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

  1. 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
  2. Novick, A., Cai, D., Nguyen, Q., Garnett, R., Adams, R. P., & Toberer, E. (2024). Probabilistic Prediction of Material Stability: Integrating Convex Hulls into Active Learning. ArXiv Preprint ArXiv:2402.15582. [PDF] bibtex/details
  3. Bordiga, G., Medina, E., Jafarzadeh, S., Boesch, C., Adams, R. P., Tournat, V., & Bertoldi, K. (2024). Automated discovery of reprogrammable nonlinear dynamic metamaterials. ArXiv Preprint ArXiv:2403.08078. [PDF] bibtex/details
  4. Liu, S., Ramadge, P. J., & Adams, R. P. (2024). Generative Marginalization Models. Proceedings of the 41st International Conference on Machine Learning (ICML). [PDF] bibtex/details
  5. Pastrana, R., Oktay, D., Adams, R. P., & Adriaenssens, S. (2023). JAX FDM: A differentiable solver for inverse form-finding. ArXiv Preprint ArXiv:2307.12407. [PDF] bibtex/details

Recent Blog Posts

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