hotai.news
← Back to AI Newsflash
AI News / Event details
x.com · Published

Google releases Gemini Robotics 2.5 vision-language-action model

Automated summary · Based on collected summaries; not individually verified
Prepared by HotAI

What happened

Google has released Gemini Robotics 2.5, describing it as the strongest vision-language-action (VLA) model to date. The model expands the breadth and speed of skills robots can learn, helping them transition from laboratory settings to real-world environments. It is now being deployed to its robot partners.

Background

What is Gemini Robotics? Action models and embodied reasoning

Gemini Robotics is Google DeepMind’s model family for physical robots. Vision-language-action models convert visual and language inputs into motor control, while ER models focus on spatial understanding and planning. As of November 11, 2026, the official model page lists Robotics 2.5, ER 2, and On-Device 2. Controlling a robot also requires integration with its interfaces and sensors.

What Is Gemini? Multimodal Models and App Features

Gemini is Google’s generative AI model family, with particular versions accepting text and multiple media types. Gemini Apps is the application for chatting and uploading files. Multimodality must distinguish input types from generated content. For example, Gemini 4 Argon accepts audio and video but outputs text; understanding video does not imply generating it. Readers seeking local model weights should also distinguish the separate Gemma family.

Reading notes

The event summary comes from collected excerpts. Background passages quote existing HotAI articles to explain terms and do not establish new facts about this event. Check the original sources for product results, conditions and subsequent updates.

Original source

Sources and collection timeline

SourceReport titleOriginal publication timeCollected by HotAI
x.comGoogle releases Gemini Robotics 2.5 vision-language-action model2026-11-12 00:082026-11-12 00:32