Update README.md

README.md

@@ -7,7 +7,9 @@ license: mit
 
 ## ImageDPO Finetuned Model  
 
-This page provides the **ImageDPO** finetuned checkpoint for LLaVA-v1.5-7B used in [Probing Visual Language Priors in VLMs](https://arxiv.org/abs/2501.00569). ImageDPO is a self-improving approach to enhance VLM visual reasoning performance by increasing reliance on visual inputs. We offer the **merged model weights** for use.  
+This page provides the **ImageDPO** finetuned checkpoint for LLaVA-v1.5-7B used in [Probing Visual Language Priors in VLMs](https://arxiv.org/abs/2501.00569). ImageDPO is a self-improving approach to enhance VLM visual reasoning performance by increasing reliance on visual inputs as illustrated in the below image. We offer the **merged model weights** for use.  
+
+![ImageDPO](https://huggingface.co/ViLP/LLaVA-v1.5-13b-ImageDPO/resolve/main/ImageDPO.png)
 
 ## Usage