Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning
Paper
•
2505.03318
•
Published
•
92
Jenson
drjaker
AI & ML interests
image inpainting
Recent Activity
upvoted
a
paper
29 days ago
Unified Multimodal Chain-of-Thought Reward Model through Reinforcement
Fine-Tuning
upvoted
a
paper
3 months ago
Unified Reward Model for Multimodal Understanding and Generation
Organizations
None yet