3 10 2

qingyang zhang

qingyangzhang

https://qingyangzhang.github.io

AI & ML interests

LLM Reasoning

Recent Activity

updated a collection 4 days ago

EMPO

updated a collection 4 days ago

EMPO

updated a collection 4 days ago

EMPO

View all activity

Organizations

None yet

qingyangzhang's activity

upvoted a paper 5 days ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published 5 days ago • 131

upvoted a paper 6 days ago

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

Paper • 2505.24864 • Published 8 days ago • 115

upvoted a paper 9 days ago

Sherlock: Self-Correcting Reasoning in Vision-Language Models

Paper • 2505.22651 • Published 10 days ago • 50

upvoted a paper 10 days ago

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

Paper • 2505.22617 • Published 10 days ago • 116

upvoted a paper 11 days ago

The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning

Paper • 2505.15134 • Published 18 days ago • 6

upvoted a paper 12 days ago

Learning to Reason without External Rewards

Paper • 2505.19590 • Published 13 days ago • 26

upvoted a paper 16 days ago

SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization

Paper • 2505.12346 • Published 21 days ago • 19

upvoted an article 21 days ago

Article

Train Reasoning Models without External Supervision

•

21 days ago

• 1

upvoted a paper 21 days ago

Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization

Paper • 2504.05812 • Published Apr 8 • 2

upvoted a collection 21 days ago

EMPO

Collection

19 items • Updated 4 days ago • 1