Weak-to-Strong Generalization via Direct On-Policy Distillation Paper • 2607.05394 • Published 23 days ago • 139
Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction Paper • 2606.29445 • Published Jun 28 • 28
GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots Paper • 2606.29705 • Published Jun 29 • 16
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe Paper • 2604.13016 • Published Apr 14 • 114