Skip to content

Askdroid

Menu
  • Home
    • About Us
    • Contact us
  • AI
  • Robotics
  • Podcasts
  • News
  • Blog
Menu
  • Home
    • About Us
    • Contact us
  • AI
  • Robotics
  • Podcasts
  • News
  • Blog
Ai Category: Vision-Language-Action ModelsAi Tags: fine-tuning Llama 2 Manipulation Open X-Embodiment Open-Source VLA
  • Profile
  • Title
  • Website URL
  • Short Description
  • Description
  • Tags
  • Company Name
  • Category
  • Country
  • License
  • Stage
  • Model Size
  • Hardware Requirement
  • API
  • Documentation
  • GitHub
  • Paper / Publication
  • Robots Using

OpenVLA is a 7-billion-parameter open-source Vision-Language-Action (VLA) model released in 2024 by a Stanford / UC Berkeley / Toyota Research Institute / Google DeepMind collaboration. Trained on 970,000 robot demonstrations from the Open X-Embodiment dataset, it pairs a Llama 2 language model backbone with a dual visual encoder that fuses DINOv2 spatial features with SigLIP semantic features. Given a camera image and a natural-language instruction, the model predicts 7-dimensional robot control actions as discrete tokens. OpenVLA was specifically built to address the closed nature of prior VLA models such as RT-2 and to provide best practices for fine-tuning on commodity GPUs. Despite being seven times smaller, it reportedly outperforms RT-2-X (55B) by roughly 16.5 percentage points across 29 manipulation tasks and multiple embodiments. The full codebase, training notebooks, and weights are openly released, making OpenVLA a foundational reference for any team building a generalist robot policy. Typical use cases include tabletop manipulation on Franka, WidowX, and other research arms, with extensive community support for LoRA-style fine-tuning to new platforms.

OpenVLA
Website URL

Open-source 7B-parameter vision-language-action model trained on 970,000 real-world robot demonstrations. Built on a Llama 2 backbone with a fused DINOv2 + SigLIP vision encoder. Generalises across multiple robot embodiments and supports parameter-efficient fine-tuning for new robots.

OpenVLA is a 7-billion-parameter open-source Vision-Language-Action (VLA) model released in 2024 by a Stanford / UC Berkeley / Toyota Research Institute / Google DeepMind collaboration. Trained on 970,000 robot demonstrations from the Open X-Embodiment dataset, it pairs a Llama 2 language model backbone with a dual visual encoder that fuses DINOv2 spatial features with SigLIP semantic features. Given a camera image and a natural-language instruction, the model predicts 7-dimensional robot control actions as discrete tokens. OpenVLA was specifically built to address the closed nature of prior VLA models such as RT-2 and to provide best practices for fine-tuning on commodity GPUs. Despite being seven times smaller, it reportedly outperforms RT-2-X (55B) by roughly 16.5 percentage points across 29 manipulation tasks and multiple embodiments. The full codebase, training notebooks, and weights are openly released, making OpenVLA a foundational reference for any team building a generalist robot policy. Typical use cases include tabletop manipulation on Franka, WidowX, and other research arms, with extensive community support for LoRA-style fine-tuning to new platforms.

fine-tuning, Llama 2, Manipulation, Open-Source, Open X-Embodiment, and VLA
Stanford / UC Berkeley / Toyota Research Institute / Google DeepMind (collaboration)
Vision-Language-Action Models
United States
Open source (MIT)
Research prototype
7B
On-device possible (~16 GB GPU VRAM for inference; A100 recommended for fine-tuning)
Python SDK
Documentation URL
GitHub URL
Kim et al., 'OpenVLA: An Open-Source Vision-Language-Action Model' (CoRL 2024) — arXiv:2406.09246
Used in research demos on Franka Panda, WidowX, and Google robot arms; widely fine-tuned in academic labs

Recent Posts

  • Versius Plus and the Gynecology Frontier: CMR Surgical’s FDA Submission and the Future of U.S. Surgical Robotics
  • Autonomous Drone Inspection in 2026: How Industrial Drones Are Replacing Human Inspectors
  • Amazon Sequoia: The Next-Generation Warehouse Robot Arriving in 2026
  • Pudu Robotics Raises 50M and Pivots to Industrial AMR Market in 2026
  • Rovex and BayCare Partner to Bring Hospital Transport Robots to Morton Plant (2026)

Recent Comments

No comments to show.

Archives

  • May 2026
  • April 2026
  • October 2024
  • August 2024
  • March 2024
  • February 2024
  • January 2024
  • December 2023

Categories

  • Blog
  • News
  • Podcast

Agriculture & Farming
AI Software & SaaS
Autonomous Systems
Aviation & Aerospace
Civil Engineering & Geospatial
Construction & Infrastructure
Defense & Security
Energy & Renewables
General Purpose & Humanoid
Hardware & Components
Healthcare & Medical
Hospitality & Wellness
Industries
Logistics & Warehousing
Manufacturing & Industrial
Product Type
Public Safety & Emergency
R&D & Developer Tools
Robotics Integration & Services
Robots & Automated Systems

Let's get in touch with us

At the intersection of innovation and technology, we are pioneers crafting a landscape for the digital age.
Please enable JavaScript in your browser to complete this form.
Name *
Loading

Contact Us

Call Us

+44 (0) 1483 870170

Email:

info@askdroid.com

Follow Us on

Copyright © 2026, Askdroid. All Rights Reserved
  • Home
    • About Us
    • Contact us
  • AI
  • Robotics
  • Podcasts
  • News
  • Blog
Change Location
Find awesome listings near you!