StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling Paper • 2608.15089 • Published 18 days ago • 445
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources Paper • 2606.29538 • Published Jul 16 • 145
GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF Text Generation • 1B • Updated Jul 13 • 332k • 328
Progressive Residual Warmup for Language Model Pretraining Paper • 2603.05369 • Published Mar 5 • 36