|
Nate Gruver, PhD
I am a machine learning researcher focusing on generative modeling and scientific discovery.
I completed my PhD at NYU Courant advised by
Andrew Gordon Wilson and working closely with
Kyunghyun Cho. I received a BS/MS in computer science from Stanford University, where I worked with
Stefano Ermon,
Mykel Kochenderfer, and
Chris Piech.
During my training, I had several internships in industry, including generative modeling of crystals and proteins at
FAIR, driver behaviour modeling at
Waymo, and applying ML to kernel virtual machines at Google Cloud.
Email  / 
Twitter  / 
Google Scholar
|
Research
My graduate work on deep learning and generative modeling had the following themes:
- Understanding the relationship between large-scale pretraining and inductive biases
[1,
2]
- Generative modeling for protein and materials design
[3,
4]
- Combining generative models with uncertainty estimates
[5,
3]
|
Publications
Large Language Models Must Be Taught to Know What They Don't Know
Sanyam Kapoor*,
Nate Gruver*,
Manley Roberts,
Katherine Collins,
Arka Pal,
Umang Bhatt,
Adrian Weller,
Samuel Dooley,
Micah Goldblum,
Andrew Gordon Wilson,
NeurIPS, 2024 (Poster)
|
|