InternVLA-A-series

InternVLA-A1: Unifying Understanding, Generation, and Action for Robotic Manipulation​

Python★ 519

manipulationroboticsvision-language-action-model

i@InternRobotics++

FluxVLA

An all-in-one VLA engineering platform for embodied AI — from data to real-robot deployment.

Python★ 578

embodiedaireal-robotsreal-timeroboticsvision-language-action-modelvlmworld-action-model

f@FluxVLA++

X-VLA

[ICLR 2026] The offical Implementation of "Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Actio…

C++★ 697

cloth-foldingflorence-2manipulationpretrained-modelsroboticsrobotics-datasetvision-language-action-modelvision-language-model

2@2toinf++

InternNav

InternRobotics' open platform for building generalized navigation foundation models.

Jupyter Notebook★ 1k

mllmsnavigationroboticsspatial-aispatial-intelligencevision-language-action-modelvision-language-navigationvisual-navigation

i@InternRobotics++

Motus

Official code of Motus: A Unified Latent Action World Model

Python★ 1.2k

diffusion-modelrobotic-manipulationroboticsunidiffuservideo-generationvision-language-action-modelworld-model

t@thu-ml++

VLA-Adapter

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

Python★ 2.3k

embodied-airoboticsvision-language-action-model

o@OpenHelix-Team++

starVLA

StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

Python★ 3.3k

robotic-foundation-modelroboticsvision-language-action-modelworld-action-model

s@starVLA++