{"hide_search_input":false,"hide_near_input":false,"input_size":"","bar_flex_wrap":"","bar_flex_wrap_md":"","bar_flex_wrap_lg":"","input_border":"","input_border_opacity":"","input_rounded_size":"","btn_bg":"","btn_rounded_size":"","btn_rounded_size_md":"","btn_rounded_size_lg":"","bg":"","mt":"","mr":"","mb":"3","ml":"","pt":"","pr":"","pb":"","pl":"","border":"","rounded":"","rounded_size":"","rounded_size_md":"","rounded_size_lg":"","shadow":"","css_class":""}
 
 
Vision-Language-Action Models
Google RT 2 1 768x362
Author Image

Google RT-2

RT-2, published by Google DeepMind in July 2023, is widely credited as the first model to establish the VLA concept.
Vision-Language-Action Models
Octo 1 768x364
Author Image

Octo

Octo is a transformer-based diffusion policy pre-trained on 800,000 robot episodes from the Open X-Embodiment dataset. It is deliberately lightweight,
Vision-Language-Action Models
NVIDIA Isaac GR00T 1 768x366
Author Image

NVIDIA Isaac GR00T

GR00T (Generalist Robot 00 Technology) is NVIDIA’s open VLA family for humanoid robots, first announced at GTC 2025. It uses
Featured
Vision-Language-Action Models
Figure Helix 1 768x361
Author Image

Figure Helix

Helix is a generalist VLA developed by Figure AI to control its humanoid robots. It uses a decoupled dual-system architecture.
Featured
Vision-Language-Action Models
Gemini Robotics 1 768x365
Author Image

Gemini Robotics

Gemini Robotics brings Gemini’s multimodal reasoning into the physical world. It comprises two complementary models. Gemini Robotics is the vision-language-action
Featured
Vision-Language-Action Models
Skild Brain
Author Image

Skild Brain

Skild Brain is a robotics foundation model from Skild AI, founded in 2023 by researchers Deepak Pathak and Abhinav Gupta.
Featured
Vision-Language-Action Models
Physical Intelligence 1 768x375
Author Image

Physical Intelligence ?0.5

?0.5 keeps the ?0 recipe — a vision-language-model backbone with a flow-matching action expert — but is built around generalisation
Simulation Platforms
Mujoco 768x373
Author Image

MuJoCo

MuJoCo (Multi-Joint dynamics with Contact) is a general-purpose physics engine designed for fast, accurate simulation of articulated systems — particularly
Vision-Language-Action Models
openvla 768x432
Author Image

OpenVLA

OpenVLA is a 7-billion-parameter open-source Vision-Language-Action (VLA) model released in 2024 by a Stanford / UC Berkeley / Toyota Research