AIbase
Home
AI Tools
AI Models
MCP
AI NEWS
EN
Model Selection
Tags
Multimodal Instructions

# Multimodal Instructions

Openvla 7b
MIT
OpenVLA 7B is an open-source vision-language-action model trained on the Open X-Embodiment dataset, capable of generating robot actions based on language instructions and camera images.
Image-to-Text Transformers English
O
openvla
1.7M
108
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase