Minerva: Hie lab's data-mining framework for scientific discovery
BrianHie · x · 2026-09-23
Brian Hie highlights a completed research project by @DavidLi and @garykbrixi: a scientific data-mining effort whose framework, Minerva, is now available as a preprint.
- Advisors: Michael Grinstein (mfgrp) and Brian Hie supported the project
- Co-authors include Alex Kim, Mateus Fiamenghi, Carolyn Driscoll, Simone Alma, Natalia Ivanova, Nikos Kyrpides, Karl Deisseroth, and Max Wilkinson
- The authors say they're excited to see what others find with Minerva
The threads by Li and Brixi contain the paper details; this is an AI-for-science framework intended to help researchers mine scientific data for new discoveries.
More from Research
- EPFL quantum CNN learns digits from 10 samples where a 45-param classical CNN stays at chance — PlisSergey · 2026-09-23
- New paper reframes score distillation as distribution matching, explains SDS mode collapse — burny_tech · 2026-09-23
- Cambridge publishes open-access 458-page book on nonparametric and high-dim stats — FrnkNlsn · 2026-09-23
- Reinforce-Ada: adaptive sampling for RLVR recovers lost signals, 2x faster convergence — burny_tech · 2026-09-23
- Paper: Transformers do have world models — failures trace to feature interference — burny_tech · 2026-09-23
- Paper suggests transformers can't learn loop-closure in world modeling — burny_tech · 2026-09-23