avatar

Fred Zhangzhi Peng

Ph.D. Student
Duke University
zhangzhi.peng@duke.edu


About Me

Hey there! I’m Fred, a third-year Ph.D. student at Duke University. I have broad interests in machine learning and its applications in scientific problems. I work with Anru on statistical machine learning, Alex on generative models, Chris on ML4Bio. Previously, I worked with Pranam on protein design when he was at Duke. In addition, I have wonderful collaborators, Chengtong and Zack, who have taught me a great deal about proteins and probabilities. My research aims to scale up the math on GPUs and see what wonderful things emerge.

I love coding and science. At the end of the day, what makes me proud isn’t necessarily publishing a paper. It’s making solid contributions that actually move the field forward — whether that’s a tool, a model, an equation, or a line of code that makes your life easier. I believe science should be accessible to everyone, and open-source is how I try to make that real - peep the goods on my GitHub.

I’m betting my 2026 on normalizing flows.

I keep reminding myself this:

A figure showing that paper quality has little effect until work becomes creative, original, and good, at which point impact rises sharply.

Long-term problems I’m pursuing:

News

Publications

    Transparency and reproducibility are important to me. I ensure open code accompanying my first-author publications. Below are selected papers. Please refer to my Google Scholar for complete publications.
  1. ICLR2026, Oral
    Planner Aware Path Learning in Diffusion Language Models Training
    Fred Zhangzhi Peng, Zachary Bezemek, Jarrid Rector-Brooks, Shuibai Zhang, Anru R. Zhang, Michael Bronstein, Avishek Joey Bose, Alexander Tong
    ICLR2026, Oral (top 1%)
    PDF Code

  2. Open-dLLM: Open Diffusion Large Language Model
    Fred Zhangzhi Peng, Shuibai Zhang, Alexander Tong
    Code Blog

  3. DeLTa@ICLR2025
    Path Planning for Masked Diffusion Model Sampling
    Fred Zhangzhi Peng, Zachary Bezemek, Sawan Patel, Jarrid Rector-Brooks, Sherwood Yao, Avishek Joey Bose, Alexander Tong, Pranam Chatterjee
    DeLTa@ICLR2025 Outstanding Paper Award, and rejected by ICML, NIPS2025,ICLR2026
    PDF Code Slides Video

  4. ICML24
    Proteus: Exploring Protein Structure Generation for Enhanced Designability and Efficiency
    Chentong Wang, Yannan Qu, Zhangzhi Peng, Yukai Wang, Hongli Zhu, Dachuan Chen, Longxing Cao
    ICML24
    PDF Code

  5. Nature Methods
    PTM-Mamba: A PTM-Aware Protein Language Model with Bidirectional Gated Mamba Blocks
    Fred Zhangzhi Peng, Chentong Wang, Tong Chen, Benjamin Schussheim, Sophia Vincoff & Pranam Chatterjee
    Nature Methods
    PDF Code Video

Services

Conference Reviewers

NIPS 2025, KDD 2025, ICLR 2025

Journal Reviewers

Misc