https://github.com/openvla/openvla

OpenVLA: An open-source vision-language-action model for robotic manipulation.
https://github.com/openvla/openvla

Last synced: over 1 year ago
JSON representation

OpenVLA: An open-source vision-language-action model for robotic manipulation.

• Host: GitHub
• URL: https://github.com/openvla/openvla
• Owner: openvla
• License: mit
• Fork: true (TRI-ML/prismatic-vlms)
• Created: 2024-06-13T21:47:02.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2025-03-23T23:41:01.000Z (over 1 year ago)
• Last Synced: 2025-03-24T00:28:22.850Z (over 1 year ago)
• Language: Python
• Homepage:
• Size: 76.2 KB
• Stars: 2,317
• Watchers: 23
• Forks: 296
• Open Issues: 35

Awesome Lists containing this project

• Awesome-Video-Robotic-Papers - Code
• awesome-llmops - OpenVLA - parameter open-source Vision-Language-Action model trained on 970K+ robot demonstrations from the Open X-Embodiment dataset for generalist robotic manipulation. |  | (Model / Robotics Foundation Model)
• awesome-open-source-robotics - OpenVLA
• awesome-vision-ai-stack - OpenVLA - Vision-language-action direction for robotics. (Agents, Grounding, and Robotics / Robotics-oriented projects)
• awesome-robotics - OpenVLA - language-action model for generalist manipulation. | (🧩 Foundation Models for Robotics)
• Awesome-RL-VLA - OpenVLA - Open-source VLA model (🔗 Useful Resources / Base VLA Models)
• awesome-robot-vision - OpenVLA - source 7B-parameter vision-language-action model for robot manipulation; achieves strong results across diverse tasks. | [GitHub](https://github.com/openvla/openvla) · [arXiv](https://arxiv.org/abs/2406.09246) · [Website](https://openvla.github.io/) | (Robot Learning Policies with Visual Input / Large Robot Foundation Models)