MAPO: Mixed Advantage Policy Optimization
Paper
•
2509.18849
•
Published
•
26
MAPO: Mixed Advantage Policy Optimization
-
-
WilliamHuang91/qwen2_5_vl_7b_geo_12_grpo
8B • Updated • 2 -
WilliamHuang91/qwen2_5_vl_7b_emoset_12_grpo
8B • Updated • 1 -
WilliamHuang91/qwen2_5_vl_7b_emoset_12_grpomixpro
8B • Updated • 4 -
WilliamHuang91/qwen2_5_vl_7b_geo_12_grpomixpro
8B • Updated • 2 -
WilliamHuang91/qwen2_5_vl_7b_geo_12_dapo_grpo
8B • Updated • 2 -
WilliamHuang91/qwen2_5_vl_7b_emoset_12_dapo_grpo
8B • Updated • 2 -
WilliamHuang91/MAPO_Emotion_OOD_Dataset
Viewer • Updated • 2.59k • 86 -
WilliamHuang91/MAPO_Math_OOD_Dataset
Viewer • Updated • 11.5k • 11.8k • 1