2 dépôts
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
Trouvez les meilleurs dépôts grâce à l'IA.Nous recherchons les dépôts les plus pertinents grâce à l'IA.
- nvidia/isaac-gr00t
NVIDIA/Isaac-GR00T
6,222Voir sur GitHubProcesses multimodal inputs including natural language and camera images to generate motor commands for generalized robot manipulation.
Jupyter Notebook - openvla/openvla
openvla/openvla
5,305Voir sur GitHubOpenVLA 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
