update

app.py

@@ -109,7 +109,7 @@ def build_demo():
         gr.Markdown(""" # Mantis
 Mantis is a multimodal conversational AI model that can chat with users about images and text. It's optimized for multi-image reasoning, where inverleaved text and images can be used to generate responses.
 
-[Paper](https://arxiv.org/abs/2405.01483) | [Github](https://github.com/TIGER-AI-Lab/Mantis) | [Models](https://huggingface.co/collections/TIGER-Lab/mantis-6619b0834594c878cdb1d6e4) | [Dataset](https://huggingface.co/datasets/TIGER-Lab/Mantis-Instruct)                   
+### [Paper](https://arxiv.org/abs/2405.01483) | [Github](https://github.com/TIGER-AI-Lab/Mantis) | [Models](https://huggingface.co/collections/TIGER-Lab/mantis-6619b0834594c878cdb1d6e4) | [Dataset](https://huggingface.co/datasets/TIGER-Lab/Mantis-Instruct)                   
         """)
         
         gr.Markdown("""## Chat with Mantis
@@ -183,6 +183,15 @@ Mantis is a multimodal conversational AI model that can chat with users about im
             inputs=[chat_input],
         )        
         
+        gr.Markdown("""
+## Citation
+```
+@article{jiang2024mantis,
+  title={MANTIS: Interleaved Multi-Image Instruction Tuning},
+  author={Jiang, Dongfu and He, Xuan and Zeng, Huaye and Wei, Con and Ku, Max and Liu, Qian and Chen, Wenhu},
+  journal={arXiv preprint arXiv:2405.01483},
+  year={2024}
+}```""")
     return demo