Qi Cao
Cooolder
AI & ML interests
None yet
Organizations
None yet
-
DreamPRM: Domain-Reweighted Process Reward Model for Multimodal Reasoning
Paper • 2505.20241 • Published -
Cooolder/DreamPRM-1_5-InstanceNet
0.9B • Updated • 3 • 1 -
Cooolder/DreamPRM-1_5-InstanceTable
0.9B • Updated • 2 • 1 -
DreamPRM-1.5: Unlocking the Potential of Each Instance for Multimodal Process Reward Model Training
Paper • 2509.05542 • Published
-
DreamPRM: Domain-Reweighted Process Reward Model for Multimodal Reasoning
Paper • 2505.20241 • Published -
Cooolder/DreamPRM-1_5-InstanceNet
0.9B • Updated • 3 • 1 -
Cooolder/DreamPRM-1_5-InstanceTable
0.9B • Updated • 2 • 1 -
DreamPRM-1.5: Unlocking the Potential of Each Instance for Multimodal Process Reward Model Training
Paper • 2509.05542 • Published
datasets 10
Cooolder/SCOPE-OOD-set
Viewer • Updated • 2.5k • 42
Cooolder/SCOPE-60K
Viewer • Updated • 68.6k • 21
Cooolder/SCOPE-sft-direct-data
Viewer • Updated • 54.8k • 6
Cooolder/kshot_inference
Viewer • Updated • 3.28k • 62
Cooolder/kshot_inference_direct
Viewer • Updated • 3.28k • 23
Cooolder/mmmu-pro-valid
Viewer • Updated • 533 • 13
Cooolder/mmmu-pro-max2img
Viewer • Updated • 1.03k • 16
Cooolder/mmmu_pro_filtered_1000
Viewer • Updated • 1.08k • 16
Cooolder/mmmu_pro_processed
Viewer • Updated • 1.15k • 34
Cooolder/DreamPRM_MMMU
Viewer • Updated • 507 • 9