b:botstest.Submit a resource ↗

Models / Research

vla0 · NVlabs

VLA-0 provides research code for building vision-language-action models from vision-language models.

roboticsvlavlm
Publisher repository ↗
vla0 · NVlabs resource page screenshot
Resource screenshot · captured 2026-10-08 · visually reviewed

Overview

VLA-0 provides research code for building vision-language-action models from vision-language models.

Publisher summary: “VLA-0: Building State-of-the-Art VLAs with Zero Modification”

Use its repository to inspect the implementation, documentation and supported workflows. This directory record identifies the maintainer, code license and related resources; it does not claim that the project has been installed or tested on your robot.

Project information

Maintainer
NVlabs
Primary language
Python
Repository code license
Not specified
Model-weight license
Not recorded
Dataset license
Not recorded
Hardware design license
Not recorded
Maintenance
Not archived in the last recorded metadata
Last observed repository push
2026-02-21

Code licenses do not automatically cover model weights, datasets or hardware designs. Unrecorded license details require confirmation with the publisher.

Documentation sections

  • [VLA-0: Building State-of-the-Art VLAs with Zero Modification](vla0.github.io)
  • Abstract
  • Key Results
  • VLA-0 Community Implementations and Extensions
  • Using VLA-0 in Your Research?
  • Installation

Browse this resource’s categories

Models / Vision-language-action ↗

Explore related collections

Vision-language-action models ↗

More in Models