yujunzhou/EVOL-RL-MATH-Train-Qwen3-4B-Base
4B
•
Updated
•
1
EVOL-RL
The models trained with EVOL-RL
-
-
yujunzhou/EVOL-RL-MATH-500-Qwen3-4B-Base
4B • Updated • 5 -
yujunzhou/EVOL-RL-AIME24-Qwen3-4B-Base
4B • Updated -
yujunzhou/EVOL-RL-MATH-Train-Qwen3-8B-Base
8B • Updated • 2 -
yujunzhou/EVOL-RL-MATH-500-Qwen3-8B-Base
8B • Updated -
yujunzhou/EVOL-RL-AIME24-Qwen3-8B-Base
8B • Updated • 1 -
Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation
Paper • 2509.15194 • Published • 33