TMLR-Group-HF/Co-rewarding-RephrasedMATH
Viewer
•
Updated
•
7.5k
•
72
Co-rewarding
Co-rewarding is a novel self-supervised RL framework that improves training stability by seeking complementary supervision from another views.
-
-
TMLR-Group-HF/Co-rewarding-I-Qwen2.5-3B-MATH
Text Generation • 3B • Updated • 15 • 1 -
TMLR-Group-HF/Co-rewarding-I-Qwen2.5-7B-MATH
Text Generation • 8B • Updated • 23 • 1 -
TMLR-Group-HF/Co-rewarding-I-Qwen3-1.7B-Base-MATH
Text Generation • 2B • Updated • 18 -
TMLR-Group-HF/Co-rewarding-I-Qwen3-4B-Base-MATH
Text Generation • 4B • Updated • 26 • 1 -
TMLR-Group-HF/Co-rewarding-I-Qwen3-8B-Base-MATH
Text Generation • 8B • Updated • 37 • 1 -
TMLR-Group-HF/Co-rewarding-I-Llama-3.2-3B-Instruct-MATH
Text Generation • 4B • Updated • 15 -
TMLR-Group-HF/Self-Certainty-Qwen2.5-3B-MATH
Text Generation • 3B • Updated • 12 -
TMLR-Group-HF/Self-Certainty-Qwen2.5-7B-MATH
Text Generation • 8B • Updated • 15 • 1 -
TMLR-Group-HF/Self-Certainty-Qwen3-8B-Base-MATH
Text Generation • 8B • Updated • 12 • 1 -
TMLR-Group-HF/Self-Certainty-Llama-3.2-3B-Instruct-MATH
Text Generation • 4B • Updated • 10 -
TMLR-Group-HF/Self-Certainty-Qwen3-4B-Base-MATH
4B • Updated • 11 • 1 -
TMLR-Group-HF/Self-Certainty-Qwen3-1.7B-Base-MATH
Text Generation • 2B • Updated • 14 • 1 -
TMLR-Group-HF/Majority-Voting-Llama-3.2-3B-Instruct-MATH
4B • Updated • 8 -
TMLR-Group-HF/GT-Qwen3-4B-Base-MATH
Text Generation • 4B • Updated • 14 -
TMLR-Group-HF/GT-Qwen2.5-3B-MATH
Text Generation • 3B • Updated • 10 -
TMLR-Group-HF/GT-Qwen2.5-7B-MATH
8B • Updated • 12 -
TMLR-Group-HF/Majority-Voting-Qwen2.5-3B-MATH
3B • Updated • 9 • 1 -
TMLR-Group-HF/GT-Llama-3.2-3B-Instruct-MATH
Text Generation • 4B • Updated • 11 -
TMLR-Group-HF/GT-Qwen3-1.7B-Base-MATH
2B • Updated • 12 -
TMLR-Group-HF/GT-Qwen3-8B-Base-MATH
Text Generation • 8B • Updated • 22 • 2 -
TMLR-Group-HF/Majority-Voting-Qwen3-8B-Base-MATH
8B • Updated • 18 • 1 -
TMLR-Group-HF/Majority-Voting-Qwen3-4B-Base-MATH
4B • Updated • 5 -
TMLR-Group-HF/Majority-Voting-Qwen2.5-7B-MATH
8B • Updated • 11 • 1 -
TMLR-Group-HF/Majority-Voting-Qwen3-1.7B-Base-MATH
2B • Updated • 6 -
TMLR-Group-HF/Entropy-Qwen2.5-3B-MATH
3B • Updated • 8 -
TMLR-Group-HF/Entropy-Qwen3-8B-Base-MATH
8B • Updated • 10 • 1 -
TMLR-Group-HF/Entropy-Qwen3-4B-Base-MATH
Text Generation • 4B • Updated • 26 • 1 -
TMLR-Group-HF/Entropy-Qwen2.5-7B-MATH
Text Generation • 8B • Updated • 12 • 1 -
TMLR-Group-HF/Entropy-Qwen3-1.7B-Base-MATH
2B • Updated • 10 • 1 -
TMLR-Group-HF/Entropy-Llama-3.2-3B-Instruct-MATH
Text Generation • 4B • Updated • 17 -
TMLR-Group-HF/Co-rewarding-RephrasedDAPO-14k
Viewer • Updated • 14.1k • 23 -
TMLR-Group-HF/Co-rewarding-RephrasedOpenRS
Viewer • Updated • 7k • 31 -
TMLR-Group-HF/Co-rewarding-II-Llama-3.2-3B-Instruct-MATH
4B • Updated • 32 -
TMLR-Group-HF/Co-rewarding-II-Qwen2.5-3B-MATH
3B • Updated • 21 -
