1d ago

MiroMind Unveils MOOSE-Star For Scalable LLM-Based Scientific Discovery

0
Original post

We post-train LLMs for math, for code, for instruction-following. Why not for scientific discovery? 🫎 MOOSE-Star (ICML 2026): the first scalable SFT recipe for discipline-agnostic scientific hypothesis discovery. By @Yang_zy223 & @LidongBing from MiroMind.

10:29 AM · May 18, 2026 View on X