update

app.py

@@ -106,16 +106,11 @@ def bot(history):
 def build_demo():
     with gr.Blocks() as demo:
         
-        with gr.Row():
-            with gr.Column():
-                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.
-
-        | [Github](https://github.com/TIGER-AI-Lab/Mantis) | [Models](https://huggingface.co/collections/TIGER-Lab/mantis-6619b0834594c878cdb1d6e4) |                   
-                """)
-                # gr.Image("./barchart_single_image_vqa.jpeg")
-            with gr.Column():
-                gr.Image("./barchart.jpeg")
+        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)                   
+        """)
         
         gr.Markdown("""## Chat with Mantis
         Mantis supports interleaved text-image input format, where you can simply use the placeholder `<image>` to indicate the position of uploaded images.