avatar

Peter Pao-Huang

Ph.D. Student
Stanford University
peterph (at) stanford.edu


About Me

I am a Computer Science Ph.D. student at Stanford University, co-advised by Stefano Ermon and Xiaojie Qiu. My research aims to develop principled generative modeling methods to understand, treat, and reverse disease. I am currently interested in modeling Perturb-seq data.

Previously, I obtained my B.S. in Computer Science from the University of Illinois at Urbana-Champaign, advised by Vikram Adve (UIUC), Bonnie Berger (MIT), and Morgan Levine (Altos Labs).

Publications

  1. In Submission
    Generative Modeling with Flux Matching
    Peter Pao-Huang, Xiaojie Qiu, Stefano Ermon
    In Submission
    PDF Code

  2. ICML 2025
    Geometric Generative Modeling with Noise-Conditioned Graph Networks
    Peter Pao-Huang, Mitchell Black, Xiaojie Qiu
    International Conference on Machine Learning 2025
    PDF Code

  3. NeurIPS GenBio 2023
    Scalable Multimer Structure Prediction using Diffusion Models
    Peter Pao-Huang, Bowen Jing, Bonnie Berger
    NeurIPS 2023 Generative AI and Biology Workshop
    PDF

  4. ICLR MLDD 2023
    EigenFold: Generative Protein Structure Prediction with Diffusion Models
    Bowen Jing, Ezra Erives, Peter Pao-Huang, Gabriele Corso, Bonnie Berger, Tommi Jaakkola
    Machine Learning for Drug Discovery Workshop at International Conference on Learning Representations 2023
    PDF Code

  5. MLSys 2023
    ApproxCaliper: A Programmable Framework for Application-aware Neural Network Optimization
    Yifan Zhao, Hashim Sharif, Peter Pao-Huang, Vatsin Shah, Arun Narenthiran Sivakumar, Mateus Valverde Gasparino, Abdulrahman Mahmoud, Nathan Zhao, Sarita Adve, Girish Chowdhary, Sasa Misailovic, Vikram Adve
    Proceedings of Machine Learning and Systems 2023
    PDF Code