Improve model card for GRPO-CARE

This PR updates the model card by:
- Adding the `pipeline_tag: video-text-to-text` for better discoverability.
- Adding the `library_name: transformers` to indicate the primary library used.
- Including a direct link to the paper within the README.

README.md

@@ -1,7 +1,11 @@
 ---
 license: apache-2.0
+library_name: transformers
+pipeline_tag: video-text-to-text
 ---
 
+This repository contains the GRPO-CARE model, presented in the paper [GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning](https://huggingface.co/papers/2506.16141).
+
 Code released at [GRPO-CARE](https://github.com/TencentARC/GRPO-CARE).
 
 ## Citation