Stephen Z. Lu

Hey there, welcome to my blog! My name is Stephen and I am a first year PhD student at UC Berkeley supervised by Prof. Yun S. Song.
I am broadly interested in developing data-driven methods to model biomolecular systems — with a focus on protein dynamics and evolution.
More concretely, my current research directions include:
- Devising novel methods for molecular design and optimization ([1])
- Evolution-informed representation learning for proteins and DNA
- Generative modeling of protein dynamics ([2], [3])
I have previously been:
- Research intern at:
- BigHat Biosciences — working on antibody optimization
- Mila — working on 2D molecule generation with GFlowNets
- Koziarski Lab — working on Bayesian optimization for synthesizable molecule hit discovery
- Co-founding engineer at Hero AI — working on clinical automation software
- Selected as an 8VC Fellow
- Selected as a Schulich Scholar
- Silver medallist at the ‘19 Canada Wide Science Fair
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
- Measuring Scientific Capabilities of Language Models with a Systems Biology Dry LabarXiv preprint arXiv:2507.02083, 2025
- Aligning Protein Conformation Ensemble Generation with Physical FeedbackIn ICML, 2025
- Structure Language Models for Protein Conformation GenerationIn ICLR, 2025
2024
- Cell morphology-guided small molecule generation with gflownetsIn ICML Workshop SPIGM, 2024