Daily Paper | Aug 11, 2025
2025-08-11
Daily Paper
- 1. On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification
- 2. R-Zero: Self-Evolving Reasoning LLM from Zero Data
- 3. GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
- 4. Learning to Reason for Factuality
- 5. Self-Questioning Language Models
- 6. Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation
- 7. Uni-cot: Towards Unified Chain-of-Thought Reasoning Across Text and Vision
本文最后更新于 天前，文中所描述的信息可能已发生改变