EPFL's GOLLuM turns AI uncertainty into a training signal, cutting lab trials by 40%

MacrinePhD · x · 2026-09-03

Researchers at EPFL built GOLLuM, a framework combining LLMs with Gaussian processes to turn uncertainty into a training signal. By learning from 'doubt,' it maps experimental recipes faster and matches traditional methods using 40% fewer lab trials, targeting AI-optimized scientific discovery.

Related event: EPFL's GOLLuM Teaches AI to Learn from Doubt(2 posts)→

Original post →

More from Research

Research channel →