🚀Join the movement to simplify VLA research. With Dexbotic by @Dexmal_AI, the power of a unified, experiment-driven toolbox based on PyTorch is now open source. Code, test, and contribute to the future of embodied AI.
26
17
45
Replies
(1/N)💡Introducing Dexbotic—an open-source, PyTorch based toolbox for Vision-Language-Action (VLA) models,which is developed by @Dexmal_AI🚀 →Website:[ https://t.co/XCnAvtUbrM] Built for embodied AI researchers, it delivers a unified, end-to-end codebase to accelerate VLA
1
0
2
(2/N)🧩VLA research today is fragmented. Inconsistent setups, irreproducible benchmarks, and outdated base models slow progress. Dexbotic changes that —support multiple VLA policies under one environment. Reproduce, compare, and extend with ease.
1
0
2
(3/N)💡Architecture Overview Data Layer: Dexdata format unifies multimodal inputs and optimizes storage. Model Layer: Integrates strong pretrained VLMs and supports policies like π0. Experiment Layer: Config-driven scripts enable fast iteration without compromising stability.
1
0
2
(4/N)🌖Go from idea to result in minimal steps. Modify a single Exp script to launch new experiments—No more rewriting pipelines. Plus, use our high-performance pretrained models to boost your VLA policies from the start. Please see tech report: https://t.co/HW6UL9aouO
1
0
2
(5/N) Key Features of Dexbotic: ✅ Unified modular VLA framework ✅ Powerful pretrained foundation models ✅ Experiment-centric development ✅ Cloud & local training support ✅ Diverse robot training and deployment
1
0
2
(6/N) Compatible with popular VLA policies, including: 🔘Pi0 🔘OpenVLA-OFT 🔘CogACT 🔘MemoryVLA 🔘MUVLA 🔘…and growing
1
0
2
(7/N)🤖We also offer our first robot product——Dexbotic Open Source - W1 (DOS - W1). Achieving the integration of hardware design and embodied intelligence, DOS - W1 is not just an execution terminal, but an open-source intelligent platform.
1
0
2
(8/N) 🎻And key features of DOS - W1： 🔘Fully open-source hardware design. 🔘Extensive quick-release, modular, and replaceable components. 🔘Low cost. 🔘Ergonomic design tailored to data collectors to reduce fatigue.
1
0
1
(9/N)🔅We’re committed to expanding the Dexbotic ecosystem—integrating more base models, real2sim tools, and real-world deployment support. GitHub
1
0
2
(10/N)🎯Our goal of Dexbotic is to build the foundational layer for general-purpose robot intelligence. Hugging Face： https://t.co/LVwNa8AdQi
1
0
2
(11/N)📩Join the community. Code, test, contribute. As Linus Torvalds said: “Software evolution requires collective wisdom.”Let’s build the future of embodied AI—together. Discord: https://t.co/laarGZ4VSX
1
0
2
I hope you've found this thread helpful. Follow me @jamescoder12 for more. Like/Repost the quote below if you can:
🚀Join the movement to simplify VLA research. With Dexbotic by @Dexmal_AI, the power of a unified, experiment-driven toolbox based on PyTorch is now open source. Code, test, and contribute to the future of embodied AI.
0
0
2
@jamescoder12 @Dexmal_AI That's a fantastic initiative, James, simplifying VLA research is definitely the need of the hour, right?
0
0
0
