orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF Text Generation • 27B • Updated 4 days ago • 7.19k • 200
Selecting Diverse SFT Traces Improves Post-RL Generalization Paper • 2609.33780 • Published 4 days ago • 32
Preference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement Paper • 2609.34528 • Published 3 days ago • 4
CaptchaArena: A Large-Scale, Fine-Grained Dataset for Training Computer-Use Agents on Interactive CAPTCHAs Paper • 2609.31957 • Published 5 days ago • 5
What Makes Recurrence Effective in Looped Language Models? Paper • 2609.36636 • Published 2 days ago • 10
Scaling Properties of Same-Family On-Policy Distillation Paper • 2609.32722 • Published 5 days ago • 220