Weiyi He (贺维易)

Ph.D. candidate at MSU

weiyi_full.jpg

Hello! I’m Weiyi He, a third-year Ph.D. student at Michigan State University (MSU), dual-majoring in Statistics and Computer Science. I am fortunate to be advised by Prof. Yue Xing and Prof. Jiliang Tang. Prior to MSU, I received my B.S. in Statistics from University of Science and Technology of China (USTC).

My research focuses on Trustworthy AI, Adversarial Training, and Statistical theory for Large Language Models (LLMs). I was also an Applied Scientist Intern at Amazon AGI, where I worked with Giuseppe Vietri and Dmitriy Bespalov on robustness in large language models. I am dedicated to understanding the theoretical foundations of modern AI systems to enhance their reliability and security.

*Bold indicates first or co-first authorship.

News

Jun 2026 I’ll be joining Amazon AGI this summer as an Applied Scientist Intern in Arlington, VA!
May 2026 I will present a poster at AISTATS 2026 in Tangier, Morocco!
Jan 2026 One paper is accepted to AISTATS 2026!
Sep 2025 I have passed the preliminary exams in both Statistics and Probability!
Apr 2025 One paper is accepted to ACL 2025!

Selected Publications

2026

  1. arXiv
    efficient-surrogate-analysis.png
    Weiyi He*, Yuping Lin, Tang Jiliang, and Yue Xing
    arXiv preprint arXiv:2607.28959, 2026
  2. AISTATS
    aistats-generalization-gap.png
    Weiyi He* and Yue Xing
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2026

2025

  1. ACL
    privacy-memory-attack.png
    Bo Wang, Weiyi He, Shenglai Zeng, Zhen Xiang, Yue Xing, Jiliang Tang, and Pengfei He
    In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025