RT-2, published by Google DeepMind in July 2023, is widely credited as the first model to establish the VLA concept.
Â
Â
Â
Â
Octo is a transformer-based diffusion policy pre-trained on 800,000 robot episodes from the Open X-Embodiment dataset. It is deliberately lightweight,
GR00T (Generalist Robot 00 Technology) is NVIDIA’s open VLA family for humanoid robots, first announced at GTC 2025. It uses
Featured
Helix is a generalist VLA developed by Figure AI to control its humanoid robots. It uses a decoupled dual-system architecture.
Featured
Gemini Robotics brings Gemini’s multimodal reasoning into the physical world. It comprises two complementary models. Gemini Robotics is the vision-language-action
Featured
Skild Brain is a robotics foundation model from Skild AI, founded in 2023 by researchers Deepak Pathak and Abhinav Gupta.
Featured
?0.5 keeps the ?0 recipe — a vision-language-model backbone with a flow-matching action expert — but is built around generalisation
Â







