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.
More from Research
- Snorkel's binary-gated GRPO lifts Qwen3.8-27B from 31.9% to 40.7% on OpenAI's GDPval — ajratner · 2026-11-21
- Artificial Analysis Launches Search API Benchmark Covering 26 Products Across 14 Providers — ArtificialAnlys · 2026-11-21
- The 250,000-page Riemann proof claim: when computational verification outpaces human comprehension — SydSteyerhart · 2026-11-21
- Genesis Molecular AI launches Ruby potency model, up to 1000x faster, open-sources training data — edunov · 2026-11-21
- 'All AI can do is plagiarize': model caught regurgitating a proof straight from The Book — moyix · 2026-11-21
- Experts gave AI 10% odds of cracking a Millennium Prize Problem by 2027 — two now claimed — theimposingshadow · 2026-11-21