SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence Paper • 2512.22334 • Published 13 days ago • 33
💧 LFM2.5 Collection Collection of Instruct, Base, and Japanese LFM2.5-1.2B models. • 19 items • Updated 3 days ago • 57
Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits Paper • 2512.20578 • Published 16 days ago • 65