We are a research group working on both core methods in machine learning and
artificial intelligence, as well as collaborative applications across science
and engineering. Some of the topics we're interested in include
- automatic differentiation [1, 2]
- Monte Carlo methods [3, 4]
- Bayesian inference [5, 6]
- ML-accelerated design and simulation [7, 8]
- group symmetry in machine learning architectures [9]
- materials science and chemistry [10, 11, 12, 13]
- computational fabrication [14, 15]
- generative modeling [16, 17]
- reinforcement learning and control [18, 19]
Recent Publications
- Mirramezani, M., Oktay, D., & Adams, R. P. (2024). A rapid and automated computational approach to the design of multistable soft actuators. Computer Physics Communicationsn.
[PDF]
bibtex/details
- Li, M., Callaway, F., Thompson, W., Adams, R. P., & Griffiths, T. (2023). Learning to learn functions. Cognitive Science, 47(4).
[PDF]
bibtex/details
- Adams, R. P., & Orbanz, P. (2023). Representing and Learning Functions Invariant Under Crystallographic Groups. ArXiv Preprint ArXiv:2306.05261.
[PDF]
bibtex/details
- Liu, S. (2023). Scalable and Interpretable Learning with Probabilistic Models for Knowledge Discovery [PhD thesis]. Princeton University.
[PDF]
bibtex/details
- Cai, D. (2023). Probabilistic Inference When the Model Is Wrong [PhD thesis]. Princeton University.
[PDF]
bibtex/details
Recent Blog Posts
Ari Seff · September 25, 2021
Vitruvion: A Generative Model of Parametric CAD Sketches
Geoffrey Roeder · September 28, 2020
Using 3D Printing to Develop Rapid-Response PPE Manufacturing
Ryan Adams · September 27, 2020
Video: Introduction to Convex Optimization
Ryan Adams · September 20, 2020
Video: Basics of Optimization
Ryan Adams · September 13, 2020
Video: Information Theory Basics
Current Collaborators
- Sigrid Adriaennsens
- Katia Bertoldi
- Abigail Doyle
- Elif Ertekin
- Tom Griffiths
- Peter Orbanz
- Peter Ramadge
- Szymon Rusinkiewicz
- Yee Whye Teh
- Eric Toberer
Funding
- National Science Foundation
- Siemens
- Templeton Foundation
- Princeton Catalyst Initiative
- Schmidt DataX
- Ansys