DreamPRM: Domain-Reweighted Process Reward Model for Multimodal Reasoning
Paper
•
2505.20241
•
Published
Qi Cao
Cooolder
AI & ML interests
None yet
Recent Activity
authored
a paper
3 days ago
DreamPRM: Domain-Reweighted Process Reward Model for Multimodal
Reasoning
authored
a paper
3 days ago
DreamPRM-1.5: Unlocking the Potential of Each Instance for Multimodal
Process Reward Model Training
authored
a paper
3 days ago
Models Under SCOPE: Scalable and Controllable Routing via Pre-hoc Reasoning
Organizations
None yet