Models / Research

UniVLA · baaivision

BAAI UniVLA provides a unified vision-language-action model research project.

Overview

BAAI UniVLA provides a unified vision-language-action model research project.

Publisher summary: “[ICLR 2026] Unified Vision-Language-Action Model”

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: baaivision
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: 2025-10-15

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

Documentation sections

🌐 UniVLA: Unified Vision-Language-Action Model
🚀 News
🧪 Highlights
🔧 REPO TODO List
📚 Experiments
Emu3 Pretraining Models

Browse this resource’s categories

Models / Vision-language-action ↗

Explore related collections

Vision-language-action models ↗

Website

Research

RoboVLMs

A framework for connecting vision-language models to robotic actions.

Vision-language-action

Models Explore →