RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning Paper • 2609.20784 • Published 16 days ago • 57
ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks Paper • 2609.18805 • Published 17 days ago • 67
Continual Learning Mechanisms Compose for Long-Horizon Memorization Paper • 2609.06986 • Published 26 days ago • 376
Kalman Delta Networks: Uncertainty-aware Associative Memory Paper • 2609.07816 • Published 26 days ago • 29
microsoft/VibeVoice-ASR-Streaming-7B Automatic Speech Recognition • 9B • Updated 30 days ago • 7.05k • 251