论文阅读库
当前重点
- Beyond the 80-20 Rule：High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
- DeepSeekMath-Pushing the Limits of Mathematical Reasoning in Open Language Models
- WavBench- Benchmarking Reasoning, Colloquialism, and Paralinguistics for End-to-End Spoken Dialogue Models