qingyang zhang's picture

3 12 2

qingyang zhang

qingyangzhang

·

https://qingyangzhang.github.io

AI & ML interests

LLM Reasoning

Recent Activity

authored a paper 7 days ago

P1: Mastering Physics Olympiads with Reinforcement Learning

upvoted a paper 9 days ago

P1: Mastering Physics Olympiads with Reinforcement Learning

authored a paper about 1 month ago

Provable Dynamic Fusion for Low-Quality Multimodal Data

View all activity

Organizations

None yet

qingyangzhang 's datasets 13

qingyangzhang/DeepMath-103K-formatted

Viewer • Updated Jun 17 • 103k • 26

qingyangzhang/numina_math_20K_formatted

Viewer • Updated Jun 14 • 20k • 10

qingyangzhang/SCP-116K-formatted

Viewer • Updated Jun 14 • 25k • 17 • 1

qingyangzhang/natural_reasoning_all_level

Viewer • Updated Apr 21 • 130k • 5

qingyangzhang/natural_reasoning_level_1

Viewer • Updated Apr 18 • 68.5k • 5

qingyangzhang/natural_reasoning_simple

Viewer • Updated Apr 17 • 12.1k • 6

qingyangzhang/natural_reasoning_simple_text_only

Viewer • Updated Apr 16 • 37.4k • 6

qingyangzhang/natural_reasoning_simple_full

Viewer • Updated Apr 15 • 81.2k • 8

qingyangzhang/natural_reasoning_non_math_determined_answer

Viewer • Updated Apr 14 • 18.8k • 42

qingyangzhang/natural_reasoning_non_math_formatted

Viewer • Updated Apr 13 • 40.1k • 65

qingyangzhang/natural_reasoning_short_answer

Viewer • Updated Apr 12 • 20.6k • 9 • 1

qingyangzhang/Natural-Reasoning-STEM-50K

Viewer • Updated Apr 12 • 50k • 10

qingyangzhang/Natural-Reasoning-STEM-25K

Viewer • Updated Apr 12 • 25k • 6