Add pipeline tag and link to paper

README.md

@@ -1,8 +1,23 @@
 ---
 license: apache-2.0
+pipeline_tag: image-to-image
 ---
+
 ## Fast and Accurate Image Restoration and Generation with Rank Enhanced Linear Attention (ECCV 2026)
 
-This repo is used to host LAformer's checkpoints.
+This repository contains the pretrained checkpoints for **LAformer**, presented in the paper [Fast and Accurate Image Restoration and Generation with Rank Enhanced Linear Attention](https://huggingface.co/papers/2505.16157).
+
+LAformer is an efficient and effective Vision Transformer built upon **Rank Enhanced Linear Attention (RELA)**, designed to handle high-resolution image processing and global context modeling with linear complexity.
+
+For more details, training configurations, and evaluation tutorials, please see the [LAformer GitHub repository](https://github.com/shallowdream204/LAformer).
+
+### Citation
 
-For more details or tutorials see https://github.com/shallowdream204/LAformer.
+```bibtex
+@inproceedings{ai2026fast,
+  title     = {Fast and Accurate Image Restoration and Generation with Rank Enhanced Linear Attention},
+  author    = {Ai, Yuang},
+  booktitle = {ECCV},
+  year      = {2026}
+}
+```