Scaling Properties of Same-Family On-Policy Distillation Paper • 2609.32722 • Published 5 days ago • 210
Same Bytes, Different Authority: Reserved-Token Representations in Chat-Template Prompt Injection Paper • 2609.35932 • Published 3 days ago • 7
Where the Model Changes Its Mind: Hindsight-Divergence Localization for Efficient Reinforcement Learning with Verifiable Rewards Paper • 2609.36864 • Published 2 days ago • 9
Selecting The Most Informative Tokens in Natural Language Autoencoders Paper • 2609.37040 • Published 2 days ago • 12
LongLive-Plug: Once-for-All Distillation for Video Generation Paper • 2609.38154 • Published 2 days ago • 25