Peihan Liu

Peihan Liu

CS PhD student, Columbia · peihanliu@cs.columbia.edu · Scholar · X

I'm a second-year CS PhD student in the Columbia theory group, advised by Rachel Cummings and Roxana Geambasu. I work on trustworthy machine learning — particularly the theoretical and empirical foundations of privacy, fairness, and modern machine learning.

Previously, I received my M.Eng. in CSE from Harvard, where I worked on algorithmic fairness with Cynthia Dwork and Juan Perdomo. Before that, I earned B.S. degrees in Mathematics and Statistics, with high honors and high distinction, from the University of Michigan, where I worked with Martin Strauss, Ranjan Pal, Shizhang Li, and Nuh Aydin on algorithmic fairness, homological algebra, and algebraic coding theory.

Beyond research, I walk my dog and (used to) play poker.

Publications

See Google Scholar for the up-to-date list.

  1. ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?
    Peihan Liu, Lucas Rosenblatt, Weiwei Kong, Natalia Ponomareva, Gautam Kamath, Rachel Cummings, Roxana Geambasu, Yu Gan, Lillian Tsai, Alex Bie
    preprint, 2026.
    TPDP 2026 (oral) · COLM 2026 Workshop on Responsibly Enabling Data for Foundation Models (oral)
    [Blog] [arXiv] [code] [dataset]
  2. Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback
    Ved Sriraman, Peihan Liu, Daniel Hsu, Adam Block
    NeurIPS, 2026 (spotlight).
    [Blog] [arXiv] [code]
  3. Adaptive Target-Charging with Privacy Filters and Individual Accounting
    Peihan Liu, Alison Caulfield, Mark Chen, Rachel Cummings, Roxana Geambasu, Mathias Lécuyer, Pierre Tholoniat
    NeurIPS, 2026.
  4. Privately Fine-Tuned LLMs Preserve Temporal Dynamics in Tabular Data
    Lucas Rosenblatt, Peihan Liu, Ryan McKenna, Natalia Ponomareva
    ICML, 2026. [arXiv] [code]
  5. Convex Relaxation for Solving Large-Margin Classifiers in Hyperbolic Space
    Sheng Yang, Peihan Liu, Cengiz Pehlevan
    TMLR, 2024. [arXiv] [code]
  6. Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training
    Alyssa Huang, Peihan Liu, Ryumei Nakada, Linjun Zhang, Wanrong Zhang
    preprint, 2024. [arXiv]

Experience

Service

Blog