Meetings
Meetings are open to the public and we encourage anyone to join: beginners, practitioners, researchers — all are welcome.
Current schedule
| Term | Fall 2026 |
|---|---|
| Day | Most weeks on Thursday |
| Time | 7:00 pm – 8:00 pm |
| Room | TBD |
| Online | Join on Zoom |
Let us know if you would like to meet in person and we will find a room.
Next meeting
Project check in and Reading Group: Beyond Perturbation Robustness: Biological Equivalence in Genomic Foundation Models — Thursday, October 22, 7:00 pm
What happens at a meeting
Our meetings generally revolve around:
- Project updates from lab members
- Open discussion and problem-solving
- Short tutorials on tools and techniques
- Coverage of the latest research in our fields of study
Reading Groups
Throughout the semester, we host reading groups to explore current developments in the industry.
Why should you attend?
- Discover topics you are interested in and want to work on.
- Form ideas for research projects that you’re passionate about.
- Practice your skills in presenting and speaking about research.
This week’s paper
Beyond Perturbation Robustness: Biological Equivalence in Genomic Foundation Models — Padmaja Mohanty, WiML Workshop at NeurIPS 2026. Presented by Padmaja Mohanty.
Different DNA sequences can encode the same protein. This paper asks whether genomic foundation models recognize that, and whether their learned representations capture the biological meaning rather than just similarity in the DNA. Mohanty tests four models on 91 human coding sequences and finds that two of them do no better than chance: a model that barely changes under DNA edits has not necessarily learned the biology.
About the presenter
Padmaja Mohanty is a Master’s student in Computer Science at the University of San Francisco working at the intersection of AI, biology and healthcare. Her research focuses on understanding what AI models learn about biological systems, how they process information and whether their representations capture meaningful biological relationships and mechanisms. Two of her projects on genomic foundation models were accepted at NeurIPS 2026 workshops: a mechanistic interpretability study of how SpliceBERT processes RNA splicing signals, and this week’s paper.
Questions?
Contact the lab manager and they’ll point you in the right direction.