Update README.md

README.md

@@ -10,23 +10,33 @@ pipeline_tag: robotics
 
 # Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization
 
+<p align="center">
+    <img src="https://raw.githubusercontent.com/BeingBeyond/Being-H/refs/heads/main/assets/being-h05.png" width="300"/>
+<p>
+
 <div align="center">
 
 [![Blog](https://img.shields.io/badge/Blog-Being--H05-green)](https://research.beingbeyond.com/being-h05)
-[![arXiv](https://img.shields.io/badge/arXiv-2601.xxxxx-b31b1b.svg)](https://research.beingbeyond.com/projects/being-h05/being-h05.pdf)
+[![Paper](https://img.shields.io/badge/arXiv-Paper-b31b1b.svg)](https://arxiv.org/pdf/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)
 
 </div>
 
 Being-H0.5 is a foundational VLA model that scales human-centric learning with UniHand-2.0 and a unified action space to enable robust cross-embodiment robot control.
 
+<div align="center">
+<video src="https://github.com/user-attachments/assets/36714389-e737-4b11-8dcf-9076cc9f1d69" controls>
+</video>
+</div>
+
 *(For our previous Being-H0 version, please visit the [being-h0](https://github.com/BeingBeyond/Being-H/tree/being-h0) branch.)*
 
 ## News
 
-- **[2026-01-20]**: We release the **Being-H0.5** codebase! Check our [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/pdf/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/abs/2507.15597). 🌟🌟🌟
+- **[2025-07-21]**: We publish **Being-H0**! Check our paper [here](https://arxiv.org/pdf/2507.15597). 🌟🌟🌟
 
 ## Model Checkpoints
 
@@ -34,11 +44,12 @@ Download models from Hugging Face:
 
 | Model Type | Model Name | Parameters | Description |
 |------------|------------|------------|-------------|
-| **VLA Pretrained** | [Being-H05-2B](https://huggingface.co/BeingBeyond/Being-H05-2B) | 2B | Base vision-language-action model |
+| **VLA Pretrained** | [Being-H05-2B](https://huggingface.co/BeingBeyond/Being-H05-2B) | 2B | Base vision-language-action model (preview) |
 | **VLA Specialist** | [Being-H05-2B_libero](https://huggingface.co/BeingBeyond/Being-H05-2B_libero) | 2B | Post-trained on LIBERO benchmark |
 | **VLA Specialist** | [Being-H05-2B_robocasa](https://huggingface.co/BeingBeyond/Being-H05-2B_robocasa) | 2B | Post-trained on RoboCasa kitchen tasks |
 | **VLA Generalist** | [Being-H05-2B_libero_robocasa](https://huggingface.co/BeingBeyond/Being-H05-2B_libero_robocasa) | 2B | Post-trained on both LIBERO and RoboCasa |
 
+Note: the vision part is 224px by default.
 
 ## Setup
 
@@ -137,16 +148,6 @@ torchrun --nproc_per_node=8 BeingH/train/train.py \
     --action_chunk_length 16
 ```
 
-## TODO
-
-The following features are planned for future implementation:
-
-- [ ] Complete pretraining scripts and documentation
-- [ ] Complete post-training scripts for all benchmarks
-- [ ] Detailed training and data documentation
-- [ ] Out-of-the-box real robot pretrained checkpoints
-- [ ] Benchmark evaluation scripts for all supported tasks
-
 ## Contributing and Building on Being-H05
 
 We encourage researchers and practitioners to leverage Being-H05 as a foundation for their own experiments and applications. Whether you're adapting Being-H05 to new robotic platforms, exploring novel manipulation tasks, or extending the model to new domains, our modular codebase is designed to support your innovations. We welcome contributions of all kinds - from bug fixes and documentation improvements to new features and model architectures. By building on Being-H05 together, we can advance the field of vision-language-action modeling and enable robots to perform more complex and diverse manipulation tasks. Join us in making robotic manipulation more capable, robust, and accessible to all.
@@ -156,6 +157,7 @@ We encourage researchers and practitioners to leverage Being-H05 as a foundation
 Being-H05 builds on the following excellent open-source projects:
 
 - [InternVL](https://github.com/OpenGVLab/InternVL): Vision-Language model backbone
+- [Bagel](https://github.com/ByteDance-Seed/Bagel): Training framework
 - [Qwen](https://github.com/QwenLM/Qwen): Language model and MoE expert
 - [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
@@ -175,9 +177,21 @@ If you find our work useful, please consider citing us and give a star to our re
 **Being-H05**
 
 ```bibtex
-@misc{beingbeyond2026beingh05,
-  title={Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization},
-  author={BeingBeyond Team},
+@article{beingbeyond2026beingh05,
+  title={Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization}, 
+  author={Luo, Hao and Wang, Ye and Zhang, Wanpeng and Zheng, Sipeng and Xi, Ziheng and Xu, Chaoyi and Xu, Haiweng and Yuan, Haoqi and Zhang, Chi and Wang, Yiqing and Feng, Yicheng and Lu, Zongqing},
+  journal={arXiv preprint arXiv:2601.12993},
   year={2026}
 }
-```
+```
+
+**Being-H0**
+
+```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},
+  journal={arXiv preprint arXiv:2507.15597},
+  year={2025}
+}
+```