Update metadata and library_name

Hi! I'm Niels from the community science team at Hugging Face. This PR improves the model card's metadata by:
- Adding `library_name: transformers` to indicate compatibility with the Transformers library (as evidenced by the configuration files).
- Updating the `pipeline_tag` to `image-text-to-text` for better discoverability and to better represent its multimodal reasoning capabilities.
- Linking the paper directly in the introduction.

These changes ensure the model is correctly categorized on the Hub and enables automated code snippet generation for users.

README.md

@@ -1,13 +1,15 @@
 ---
-license: apache-2.0
+base_model:
+- Qwen/Qwen3-VL-2B-Instruct
 datasets:
 - OpenDataArena/MMFineReason-1.8M
 language:
 - en
-pipeline_tag: visual-question-answering
-base_model:
-- Qwen/Qwen3-VL-2B-Instruct
+license: apache-2.0
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
+
 <div align="center">
   <h1>MMFineReason</h1>
   <p><strong>Closing the Multimodal Reasoning Gap via Open Data-Centric Methods</strong></p>
@@ -27,7 +29,9 @@ base_model:
 </figure>
 
 ---
-This repository provides **MMFineReason-2B**; detailed dataset information is available at https://huggingface.co/datasets/OpenDataArena/MMFineReason-1.8M.
+This repository provides **MMFineReason-2B**, a multimodal model presented in the paper [MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods](https://huggingface.co/papers/2601.21821). 
+
+Detailed dataset information is available at https://huggingface.co/datasets/OpenDataArena/MMFineReason-1.8M.
 
 ## 📖 Overview