qingyang zhang

qingyangzhang's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset 25 days ago

qingyangzhang/DeepMath-103K-formatted

Viewer • Updated 25 days ago • 103k • 99

published a dataset 25 days ago

qingyangzhang/DeepMath-103K-formatted

Viewer • Updated 25 days ago • 103k • 99

updated a model 28 days ago

qingyangzhang/Qwen2.5-1.5B-EMPO-NM-COT-20K-0614

2B • Updated 28 days ago • 3

updated a dataset 28 days ago

qingyangzhang/numina_math_20K_formatted

Viewer • Updated 28 days ago • 20k • 114

published a dataset 28 days ago

qingyangzhang/numina_math_20K_formatted

Viewer • Updated 28 days ago • 20k • 114

published a model 28 days ago

qingyangzhang/Qwen2.5-1.5B-EMPO-NM-COT-20K-0614

2B • Updated 28 days ago • 3

updated a dataset 28 days ago

qingyangzhang/SCP-116K-formatted

Viewer • Updated 28 days ago • 25k • 118 • 1

published a dataset 28 days ago

qingyangzhang/SCP-116K-formatted

Viewer • Updated 28 days ago • 25k • 118 • 1

updated a model 28 days ago

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

2B • Updated 28 days ago • 5

published a model about 1 month ago

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

2B • Updated 28 days ago • 5

updated a collection about 1 month ago

EMPO

Collection

19 items • Updated Jun 4 • 2

upvoted a paper about 1 month ago

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

Paper • 2506.01939 • Published Jun 2 • 168

updated a model about 1 month ago

qingyangzhang/Qwen2.5-3B-Random-Natural-Reasoning

Text Generation • 3B • Updated Jun 2 • 3

upvoted a paper about 1 month ago

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

Paper • 2505.24864 • Published May 30 • 133

published a model about 1 month ago

qingyangzhang/Qwen2.5-3B-Random-Natural-Reasoning

Text Generation • 3B • Updated Jun 2 • 3