NeurIPS workshop on Interpretability for Discovery set for Dec 12 in Atlanta

ChenhaoTan · x · 2026-11-20

A NeurIPS workshop titled "Interpretability for Discovery" will be held Dec 12 in Atlanta, exploring what scientific discoveries are hiding inside AI models. Speakers include Gasper Begus, kfrankelab, nkwang24, and jwuphysics, with spotlight talks, posters, a panel, and a post-workshop social sponsored by GoodfireAI. Organizers include boknilev, EkdeepL, YNikankin, ChenhaoTan, and amirtha255.

Related event: NeurIPS Atlanta to Host Workshop on Interpretability for Scientific Discovery(2 posts)→

Original post →

More from Research

Research channel →