NeurIPS workshop on interpretability for scientific discovery, Dec 12

niloofar_mire · x · 2026-11-20

The "Interpretability for Discovery" workshop runs Dec 12 at NeurIPS in Atlanta, exploring scientific discoveries hidden inside AI models, with spotlight talks on interpretability in astronomy and astro foundation models from speakers including begusgasper and jwuphysics, plus posters, a panel, and a post-workshop social. Sponsored by GoodfireAI; organized by boknilev, ChenhaoTan, and others.

Related event: NeurIPS to Host "Interpretability for Discovery" Workshop in Atlanta in December(5 posts)→

Original post →

More from Research

Research channel →