On-Policy Distillation Teaches New Skills but Not New Knowledge Paper • 2610.09639 • Published 5 days ago • 6
Mechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid Position Paper • 2610.10114 • Published 5 days ago • 31
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published 25 days ago • 228
Continual Learning Mechanisms Compose for Long-Horizon Memorization Paper • 2609.06986 • Published Sep 7 • 376
EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents Paper • 2609.05903 • Published Sep 5 • 65