Cover Image

Dexbotic: Open-Source Vision-Language-Action Toolbox

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xie, Bin, Zhou, Erjin, Jia, Fan, Shi, Hao, Fan, Haoqiang, Zhang, Haowei, Li, Hebei, Sun, Jianjian, Bin, Jie, Huang, Junwen, Liu, Kai, Liu, Kaixin, Gu, Kefan, Sun, Lin, Zhang, Meng, Han, Peilong, Hao, Ruitao, Zhang, Ruitao, Huang, Saike, Xie, Songhan, Wang, Tiancai, Liu, Tianle, Tang, Wenbin, Zhu, Wenqi, Chen, Yang, Liu, Yingfei, Zhou, Yizhuang, Liu, Yu, Zhao, Yucheng, Ma, Yunchao, Wei, Yunfei, Chen, Yuxiang, Chen, Ze, Li, Zeming, Wu, Zhao, Zhang, Ziheng, Liu, Ziming, Yan, Ziwei, Zhang, Ziyu
Format:	Preprint
Published:	2025
Subjects:	Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866911234915303424
author	Xie, Bin Zhou, Erjin Jia, Fan Shi, Hao Fan, Haoqiang Zhang, Haowei Li, Hebei Sun, Jianjian Bin, Jie Huang, Junwen Liu, Kai Liu, Kaixin Gu, Kefan Sun, Lin Zhang, Meng Han, Peilong Hao, Ruitao Zhang, Ruitao Huang, Saike Xie, Songhan Wang, Tiancai Liu, Tianle Tang, Wenbin Zhu, Wenqi Chen, Yang Liu, Yingfei Zhou, Yizhuang Liu, Yu Zhao, Yucheng Ma, Yunchao Wei, Yunfei Chen, Yuxiang Chen, Ze Li, Zeming Wu, Zhao Zhang, Ziheng Liu, Ziming Yan, Ziwei Zhang, Ziyu
author_facet	Xie, Bin Zhou, Erjin Jia, Fan Shi, Hao Fan, Haoqiang Zhang, Haowei Li, Hebei Sun, Jianjian Bin, Jie Huang, Junwen Liu, Kai Liu, Kaixin Gu, Kefan Sun, Lin Zhang, Meng Han, Peilong Hao, Ruitao Zhang, Ruitao Huang, Saike Xie, Songhan Wang, Tiancai Liu, Tianle Tang, Wenbin Zhu, Wenqi Chen, Yang Liu, Yingfei Zhou, Yizhuang Liu, Yu Zhao, Yucheng Ma, Yunchao Wei, Yunfei Chen, Yuxiang Chen, Ze Li, Zeming Wu, Zhao Zhang, Ziheng Liu, Ziming Yan, Ziwei Zhang, Ziyu
contents	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.
format	Preprint
id	arxiv_https___arxiv_org_abs_2510_23511
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	Dexbotic: Open-Source Vision-Language-Action Toolbox Xie, Bin Zhou, Erjin Jia, Fan Shi, Hao Fan, Haoqiang Zhang, Haowei Li, Hebei Sun, Jianjian Bin, Jie Huang, Junwen Liu, Kai Liu, Kaixin Gu, Kefan Sun, Lin Zhang, Meng Han, Peilong Hao, Ruitao Zhang, Ruitao Huang, Saike Xie, Songhan Wang, Tiancai Liu, Tianle Tang, Wenbin Zhu, Wenqi Chen, Yang Liu, Yingfei Zhou, Yizhuang Liu, Yu Zhao, Yucheng Ma, Yunchao Wei, Yunfei Chen, Yuxiang Chen, Ze Li, Zeming Wu, Zhao Zhang, Ziheng Liu, Ziming Yan, Ziwei Zhang, Ziyu Robotics 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.
title	Dexbotic: Open-Source Vision-Language-Action Toolbox
topic	Robotics
url	https://arxiv.org/abs/2510.23511