Understanding and mitigating distribution shifts for universal machine learning interatomic potentials
We find common distribution shifts that pose challenges for universal machine learning interatomic potentials (MLIPs). We develop test-time refinement strategies that mitigate the shifts and provide insights into why MLIPs struggle to generalize.
Authors
- Aditi S. Krishnapriyan (ORCID: https://orcid.org/0000-0003-3472-6080)
- Tobias Kreiman
Institutions
- Berkeley College (US)
- University of California, Berkeley (US)
Publication Details
- Journal
- Digital Discovery
- Published
- 2025-12-04
- DOI
- https://doi.org/10.1039/d5dd00260e
- Citations
- 1
- Primary Topic
- Generative Adversarial Networks and Image Synthesis
- Type
- article
- Field-Weighted Citation Impact
- 1.28
Funders
- Toyota Research Institute
- National Energy Research Scientific Computing Center
- Office of Science
- Lawrence Berkeley National Laboratory