Divya Nori

I am a PhD student in Computer Science at Stanford, currently rotating with Prof. Brian Hie at the Arc Institute. My research explores what a world model for biology might look like - in particular, how we can improve AI models to better represent and design biological systems across scales, from molecules to genomes. Some of the questions I am currently interested in are:

• Along which axes should we scale models to better understand biology?
• How can models efficiently process vast biological context to make accurate predictions in new settings?
• When are foundation models useful versus task-specific models in the biological sciences?
• How can we represent molecular function precisely enough to achieve truly programmable design?

I aim to deploy such models to unlock unprecedented advances in health and disease. At the same time, improving biological understanding in AI models raises critical biosecurity concerns. This motivates my work as a founding member of technical staff at Valthos, where we build AI and software infrastructure to rapidly counter emerging biological threats.

Outside of research, I am a co-organizer of the ML Protein Engineering Seminar Series.

Feel free to reach out at dnori [at] stanford.edu

Past

Prior to my PhD, I completed my SB and MEng in EECS at MIT where I became interested in generative biology. My first undergraduate research experience, advised by Prof. Connor Coley, piqued my interest in algorithms for molecular design. I then spent three years at the Broad Institute’s Eric and Wendy Schmidt Center, where I was fortunate to be advised by Profs. Wengong Jin and Caroline Uhler, developing generative methods for RNA and protein design.

Outside of academia, I gained ML engineering experience through internships at D. E. Shaw Research, Absci, and Microsoft Research.