Update app.py

app.py

@@ -2011,14 +2011,14 @@ def handle_example_click(mode, img_path_display, file_list_for_state, obj_info):
 with gr.Blocks() as app:
     #gr.Markdown("# Personalized Multimodal Understanding with RC-MLLM")
     gr.Markdown("<div style='text-align: center;'><h1 style=' font-size: 28px; '>Personalized Multimodal Understanding with RC-MLLM</h1></div>")
-    gr.Markdown("**RC-MLLM** model is developed based on the Qwen2-VL model through a novel method called **RCVIT (Region-level Context-aware Visual Instruction Tuning)**, using the specially constructed **RCMU dataset** for training. Its core feature is the capability for **Region-level Context-aware Multimodal Understanding (RCMU)**. This means it can simultaneously understand both the visual content of specific regions/objects within an image and their associated textual information (utilizing bounding boxes coordinates), allowing it to respond to user instructions in a more context-aware manner. Simply put, RC-MLLM not only understands images but can also integrate the textual information linked to specific objects within the image for understanding. It achieves outstanding performance on RCMU tasks and is suitable for applications like multimodal RAG and personalized conversation.")
+    gr.Markdown("**RC-MLLM** model is developed based on the Qwen2-VL model through a novel method called **RCVIT (Region-level Context-aware Visual Instruction Tuning)**, using the specially constructed **RCMU dataset** for training. Its core feature is the capability for **Region-level Context-aware Multimodal Understanding (RCMU)**. This means it can simultaneously understand both the visual content of specific regions/objects within an image and their associated textual information (utilizing bounding boxes coordinates), allowing it to respond to user instructions in a more context-aware manner. Simply put, RC-MLLM not only understands images but can also integrate the textual information linked to specific objects within the image for understanding. It achieves outstanding performance on RCMU tasks and is suitable for applications like personalized conversation.")
 
     markdown_content = """
-        📑 [Arxiv](https://arxiv.org/abs/your-paper-id) | 
-        🤗 [Checkpoint]() | 
+        📑 [Region-Level Context-Aware Multimodal Understanding](https://arxiv.org/abs/2508.12263) | 
+        🤗 Models:[RC-Qwen2VL-2b](https://huggingface.co/weihongliang/RC-Qwen2VL-2b/blob/main/README.md) [RC-Qwen2VL-7b](https://huggingface.co/weihongliang/RC-Qwen2VL-7b/blob/main/README.md)| 
         📁 [Dataset](https://huggingface.co/your-model-name) |
-        [Github](https://github.com/your-username/your-repo) | 
-        🚀 [Multimodal RAG with RC-MLLM](https://your-project-url.com)
+        [Github](https://github.com/hongliang-wei/RC-MLLM) | 
+        🚀 [Celebrity Recognition and VQA Demo](https://huggingface.co/spaces/weihongliang/RCMLLM)
         """
     gr.Markdown(markdown_content)