2 Repos
Awesome GitHub RepositoriesAction Output Models
Processes multimodal inputs including natural language and camera images to generate motor commands for generalized robot manipulation.
Distinct from Vision-Language Models: Distinct from Vision-Language Models: extends vision-language processing to generate motor commands (action output), not just visual and linguistic understanding.
Explore 2 awesome GitHub repositories matching artificial intelligence & ml · Action Output Models. Refine with filters or upvote what's useful.
Awesome Action Output Models GitHub Repositories
Finde die besten Repos mit KI.Wir suchen mit KI nach den am besten passenden Repositories.
- nvidia/isaac-gr00t
NVIDIA/Isaac-GR00T
6,222Auf GitHub ansehenProcesses multimodal inputs including natural language and camera images to generate motor commands for generalized robot manipulation.
Jupyter Notebook - openvla/openvla
openvla/openvla
5,305Auf GitHub ansehenOpenVLA is a vision-language-action model and framework designed for general-purpose robotic manipulation. It provides a robotic policy training framework and a control inference engine that map visual and textual inputs to robotic control actions, enabling zero-shot instruction following on hardware. The project includes a robotics dataset pipeline for standardizing diverse trajectory data and managing dataset mixtures. It supports large-scale model training through distributed GPU compute and sharded data parallelism, alongside parameter-efficient adaptation for fine-tuning models to new ta
Maps visual and textual inputs to tokenized action sequences for general-purpose robotic manipulation.
Python
