Skip to content
View original post on X: GoogleOfficial
Published
Same story62/100

Google introduces Gemini Robotics 2.5, a vision-language-action model for robots

AIGoogle introduces Gemini Robotics 2.5, which it calls its most capable vision-language-action model to date. The company says it increases both the range of skills robots can learn and how quickly they learn them.
GoogleVerified on XOfficial
@Google
View on X

Introducing Gemini Robotics 2.5, our most capable vision-language-action (VLA) model to date. 🤖

It increases both the breadth of skills a robot can learn and the speed at which it acquires them — helping robots step out of the lab and into real-world environments.

Learn more about Gemini Robotics 2.5, now rolling out to our robotics partners 🧵

This story is featured in top picks: “Google DeepMind releases Gemini Robotics 2.5 for real-world robot dexterity”

Source details

Google · x.comPublished · added here

Original title: Introducing Gemini Robotics 2.5, our most capable vision-language-action (VLA) model to date. 🤖

Topics

Google / GeminiMultimodal AIEmbodied AIModel releases