Improve model card: add pipeline tag and paper link

This PR updates the model card for the VFRTok model to enhance its discoverability and information clarity on the Hugging Face Hub.

Specifically, it includes the following changes:
- Adds the `pipeline_tag: other` to the metadata, which is appropriate for a video tokenizer model and improves searchability.
- Explicitly adds a link to the official Hugging Face paper page ([https://huggingface.co/papers/2505.12053](https://huggingface.co/papers/2505.12053)) within the markdown content, providing direct access to the associated research paper.

No `library_name` was added, as there is no direct evidence in the provided code for compatibility with any Hugging Face library.

README.md

@@ -1,8 +1,12 @@
 ---
 license: mit
+pipeline_tag: other
 ---
+
 # [NeurIPS'25] VFRTok: Variable Frame Rates Video Tokenizer with Duration-Proportional Information Assumption
 
+This model is presented in the paper [VFRTok: Variable Frame Rates Video Tokenizer with Duration-Proportional Information Assumption](https://huggingface.co/papers/2505.12053).
+
 <div align="center">
 
 [![arXiv](https://img.shields.io/badge/arXiv-2502.12053-904CE5.svg)](https://arxiv.org/pdf/2505.12053)&nbsp;