qingyang zhang

qingyangzhang

·

https://qingyangzhang.github.io

AI & ML interests

RL

Recent Activity

liked a model 2 days ago

tencent/Hy4-preview

upvoted a paper 21 days ago

ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation

upvoted a paper about 1 month ago

Recursive Synthesis for Long-Horizon Terminal Tasks

View all activity

Organizations

None yet

qingyangzhang 's datasets 13

qingyangzhang/DeepMath-103K-formatted

Viewer • Updated Jun 17, 2025 • 103k • 12

qingyangzhang/numina_math_20K_formatted

Viewer • Updated Jun 14, 2025 • 20k • 11

qingyangzhang/SCP-116K-formatted

Viewer • Updated Jun 14, 2025 • 25k • 8 • 1

qingyangzhang/natural_reasoning_all_level

Viewer • Updated Apr 21, 2025 • 130k • 5

qingyangzhang/natural_reasoning_level_1

Viewer • Updated Apr 18, 2025 • 68.5k • 3

qingyangzhang/natural_reasoning_simple

Viewer • Updated Apr 17, 2025 • 12.1k • 8

qingyangzhang/natural_reasoning_simple_text_only

Viewer • Updated Apr 16, 2025 • 37.4k • 16

qingyangzhang/natural_reasoning_simple_full

Viewer • Updated Apr 15, 2025 • 81.2k • 13

qingyangzhang/natural_reasoning_non_math_determined_answer

Viewer • Updated Apr 14, 2025 • 18.8k • 11

qingyangzhang/natural_reasoning_non_math_formatted

Viewer • Updated Apr 13, 2025 • 40.1k • 13

qingyangzhang/natural_reasoning_short_answer

Viewer • Updated Apr 12, 2025 • 20.6k • 16 • 1

qingyangzhang/Natural-Reasoning-STEM-50K

Viewer • Updated Apr 12, 2025 • 50k • 41

qingyangzhang/Natural-Reasoning-STEM-25K

Viewer • Updated Apr 12, 2025 • 25k • 216