avatar

Thomas P. Zeng（曾沛青）

Ph.D. Student, Computer Science
University of Wisconsin-Madison
tpzeng (at) wisc.edu


About Me

I am a 3rd Year Computer Science Ph.D. student at University of Wisconsin-Madison, and very fortunate to be advised by Professor Kangwook Lee. Prior to Madison, I received my B.A. in Mathematics and Computer Science from Carleton College. Currently, I’m interested in LLMs and obtaining a theoretically grounded understanding of what they can do.

Papers

  1. A Cramér-von Mises Approach to Incentivizing Truthful Data Sharing
    Alex Clinton, Thomas Zeng, Yiding Chen, Xiaojin Zhu, Kirthevasan Kandasamy
    Thirty-Ninth Annual Conference on Neural Information Processing Systems, 2025.
    PDF

  2. VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data
    Thomas Zeng, Shuibai Zhang, Shutong Wu, Christian Classen, Daewon Chae, Ethan Ewer, Minjae Lee, Heeju Kim, Wonjun Kang, Jackson Kunde, Ying Fan, Jungtaek Kim, Hyung Il Koo, Kannan Ramchandran, Dimitris Papailiopoulos, Kangwook Lee
    Forty-Second International Conference on Machine Learning (ICML), 2025.
    PDF Code (oral)

  3. When the Universe is Too Big: Bounding Consideration Probabilities for Plackett-Luce Rankings
    Ben Aoki-Sherwood, Catherine Bregou, David Liben-Nowell, Kiran Tomlinson, Thomas Zeng*
    The 28th International Conference on Artificial Intelligence and Statistics (AISTATS), 2025.
    PDF Code (*authors in alphabetical order)

  4. ENTP: Encoder-only Next Token Prediction
    Ethan Ewer*, Daewon Chae*, Thomas Zeng*, Jinkyu Kim, Kangwook Lee
    arXiv, 2024.
    PDF Code (*equal contribution)

  5. A model for horizontally restricted random square-tiled surfaces
    Nick Fitzhugh, Aaron Schondorf, Sunrose Shrestha, Sebastian Vander Ploeg Fallon, Thomas Zeng
    arXiv, 2024.
    PDF

  6. No nodule left behind: evaluating lung nodule malignancy classification with different stratification schemes
    Thomas Zeng, Elias Furst, Yiyang Wang, Roselyne Tchoua, Jacob Furst, Daniela Raicu
    Medical Imaging 2023: Computer-Aided Diagnosis (SPIE MI), 2023.
    PDF Code


Powered by Jekyll and Minimal Light theme.