SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence Paper • 2512.22334 • Published 14 days ago • 34
SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence Paper • 2512.22334 • Published 14 days ago • 34
Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics Paper • 2512.12602 • Published 27 days ago • 42
P1: Mastering Physics Olympiads with Reinforcement Learning Paper • 2511.13612 • Published Nov 17, 2025 • 134
Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning Paper • 2510.25992 • Published Oct 29, 2025 • 45
Glyph: Scaling Context Windows via Visual-Text Compression Paper • 2510.17800 • Published Oct 20, 2025 • 67
DeepAnalyze: Agentic Large Language Models for Autonomous Data Science Paper • 2510.16872 • Published Oct 19, 2025 • 106