MAPO: Mixed Advantage Policy Optimization
Paper • 2509.18849 • Published • 27
MAPO: Mixed Advantage Policy Optimization
-
-
WilliamHuang91/qwen2_5_vl_7b_geo_12_grpo
8B • Updated • 5 -
WilliamHuang91/qwen2_5_vl_7b_emoset_12_grpo
8B • Updated • 5 -
WilliamHuang91/qwen2_5_vl_7b_emoset_12_grpomixpro
8B • Updated • 1 -
WilliamHuang91/qwen2_5_vl_7b_geo_12_grpomixpro
8B • Updated -
WilliamHuang91/qwen2_5_vl_7b_geo_12_dapo_grpo
8B • Updated -
WilliamHuang91/qwen2_5_vl_7b_emoset_12_dapo_grpo
8B • Updated -
WilliamHuang91/MAPO_Emotion_OOD_Dataset
Viewer • Updated • 2.59k • 43 -
WilliamHuang91/MAPO_Math_OOD_Dataset
Preview • Updated • 23 • 1