processing Systems (NeurIPS), 2025