In this paper, we present Dexbotic, an open-source Vision-Language-Action (VLA) model toolbox based on PyTorch. It aims to provide a one-stop VLA research service for professionals in the field of embodied intelligence. It offers a codebase that supports multiple mainstream VLA policies simultaneously, allowing users to reproduce various VLA methods with just a single environment setup. The toolbox is experiment-centric, where the users can quickly develop new VLA experiments by simply modifying the Exp script. Moreover, we provide much stronger pretrained models to achieve great performance improvements for state-of-the-art VLA policies. Dexbotic will continuously update to include more of the latest pre-trained foundation models and cutting-edge VLA models in the industry.
Cite
@article{arxiv.2510.23511,
title = {Dexbotic: Open-Source Vision-Language-Action Toolbox},
author = {Bin Xie and Erjin Zhou and Fan Jia and Hao Shi and Haoqiang Fan and Haowei Zhang and Hebei Li and Jianjian Sun and Jie Bin and Junwen Huang and Kai Liu and Kaixin Liu and Kefan Gu and Lin Sun and Meng Zhang and Peilong Han and Ruitao Hao and Ruitao Zhang and Saike Huang and Songhan Xie and Tiancai Wang and Tianle Liu and Wenbin Tang and Wenqi Zhu and Yang Chen and Yingfei Liu and Yizhuang Zhou and Yu Liu and Yucheng Zhao and Yunchao Ma and Yunfei Wei and Yuxiang Chen and Ze Chen and Zeming Li and Zhao Wu and Ziheng Zhang and Ziming Liu and Ziwei Yan and Ziyu Zhang},
journal= {arXiv preprint arXiv:2510.23511},
year = {2025}
}
Comments
Authors are listed in alphabetical order. The official website is located at https://dexbotic.com/. Code is available at https://github.com/Dexmal/dexbotic