Update model card metadata and add external links

This PR improves the model card for Innovator-VL-8B-Instruct:
- Updates the `pipeline_tag` to `image-text-to-text` to better reflect its multimodal capabilities.
- Adds `library_name: transformers` to the metadata to enable Hub integration features.
- Adds direct links to the paper, project page, and GitHub repository.
- Maintains the existing sample usage and architectural details.

README.md

@@ -1,13 +1,16 @@
 ---
-license: mit
 language:
 - en
 - zh
-pipeline_tag: text-generation
+license: mit
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
 
 # Innovator-VL-8B-Instruct
 
+[**Paper**](https://huggingface.co/papers/2601.19325) | [**Project Page**](https://innovatorlm.github.io/Innovator-VL) | [**GitHub**](https://github.com/InnovatorLM/Innovator-VL)
+
 ## Model Summary
 
 **Innovator-VL-8B-Instruct** is a multimodal instruction-following large language model designed for scientific understanding and reasoning. The model integrates strong general-purpose vision-language capabilities with enhanced scientific multimodal alignment, while maintaining a fully transparent and reproducible training pipeline.
@@ -136,7 +139,8 @@ print(output_text)
 ```bibtex
 @article{wen2026innovator,
   title={Innovator-VL: A Multimodal Large Language Model for Scientific Discovery},
-  author={Wen, Zichen and Yang, Boxue and Chen, Shuang and Zhang, Yaojie and Han, Yuhang and Ke, Junlong and Wang, Cong and others},
+  author={Wen, Zichen and Yang, Boxue and Bird, Shuang and Zhang, Yaojie and Han, Yuhang and Ke, Junlong and Wang, Cong and others},
   journal={arXiv preprint arXiv:2601.19325},
   year={2026}
-}
+}
+```