Di Wu
Home

Di Wu

alt text 

I am a third-year Ph.D. student in the Applied Mathematics & Statistics, and Scientific Computation (AMSC) program at the University of Maryland, College Park. I am fortunate to be advised by Prof. Haizhao Yang. I also work closely with Prof. Ling Liang. I received my bachelor's and master's degrees in Computational Mathematics from Wuhan University, under the guidance of Prof. Yuling Jiao and Prof. Xiliang Lu. I also spent time as a research intern at JD Explore Academy, where I was mentored by Prof. Li Shen.

Current interests

  • Agentic mathematics and science

  • Uncertainty quantification

I am interested in how AI agents can support mathematical reasoning and scientific discovery, and how uncertainty can be quantified to inform reliable decisions. I welcome discussions with anyone interested in these topics.

My previous research focused on Bayesian statistics, optimization, and reinforcement learning.

e-mail: dwuwd 'at’ umd 'dot’ edu

Research [Google Scholar]

  • FARMS: A Verifiable Foundation for Automated Computational Science
    Di Wu, Ling Liang, Haizhao Yang
    arXiv preprint, 2026
    [arXiv] [Website]

  • SciΠvot: Benchmarking Principal-Investigator Judgment at Pivotal Moments of Scientific AutoResearch Agents
    Youran Sun, Xingyu Ren, Chugang Yi, Kejia Zhang, Di Wu, Yingkang Cao, Allen Zhou, Jianping Ye, Suying Liu, Jiaxuan Guo, Jianda Du, Weicheng Ye, Kecheng Liu, Hefan Zhang, Haixin Wang, Jie Xiao, Eric Yang, Haizhao Yang
    arXiv preprint, 2026
    [arXiv]

  • Beyond Expected Information Gain: Stable Bayesian Optimal Experimental Design with Integral Probability Metrics and Plug-and-Play Extensions
    Di Wu, Ling Liang, Haizhao Yang
    arXiv preprint, 2026
    [arXiv]

  • Randomized Subsystem Descent for Fermion-to-Qubit Mapping
    Gengzhi Yang, Di Wu, Haizhao Yang, Xiaodi Wu, Ji Liu
    Accepted to Journal of Chemical Theory and Computation, 2026
    [arXiv]

  • PINS: Proximal Iterations with Sparse Newton and Sinkhorn for Optimal Transport
    Di Wu, Ling Liang, Haizhao Yang
    arXiv preprint, 2025
    [arXiv]

  • Neural Network Approximation for Pessimistic Offline Reinforcement Learning
    Di Wu, Yuling Jiao, Li Shen, Haizhao Yang, Xiliang Lu
    Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2024
    [arXiv] [Published version]

Teaching

Teaching Assistant

University of Maryland, College Park
(leading discussion sections, holding office hours, and grading)

  • MATH 240: Introduction to Linear Algebra

  • STAT 400: Applied Probability and Statistics

  • STAT 426: Introduction to Data Science and Machine Learning

  • AMSC 460: Computational Methods

  • AMSC 660: Scientific Computing I

Earlier TA Experience

Wuhan University: Teaching assistant for graduate courses including Numerical Analysis, Statistical Computing, High Dimensional Data and Machine Learning, Theory and Algorithms of Machine Learning, and Advanced Engineering Mathematics.

National Tianyuan Mathematics Center: Teaching assistant for the summer school on ‘‘Mathematical Theory and Applications of Deep Learning’’.

Activities

Talks

  • Beyond Expected Information Gain: Stable Bayesian Optimal Experimental Design with Integral Probability Metrics and Plug-and-Play Extensions [Slide]
    SIAM Conference on Mathematics of Data Science, Salt Lake City, November 2026
    2026 INFORMS Annual Meeting, San Francisco, November 2026
    Sayas Numerics Day (formerly DelMar Numerics Day), May 2026

  • PINS: Proximal Iterations with Sparse Newton and Sinkhorn for Optimal Transport [Slide]
    Applied Math Seminar, George Washington University, February 2026

  • Neural Network Approximation for Pessimistic Offline Reinforcement Learning [Slide]
    School of Mathematics and Statistics, Wuhan University, March 2024

Professional Services & Activities

  • Review Panelist, NASA Research Proposal Review

  • Co-organizer, Minisymposium on Optimal Transport, SIAM MDS 2026 (link)

  • Reviewer: NeurIPS; Frontiers in Applied Mathematics

Awards & Honors

  • Mark E. Lachtman Award, University of Maryland, 2026

  • Dean's Fellowship, University of Maryland, 2025, 2026

Earlier Awards & Honors

  • Lei Jun Educational Fund (around 5,000 USD), Wuhan University

  • First-Class Scholarship (Undergraduate & Graduate), Wuhan University

  • First Prize, Contemporary Undergraduate Mathematical Contest in Modeling (Team Leader), CSIAM

  • Outstanding Graduate, Wuhan University

  • Merit Student (3 times), Wuhan University

  • First Prize, National High School Mathematics Competition

  • First Prize, National High School Physics Competition

Last updated: November 2026