Update metadata and add paper link

README.md

@@ -1,14 +1,15 @@
 ---
 license: apache-2.0
-pipeline_tag: text-to-video
-inference: false
+pipeline_tag: image-to-video
+library_name: diffusers
 tags:
-  - world-model
-  - video-generation
-  - text-to-video
-  - image-to-video
-  - interactive
-  - distillation
+- world-model
+- video-generation
+- text-to-video
+- image-to-video
+- interactive
+- distillation
+inference: false
 ---
 
 <h1 align="center">Alaya-EVOKE: From Linear-Scaling Supervision to Endless World</h1>
@@ -16,7 +17,7 @@ tags:
 <p align="center">
   <a href="https://github.com/SII-YuanyangYin/Evoke"><img src="https://img.shields.io/badge/GitHub-SII--YuanyangYin/Evoke-181717.svg?logo=github" alt="GitHub"></a>
   <a href="https://evoke-world.github.io/Evoke/"><img src="https://img.shields.io/badge/🌐_Project_Page-evoke--world.github.io-1a73e8.svg" alt="Project Page"></a>
-  <a href="#"><img src="https://img.shields.io/badge/arXiv-coming_soon-b31b1b.svg" alt="arXiv"></a>
+  <a href="https://huggingface.co/papers/2608.13546"><img src="https://img.shields.io/badge/📄_Paper-HuggingFace-ffd21e.svg" alt="Paper"></a>
 </p>
 
 Model weights for **EVOKE**, a 3-step, CFG-free interactive world model that generates
@@ -78,4 +79,4 @@ built on [LingBot-World](https://github.com/robbyant/lingbot-world).
   title = {Alaya-EVOKE: From Linear-Scaling Supervision to Endless World},
   year  = {2026},
 }
-```
+```