TMLR-Group-HF/Co-rewarding-II-Qwen3-1.7B-Base-MATH
2B • Updated • 33 • 1 -
TMLR-Group-HF/Co-rewarding-II-Llama-3.2-3B-Instruct-DAPO14k
4B • Updated • 22 -
TMLR-Group-HF/Co-rewarding-II-Qwen2.5-7B-MATH
Text Generation • 8B • Updated • 22 • 1 -
TMLR-Group-HF/Co-rewarding-II-Qwen3-4B-Base-MATH
4B • Updated • 21 • 1 -
TMLR-Group-HF/Co-rewarding-II-Qwen3-4B-Base-OpenRS
4B • Updated • 33 -
TMLR-Group-HF/Co-rewarding-II-Qwen3-8B-Base-DAPO14k
8B • Updated • 25 • 1 -
TMLR-Group-HF/Co-rewarding-II-Qwen3-8B-Base-MATH
8B • Updated • 34 • 1 -
TMLR-Group-HF/Co-rewarding-II-Qwen3-8B-Base-OpenRS
8B • Updated • 21 -
TMLR-Group-HF/Co-rewarding-I-Llama-3.2-3B-Instruct-DAPO14k
4B • Updated • 36 -
TMLR-Group-HF/Co-rewarding-II-Qwen3-4B-Base-DAPO14k
4B • Updated • 24 • 1 -
TMLR-Group-HF/Co-rewarding-I-Qwen3-4B-Base-DAPO14k
4B • Updated • 35 -
TMLR-Group-HF/GT-Qwen3-8B-Base-DAPO14k
Text Generation • 8B • Updated • 34 • 1 -
TMLR-Group-HF/GT-Qwen3-4B-Base-DAPO14k
Text Generation • 4B • Updated • 32 -
TMLR-Group-HF/GT-Llama-3.2-3B-Instruct-DAPO14k
Text Generation • 4B • Updated • 27 -
TMLR-Group-HF/Self-Certainty-Qwen3-8B-Base-DAPO14k
Text Generation • 8B • Updated • 35 • 1 -
TMLR-Group-HF/Self-Certainty-Qwen3-4B-Base-DAPO14k
Text Generation • 4B • Updated • 27 • 1 -
TMLR-Group-HF/Self-Certainty-Llama-3.2-3B-Instruct-DAPO14k
Text Generation • 4B • Updated • 46 -
TMLR-Group-HF/Entropy-Qwen3-8B-Base-DAPO14k
Text Generation • 8B • Updated • 29 • 1 -
TMLR-Group-HF/Entropy-Qwen3-4B-Base-DAPO14k
Text Generation • 4B • Updated • 25 -
TMLR-Group-HF/Entropy-Llama-3.2-3B-Instruct-DAPO14k
Text Generation • 4B • Updated • 29 -
TMLR-Group-HF/Majority-Voting-Qwen3-8B-Base-DAPO14k
Text Generation • 8B • Updated • 32 • 2 -
TMLR-Group-HF/Majority-Voting-Qwen3-4B-Base-DAPO14k
Text Generation • 4B • Updated • 33 -
TMLR-Group-HF/Co-rewarding-I-Qwen3-8B-Base-OpenRS
Text Generation • 8B • Updated • 39 • 1 -
TMLR-Group-HF/Majority-Voting-Llama-3.2-3B-Instruct-DAPO14k
Text Generation • 4B • Updated • 35 -
TMLR-Group-HF/Co-rewarding-I-Qwen3-4B-Base-OpenRS
Text Generation • 4B • Updated • 18 -
TMLR-Group-HF/GT-Qwen3-4B-Base-OpenRS
Text Generation • 4B • Updated • 33 -
TMLR-Group-HF/GT-Qwen3-8B-Base-OpenRS
Text Generation • 8B • Updated • 26 • 1 -
TMLR-Group-HF/Self-Certainty-Qwen3-4B-Base-OpenRS
Text Generation • 4B • Updated • 32 -
TMLR-Group-HF/Entropy-Qwen3-4B-Base-OpenRS
Text Generation • 4B • Updated • 21 -
TMLR-Group-HF/Self-Certainty-Qwen3-8B-Base-OpenRS
Text Generation • 8B • Updated • 27 • 1 -
TMLR-Group-HF/Majority-Voting-Qwen3-4B-Base-OpenRS
Text Generation • 4B • Updated • 28 -
TMLR-Group-HF/Co-rewarding-I-Qwen3-8B-Base-DAPO14k
Text Generation • 8B • Updated • 26 • 1 -
TMLR-Group-HF/Majority-Voting-Qwen3-8B-Base-OpenRS
Text Generation • 8B • Updated • 30 • 1 -
TMLR-Group-HF/Entropy-Qwen3-8B-Base-OpenRS
Text Generation • 8B • Updated • 31 • 1