3 10 2

qingyang zhang

qingyangzhang

https://qingyangzhang.github.io

AI & ML interests

LLM Reasoning

Recent Activity

updated a dataset about 3 hours ago

qingyangzhang/SCP-116K-formatted

published a dataset about 3 hours ago

qingyangzhang/SCP-116K-formatted

updated a model about 4 hours ago

qingyangzhang/Qwen2.5-1.5B-EMPO-NM-COT-20K

View all activity

Organizations

None yet

qingyangzhang's activity

upvoted a paper 11 days ago

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

Paper • 2506.01939 • Published 12 days ago • 150

upvoted a paper 12 days ago

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

Paper • 2505.24864 • Published 15 days ago • 121

upvoted a paper 15 days ago

Sherlock: Self-Correcting Reasoning in Vision-Language Models

Paper • 2505.22651 • Published 17 days ago • 50

upvoted a paper 16 days ago

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

Paper • 2505.22617 • Published 17 days ago • 120

upvoted a paper 17 days ago

The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning

Paper • 2505.15134 • Published 24 days ago • 6

upvoted a paper 18 days ago

Learning to Reason without External Rewards

Paper • 2505.19590 • Published 19 days ago • 27

upvoted a paper 22 days ago

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

Paper • 2505.12346 • Published 27 days ago • 19

upvoted an article 27 days ago

Article

Train Reasoning Models without External Supervision

•

27 days ago

• 1

upvoted a paper 27 days ago

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

Paper • 2504.05812 • Published Apr 8 • 2

upvoted a collection 27 days ago

EMPO

Collection

19 items • Updated 10 days ago • 1