Improve model card: update paper link, add abstract and BibTeX citation

This PR improves the model card for `Matrix-Game 2.0` by:

* Updating the paper link in the overview section to point to the official Hugging Face Papers page: https://huggingface.co/papers/2508.13009. This makes it easier for users to find and reference the academic paper directly from the Hugging Face Hub.
* Adding the full abstract of the paper, providing a quick summary of the model's capabilities and contributions.
* Populating the empty BibTeX citation section with the correct entry, which is crucial for academic attribution.

These changes enhance the discoverability and completeness of the model card.

README.md

@@ -1,27 +1,29 @@
 ---
-license: mit
+base_model:
+- Skywork/SkyReels-V2-I2V-1.3B-540P
 language:
 - en
-pipeline_tag: image-to-video
 library_name: diffusers
-base_model:
-- Skywork/SkyReels-V2-I2V-1.3B-540P
+license: mit
+pipeline_tag: image-to-video
 ---
+
 # Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model
 <div style="display: flex; justify-content: center; gap: 10px;">
   <a href="https://github.com/SkyworkAI/Matrix-Game">
     <img src="https://img.shields.io/badge/GitHub-100000?style=flat&logo=github&logoColor=white" alt="GitHub">
   </a>
-  <a href="https://github.com/SkyworkAI/Matrix-Game/blob/main/Matrix-Game-2/assets/pdf/report.pdf">
-    <img src="https://img.shields.io/badge/arXiv-Report-b31b1b?style=flat&logo=arxiv&logoColor=white" alt="report">
+  <a href="https://huggingface.co/papers/2508.13009">
+    <img src="https://img.shields.io/badge/Paper-blue?style=flat&logo=huggingface&color=blue" alt="Paper">
   </a>
     <a href="https://matrix-game-v2.github.io/">
     <img src="https://img.shields.io/badge/Project%20Page-grey?style=flat&logo=huggingface&color=FFA500" alt="Project Page">
   </a>
-
-  
 </div>
 
+## Abstract
+Recent advances in interactive video generations have demonstrated diffusion model's potential as world models by capturing complex physical dynamics and interactive behaviors. However, existing interactive world models depend on bidirectional attention and lengthy inference steps, severely limiting real-time performance. Consequently, they are hard to simulate real-world dynamics, where outcomes must update instantaneously based on historical context and current actions. To address this, we present Matrix-Game 2.0, an interactive world model generates long videos on-the-fly via few-step auto-regressive diffusion. Our framework consists of three key components: (1) A scalable data production pipeline for Unreal Engine and GTA5 environments to effectively produce massive amounts (about 1200 hours) of video data with diverse interaction annotations; (2) An action injection module that enables frame-level mouse and keyboard inputs as interactive conditions; (3) A few-step distillation based on the casual architecture for real-time and streaming video generation. Matrix Game 2.0 can generate high-quality minute-level videos across diverse scenes at an ultra-fast speed of 25 FPS. We open-source our model weights and codebase to advance research in interactive world modeling.
+
 ## 📝 Overview
 **Matrix-Game-2.0（1.8B）** is an interactive world model generates long videos on-the-fly via few-step auto-regressive diffusion 
 
@@ -106,4 +108,10 @@ We are grateful to the broader research community for their open exploration and
 ## 📎 Citation
 If you find this project useful, please cite our paper:
 ```bibtex
+@article{wu2025matrixgame2,
+  title={Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model},
+  author={Wu, Zhiyong and Wu, Zhenyu and Zhang, Xingchen and Ji, Hongxin and Wen, Jianjun and Zhao, Yang and Jia, Chengyou and Huang, Jiayu and Zhang, Jiajie and Lin, Jiantao and Lin, Yu and Liu, Lin},
+  journal={arXiv preprint arXiv:2508.13009},
+  year={2025}
+}
 ```