Add/improve model card

This PR adds/improves the model card by adding metadata such as `pipeline_tag` and `library_name`. It also ensures that the model card is linked to the paper.

README.md

@@ -1,3 +1,14 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: image-to-image
+---
+
+This repository contains the model presented in the paper [UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface](https://hf.co/papers/2503.01342).
+
+UFO unifies object-level detection, pixel-level segmentation, and image-level vision-language tasks into a single model by transforming all perception targets into the language space.  It introduces a novel embedding retrieval approach that relies solely on the language interface to support segmentation tasks.
+
+For more details, please refer to the original paper and the GitHub repository:
+
+- Paper: [UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface](https://hf.co/papers/2503.01342)
+- GitHub: [https://github.com/nnnth/UFO](https://github.com/nnnth/UFO)