Unified Reward Model for Multimodal Understanding and Generation
Paper
•
2503.05236
•
Published
•
124
UnifiedReward Models
-
-
Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning
Paper • 2505.03318 • Published • 94 -
CodeGoat24/UnifiedReward-qwen-32b
33B • Updated • 1.33k • 1
CodeGoat24/UnifiedReward-qwen-7b
8B • Updated • 2.78k • 5Note Built upon Qwen2.5-VL-Instruct, which is recommended!
-
CodeGoat24/UnifiedReward-7b-v1.5
8B • Updated • 1.77k • 6 -
CodeGoat24/UnifiedReward-qwen-3b
4B • Updated • 2.79k • 1 -
CodeGoat24/UnifiedReward-Think-qwen-7b
8B • Updated • 1.64k • 3 -
CodeGoat24/UnifiedReward-7b
8B • Updated • 460 • 6 -
CodeGoat24/UnifiedReward-Think-7b
8B • Updated • 476 • 10 -
CodeGoat24/UnifiedReward-0.5b
1B • Updated • 42 • 1 -
CodeGoat24/llava-onevision-qwen2-7b-ov-unifiedreward-dpo
8B • Updated • 6 -
CodeGoat24/sdxl-turbo-unified-reward-dpo
Text-to-Image • Updated • 10 • 1 -
CodeGoat24/LLaVA-Video-7B-Qwen2-UnifiedReward-DPO
8B • Updated • 47 -
CodeGoat24/T2V-Turbo
Updated