ENERVERSE-AC: Envisioning EmbodiedEnvironments with Action Condition

     

Introduction

This repo provides the pretrained weights of EnerVerse-AC (single-view). You can refer to our Github Repo to set-up environment and run inference.

Note: Due to commercial restrictions on portions of the training data referenced in the paper, the released model weights were trained exclusively on the open-source AgibotWorld dataset and do not include any failure trajectory data.

Citation

If you find EnerVerse-AC useful, please feel free to help ⭐ the [Github Repo] or citing our paper.

Thanks!

@article{huang2025enerverseac,
  title={EnerVerse-AC: Envisioning Embodied Environments with Action Condition},
  author={Jiang, Yuxin and Chen, Shengcong and Huang, Siyuan and Chen, Liliang and Zhou, Pengfei and Liao, Yue and He, Xindong and Liu, Chiming and Li, Hongsheng and Yao, Maoqing and Ren, Guanghui},
  journal={arXiv preprint arXiv:2505.09723},
  year={2025}
}

@article{huang2025enerverse,
  title={Enerverse: Envisioning Embodied Future Space for Robotics Manipulation},
  author={Huang, Siyuan and Chen, Liliang and Zhou, Pengfei and Chen, Shengcong and Jiang, Zhengkai and Hu, Yue and Liao, Yue and Gao, Peng and Li, Hongsheng and Yao, Maoqing and others},
  journal={arXiv preprint arXiv:2501.01895},
  year={2025}
}

License

All the data and code within this repo are under CC BY-NC-SA 4.0.