CaraJ commited on
Commit
64c3bc2
·
verified ·
1 Parent(s): 74b410c

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ This is the output reward model (ORM) used in [T2I-R1](https://github.com/CaraJ7/T2I-R1).
2
+
3
+ This model is fine-tuned from [lmms-lab/llava-onevision-qwen2-7b-ov](https://huggingface.co/lmms-lab/llava-onevision-qwen2-7b-ov).
4
+
5
+ Please check our paper: "[T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT](https://arxiv.org/pdf/2505.00703)" and [GitHub](https://github.com/CaraJ7/T2I-R1) for more information.