Stephen Z. Lu

prof_pic.jpg

Hi! My name is Stephen and I am a first year PhD student at UC Berkeley supervised by Prof. Yun S. Song. I completed my undergraduate studies at McGill University in my hometown of Montreal, Canada 🇨🇦.

My research focuses on developing computational methods to navigate the energy and fitness landscapes that govern molecular function and evolution.

More concretely, my current research projects include:

  • Building deep models of protein sequence evolution with applications to design and optimization
  • Exploring methods to accelerate atomistic simulations and approximate quantum mechanical properties

I have previously worked on:

  • Small molecule generative models for phenotypic drug discovery ([1], [2])
  • Flow-based generative models for protein conformational sampling ([3], [4])
  • Benchmarking LLM agents on scientific discovery tasks in biology ([5])

In my free time, I love playing pickup basketball, composing mostly funky (and a few serious) songs on the piano, discovering new hiking trails (my profile pic above was taken atop Mt. Wakakusa in Nara, Japan), and spending time with my family and friends.

Feel free to reach out stephen.lu@berkeley.edu if you’d like to chat about research or meet for coffee in the Bay Area!

selected publications

2025

  1. scigym.png
    Measuring Scientific Capabilities of Language Models with a Systems Biology Dry Lab
    Haonan Duan*, Stephen Zhewen Lu*, Caitlin Fiona Harrigan, and 5 more authors
    In NeurIPS Datasets and Benchmarks Track, 2025
  2. eba.png
    Aligning Protein Conformation Ensemble Generation with Physical Feedback
    Jiarui Lu, Xiaoyin Chen, Stephen Zhewen Lu, and 4 more authors
    In ICML, 2025
  3. slm.png
    Structure Language Models for Protein Conformation Generation
    Jiarui Lu, Xiaoyin Chen, Stephen Zhewen Lu, and 4 more authors
    In ICLR, 2025

2024

  1. omics-gfn.jpg
    Cell morphology-guided small molecule generation with gflownets
    Stephen Zhewen Lu, Ziqing Lu, Ehsan Hajiramezanali, and 4 more authors
    In ICML Workshop SPIGM, 2024