Gemini Robotics 1.5: Embodied Reasoning and Multi-Embodiment Action

https://is1-ssl.mzstatic.com/image/thumb/Podcasts211/v4/3a/6a/25/3a6a2521-e9c8-50fb-f24c-72997aa0376e/mza_16441109677767728869.jpg/600x600bb.jpg

Intelligence Unbound

Fourth Mind

44 episodes

4 days ago

Unpacking the questions shaping the next intelligence era. I am producing a fully AI-generated podcast that explores the influence of AI within various industries and examines significant technological breakthroughs.

Technology

RSS

All content for Intelligence Unbound is the property of Fourth Mind and is served directly from their servers with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.

Technology

https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_nologo/43986554/43986554-1751387264162-08d1b0cbbe5db.jpg

Gemini Robotics 1.5: Embodied Reasoning and Multi-Embodiment Action

Intelligence Unbound

13 minutes 27 seconds

1 month ago

Gemini Robotics 1.5: Embodied Reasoning and Multi-Embodiment Action

This episode dives deep on the Gemini-Robotics-1-5-Tech-Report report; significant advancement in generalist robots through the introduction of the Gemini Robotics 1.5 model family. This system features two core components: Gemini Robotics 1.5 (GR 1.5), a Vision-Language-Action (VLA) model that translates instructions into robot actions and supports multi-embodiment control, and Gemini Robotics-ER 1.5 (GR-ER 1.5), an enhanced Vision-Language Model (VLM) specialized in complex embodied reasoning and high-level task planning.