InfraRSI: Harnessing Recursive Self-Improvement for Training Infrastructure Paper • 2611.11558 • Published 3 days ago • 20
SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments Paper • 2610.12611 • Published Oct 8 • 84
CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements Paper • 2611.03126 • Published 9 days ago • 51
xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic Text Generation • 9B • Updated 3 days ago • 14.4k • 1.27k
Candidate for main ai(35B A3B class) Collection 32GB CPUs(+ little GPUs)の環境で現実的に動かせるモデルのコレクション 時間が確保出来たら大規模なcoding agent benchmarkを測定します • 18 items • Updated 4 days ago • 1
Infatoshi/DeepSeek-V4.1-Flash-1017-MXFP4-uncensored Text Generation • 763B • Updated 23 days ago • 2.13k • 55
OBLITERATUS/DeepSeek-V4.1-Flash-1017-obliterated Text Generation • 755B • Updated 12 days ago • 8.35k • 284