Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training Paper • 2609.07108 • Published 10 days ago • 35
Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling Paper • 2608.30821 • Published 17 days ago • 122
EgoSteer: A Full-Stack System Towards Steerable Dexterous Manipulation from Egocentric Videos Paper • 2607.09701 • Published Jun 21 • 17
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning Paper • 2606.29526 • Published Jun 28 • 171