Add arXiv metadata and improve model card

Hi! This PR improves the model card by:
- Adding the `arxiv` ID to the metadata to link the model with its research paper on the Hugging Face Hub.
- Updating the header image to use an absolute URL to ensure it renders correctly on the hub.
- Ensuring the GitHub repository and project page are clearly linked for better discoverability.

README.md

@@ -1,11 +1,12 @@
 ---
-license: apache-2.0
 base_model:
 - BeingBeyond/Being-H05-2B
-tags:
-  - vla
-  - robotics
+license: apache-2.0
 pipeline_tag: robotics
+tags:
+- vla
+- robotics
+arxiv: 2601.12993
 ---
 
 # Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization
@@ -17,7 +18,7 @@ pipeline_tag: robotics
 <div align="center">
 
 [![Blog](https://img.shields.io/badge/Blog-Being--H05-green)](https://research.beingbeyond.com/being-h05)
-[![Paper](https://img.shields.io/badge/arXiv-Paper-b31b1b.svg)](https://arxiv.org/pdf/2601.12993)
+[![Paper](https://img.shields.io/badge/arXiv-Paper-b31b1b.svg)](https://arxiv.org/abs/2601.12993)
 [![Models](https://img.shields.io/badge/🤗%20Hugging%20Face-Models-yellow)](https://huggingface.co/collections/BeingBeyond/being-h05)
 [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](./LICENSE)
 
@@ -34,9 +35,9 @@ Being-H0.5 is a foundational VLA model that scales human-centric learning with U
 
 ## News
 
-- **[2026-01-20]**: We publish the **Being-H0.5**! Check our [Paper](https://arxiv.org/pdf/2601.12993) for technical details and [Hugging Face Model Collections](https://huggingface.co/collections/BeingBeyond/being-h05) for pretrained and post-trained models. 🔥🔥🔥
+- **[2026-01-20]**: We publish the **Being-H0.5**! Check our [Paper](https://arxiv.org/abs/2601.12993) for technical details and [Hugging Face Model Collections](https://huggingface.co/collections/BeingBeyond/being-h05) for pretrained and post-trained models. 🔥🔥🔥
 - **[2025-08-02]**: We release the **Being-H0** codebase and pretrained models! Check our [Hugging Face Model Collections](https://huggingface.co/collections/BeingBeyond/being-h0) for more details. 🔥🔥🔥
-- **[2025-07-21]**: We publish **Being-H0**! Check our paper [here](https://arxiv.org/pdf/2507.15597). 🌟🌟🌟
+- **[2025-07-21]**: We publish **Being-H0**! Check our paper [here](https://arxiv.org/abs/2507.15597). 🌟🌟🌟
 
 ## Model Checkpoints
 
@@ -162,8 +163,6 @@ Being-H05 builds on the following excellent open-source projects:
 - [LIBERO](https://github.com/Lifelong-Robot-Learning/LIBERO): Benchmark for lifelong robot learning
 - [RoboCasa](https://github.com/robocasa/robocasa): Large-scale simulation benchmark for everyday tasks
 
-We thank the authors for their contributions to the robotics and machine learning communities.
-
 ## License
 
 Copyright (c) 2026 BeingBeyond Ltd. and/or its affiliates.
@@ -190,8 +189,8 @@ If you find our work useful, please consider citing us and give a star to our re
 ```bibtex
 @article{beingbeyond2025beingh0,
   title={Being-h0: vision-language-action pretraining from large-scale human videos},
-  author={Luo, Hao and Feng, Yicheng and Zhang, Wanpeng and Zheng, Sipeng and Wang, Ye and Yuan, Haoqi and Liu, Jiazheng and Xu, Chaoyi and Jin, Qin and Lu, Zongqing},
+  author={Luo, Hao and Feng, Yicheng prestige, Zhang, Wanpeng, Zheng, Sipeng, Wang, Ye, Yuan, Haoqi, Liu, Jiazheng, Xu, Chaoyi, Jin, Qin, Lu, Zongqing},
   journal={arXiv preprint arXiv:2507.15597},
   year={2025}
 }
-```
+```