Portrait of Yuezhou Ma

Yuezhou Ma

Ph.D. Student
Tsinghua University
mayuezhou20(at)gmail.com


About Me

I am currently a Ph.D. student in the School of Software, Tsinghua University, advised by Prof. Mingsheng Long.

My research focuses on Physical AI and world models, with the goal of building learning systems that understand, simulate, and interact with the physical world.

Publications & Preprints

  1. ProPINN: Demystifying Propagation Failures in Physics-Informed Neural Networks
    Yuezhou Ma*, Haixu Wu*, Hang Zhou, Huikun Weng, Jianmin Wang, Mingsheng Long#
    Transactions on Machine Learning Research (TMLR), 2026.
    PDF Code
  2. Brep2Shape: Boundary and Shape Representation Alignment via Self-Supervised Transformers
    Yuanxu Sun*, Yuezhou Ma*, Haixu Wu#, Guanyang Zeng, Muye Chen, Jianmin Wang, Mingsheng Long#
    International Conference on Machine Learning (ICML), 2026.
    PDF Code
  3. Transolver-3: Scaling Up Transformer Solvers to Industrial-Scale Geometries
    Hang Zhou, Haixu Wu, Haonan Shangguan, Yuezhou Ma, Huikun Weng, Jianmin Wang, Mingsheng Long#
    International Conference on Machine Learning (ICML), 2026.
    PDF Code
  4. PhySense: Sensor Placement Optimization for Accurate Physics Sensing
    Yuezhou Ma, Haixu Wu, Hang Zhou, Huikun Weng, Jianmin Wang, Mingsheng Long#
    Conference on Neural Information Processing Systems (NeurIPS), 2025.
    Oral Paper (Top 0.3%)
    PDF Code
  5. Unisolver: PDE-Conditional Transformers Are Universal PDE Solvers
    Hang Zhou*, Yuezhou Ma*, Haixu Wu#, Haowen Wang, Mingsheng Long#
    International Conference on Machine Learning (ICML), 2025.
    PDF Code
  6. Exploring Accuracy Law for Deep Time Series Forecasters: An Empirical Study
    Yuxuan Wang*, Haixu Wu*, Yuezhou Ma, Yuchen Fang, Ziyi Zhang, Yong Liu, Shiyu Wang, Zhou Ye, Yang Xiang, Jianmin Wang, Mingsheng Long#
    arXiv preprint, 2025.
    PDF
  7. FlashBias: Fast Computation of Attention with Bias
    Haixu Wu, Minghao Guo, Yuezhou Ma, Yuanxu Sun, Jianmin Wang, Wojciech Matusik, Mingsheng Long#
    Conference on Neural Information Processing Systems (NeurIPS), 2025.
    PDF Code
  8. RoPINN: Region Optimized Physics-Informed Neural Networks
    Haixu Wu, Huakun Luo, Yuezhou Ma, Jianmin Wang, Mingsheng Long#
    Conference on Neural Information Processing Systems (NeurIPS), 2024.
    PDF Code
  9. HelmFluid: Learning Helmholtz Dynamics for Interpretable Fluid Prediction
    Lanxiang Xing*, Haixu Wu*, Yuezhou Ma, Jianmin Wang, Mingsheng Long#
    International Conference on Machine Learning (ICML), 2024.
    PDF Code

* Equal contribution. # Corresponding author.

Education

Honors & Awards

Professional Service

Reviewer

Invited Talks

Teaching Assistant

Service