D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI Paper • 2510.05684 • Published Oct 7 • 141
Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought Paper • 2510.04230 • Published Oct 5 • 26
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model? Paper • 2504.13837 • Published Apr 18 • 138