Improve model card: Add metadata (pipeline_tag, library_name, license) and update paper link

README.md

@@ -1,8 +1,14 @@
+---
+pipeline_tag: image-to-text
+library_name: transformers
+license: other
+---
+
 # Boosting Multi-modal Keyphrase Prediction with Dynamic Chain-of-Thought in Vision-Language Models
 
 <div align="center">
 <p align="center">
-  <a>
+  <a href="https://huggingface.co/papers/2510.09358">
     <img
       src="https://img.shields.io/badge/ArXiv-Paper-red?logo=arxiv&logoColor=red"
       alt="Paper"
@@ -54,7 +60,7 @@ bash eval_full_sft.sh {/path/to/model} {/path/to/source_txt} --template {templat
 ```
 
 ## 🧾 License
-DynamicCoT are derived from [Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct), which is subject to [Qwen RESEARCH LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/LICENSE). We retain ownership of all intellectual property rights in and to any derivative works and modifications that we made.
+DynamicCoT are derived from [Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/LICENSE), which is subject to [Qwen RESEARCH LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/LICENSE). We retain ownership of all intellectual property rights in and to any derivative works and modifications that we made.
 
 
 ## 🙏 Acknowledgement