tracked author

Lei Bai (白磊)

Shanghai AI Laboratory Young Scientist and Fudan University dual-appointed researcher; connects the archived Entropy Mechanism paper with the ACL 2026 data-scarcity RL survey.

2 archived notes X: not-found Homepage

Related Notes

按论文归档时间排序，展示该作者在本站已经出现的材料。

归档 Jul 16, 2026

A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions

把 LLM 强化学习中的高成本外部监督与有限内部生成经验统一到 data、training、framework 三层九类干预点，并组织为一份覆盖 125 条文献记录的设计地图。

待审阅 2604.17312-rl-llm-data-scarcity-survey Reasoning RL Rollout Optimization Reward Modeling

归档 Jun 21, 2026

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

把 RLVR 训练能力上限关联到 policy entropy 消耗，并分析 advantage update 的熵动力学。

待审阅 2505.22617-entropy-mechanism-rl-reasoning-language-models Training Stability Reasoning RL RL Theory