Song Yu

Corresponding Author

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Reasoning & Chain-of-Thought (1)RLHF & Preference Learning (1)Training Efficiency & Optimization (1)

Frequent co-authors

Li Li (1)

Papers (1)

Mar 30, 2026

Corresponding Author2d ago

ERPO: Token-Level Entropy-Regulated Policy Optimization for Large Reasoning Models

LLMs can reason more accurately and concisely when RL is guided by token-level entropy, pinpointing and exploring "forks in the road" during the reasoning process.

Song Yu, Li Li

Reasoning & Chain-of-Thought RLHF & Preference Learning Training Efficiency & Optimization

Search

Song Yu

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)