Thinking Inertia: LLMs Keep Thinking When Told Not To Paper • 2610.11765 • Published 12 days ago • 250
nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 Image-Text-to-Text • 27B • Updated about 21 hours ago • 290k • 444
From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation Paper • 2610.02179 • Published 19 days ago • 21
Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents Paper • 2609.17653 • Published Sep 15 • 45
Gaze as Evidence for Common Grounding: A Cross-Corpus Analysis of MapTask and MUNDEX Paper • 2609.18011 • Published Sep 16 • 30
The Missing Temporal Link: Temporal Context Routing for Script-Driven Audio-Video Generation Paper • 2609.02367 • Published Sep 2 • 38
Rethinking On-Policy Distillation of Large Language Models II: One Training Example Paper • 2609.04172 • Published Sep 3 • 105
HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF Image-Text-to-Text • 2B • Updated Aug 17 • 2.36M • 1.92k