Dexbotic: Open-Source Vision-Language-Action Toolbox

2025/10/27 by Xie, Bin, Zhou, Erjin, Jia, Fan +36 · 3 citations
#FOS: Computer and information sciences #Robotics (cs.RO)

paper · doi:10.48550/arxiv.2510.23511

Abstract

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.

Citations

• MUVLA: Learning to Explore Object Navigation via Map Understanding
• LLaDA-VLA: Vision Language Diffusion Action Models
• MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation
• GeoVLA: Empowering 3D Representations in Vision-Language-Action Models
• RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
• Qwen3 Technical Report
• π_0.5: a Vision-Language-Action Model with Open-World Generalization
• AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
• Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
• RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation
• NaVILA: Legged Robot Vision-Language-Action Model for Navigation
• CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
• RoboGSim: A Real2Sim2Real Robotic Gaussian Splatting Simulator
• π₀: A Vision-Language-Action Flow Model for General Robot Control
• SplatSim: Zero-Shot Sim2Real Transfer of RGB Manipulation Policies Using Gaussian Splatting
• PaliGemma: A versatile 3B VLM for transfer
• Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
• OpenVLA: An Open-Source Vision-Language-Action Model
• Evaluating Real-World Robot Manipulation Policies in Simulation
• NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
• RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
• 3D Gaussian Splatting for Real-Time Radiance Field Rendering
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
• Visual Instruction Tuning
• Sigmoid Loss for Language Image Pre-Training
• ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills
• CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks
• RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning
• Learning Transferable Visual Models From Natural Language Supervision
• RLBench: The Robot Learning Benchmark & Learning Environment
• MMDetection: Open MMLab Detection Toolbox and Benchmark

Cited by

• A Pragmatic VLA Foundation Model
• An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges
• SpatialActor: Exploring Disentangled Spatial Representations for Robust Robotic Manipulation
• SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning
• MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation

Related

• An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges
• VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
• OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation
• VLA²: Empowering Vision-Language-Action Models with an Agentic Framework for Unseen Concept Manipulation
• A Survey on Efficient Vision-Language-Action Models