Update app.py

app.py

@@ -220,6 +220,9 @@ description = f"""
             If you experience tokenizer artifacts or very dark images, you can use gamma correction to handle this. 
         </li>
     </ul>
+    <p>
+    Paper: <a href="https://arxiv.org/abs/2505.15263">https://arxiv.org/abs/2505.15263</a>
+    </p>
     <p>
         For faster inference, please check out our GitHub to run the models locally on a GPU:
         <a href="https://github.com/UCDvision/gen2seg" target="_blank">https://github.com/UCDvision/gen2seg</a> or check out our Colab demo <a href="https://colab.research.google.com/drive/10lPBP4figJf7MLp9T1b5cDQeU7MgODw3?usp=sharing" target="_blank">here</a>.