UCSB team wins $1M NSF grant to build AI that uncovers higher-order interactions in complex systems
ninamiolane · x · 2026-10-13
Four UC Santa Barbara researchers (Nina Miolane, Haewon Jeong, Yao Qin, and Sanjukta Krishnagopal) received a $1 million NSF award to develop AI methods that discover the laws governing complex systems — the first federal grant for UCSB's Real AI initiative launched this year.
The problem: most current AI-for-science approaches model only pairwise interactions (two atoms, two brain regions, two stars), while real systems exhibit higher-order interactions — groups of molecules, planets, or people creating emergent phenomena no pair could produce independently. The team aims to build models that capture overlapping multi-component interactions across scales and over time.
Motivation, per Miolane: Newton wrote the equations of mechanics, but fields like neuroscience still lack known "beautiful laws" — many scientific laws remain to be discovered. Jeong notes LLMs answer questions well yet remain weak at predicting whole-system behavior, a major gap this work targets.
Related event: UCSB Team Wins $1M NSF Grant for AI on Higher-Order Interactions(2 posts)→
More from Research
- Label-free minibatch OT coupling beats conditional OT, hits 1.91 FID on ImageNet-256 — AlexanderTong7 · 2026-10-13
- EXL details GNN fraud detection system with 27-33% detection gains — AI Engineer · 2026-10-13
- RTNav: open-source modular asynchronous agent for real-time zero-shot object navigation — rsasaki0109 · 2026-10-13
- AI-CFD benchmark culture: a mesh-free solver takes a cow to Mach 2 — burhop · 2026-10-13
- The Implicit Curriculum Hypothesis wins COLM outstanding paper award, powered by NSF public compute — IanArawjo · 2026-10-13
- Computational biology shifts as AI builds 'better predictors' in under a day — jmschreiber91 · 2026-10-13