{"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":""}
 
 
New 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.
Featured
New 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
Â