Serkan Cabi

[Google DeepMind @GoogleDeepMind]

One brain. For any robot. 🤖

We’re launching Gemini Robotics 2: our next-generation physical AI bringing full body intelligence to humanoids, advanced dexterity, multi-robot teamwork and more.

[Demis Hassabis @demishassabis]

Gemini Robotics 2 is here, with our new suite of models, robots can now reason through every movement to manage tasks that weren’t possible before, like tying delicate knots - and even team up to solve complex workflows. Huge congrats to the robotics team on this great milestone!

[Google DeepMind @GoogleDeepMind]

We’re scaling up robotics in Europe. 🤖

Our Robotics Accelerator is tailored for startups and designed to bridge the gap between technology and business, powering the next generation of physical agents.

[Caden Lu @jyluxx]

Interacting with Gemini Robotics 1.5 is so fun! Our Embodied Reasoning model planned the multi-step task and orchestrated our Vision Language Action model for precise execution!

[Ksenia Konyushkova @ks_konyushkova]

Interacting with robots just got easier with the agentic capabilities of Gemini Robotics 1.5. Talk to the robot or show it things! See how the ER model reads a handwritten list on paper and packs the tools for the job.

[Ksenia Konyushkova @ks_konyushkova]

Meet Gemini Robotics 1.5! Our ER model brings embodied reasoning to the real world. It understands high-level goals like "pack ingredients for mushroom risotto" with planning & success detection.
Also, check out the cool "active vision" behavior – observing the action up close!🔍

[Norman Di Palo @normandipalo]

This is a remarkable result, let me explain.

These tasks were only shown on a single robot embodiment. With the advancements of Gemini Robotics 1.5, *robots can learn from data from other robots*

You taught a humanoid to pack gifts? Now a bi-arm Franka knows how to do it too

[Konstantinos Bousmalis @bousmalis]

Another agentic example and one of the demos we showed @corl_conf! Loved demonstrating the capabilities of Gemini Robotics 1.5 all week and it was fun to see how excited people were to interact with it in their own language with their own writing, drawings, and objects!

[Konstantinos Bousmalis @bousmalis]

One of the coolest features in our newest release for Gemini Robotics 1.5 was using the wrist camera of one of the arms of our bi-arm Franka robot for active vision! Without this capability the model would not have enough visibility to solve some of our most dexterous tasks.

[Konstantinos Bousmalis @bousmalis]

You have to watch this! For years now, I've been looking for signs of nontrivial zero-shot transfer across seen embodiments. When I saw the Alohas unhang tools from a wall used only on our Frankas I knew we had it! Gemini Robotics 1.5 is the first VLA to achieve such transfer!!

[Serkan Cabi @serkancabi]

We just released our new generation of Gemini Robotics. It can control multiple robots, plan and execute more steps and even transfer skills from one robot to another.

[Google DeepMind @GoogleDeepMind]

We’re making robots more capable than ever in the physical world. 🤖

Gemini Robotics 1.5 is a levelled up agentic system that can reason better, plan ahead, use digital tools such as @Google Search, interact with humans and much more. Here’s how it works 🧵

[Serkan Cabi @serkancabi]

We helped making gravitational wave detection more sensitive. It was such a pleasure to be part of this project where physics meets machine learning. Google DeepMind is a wonderful and rare place where projects like this become possible.

[Google DeepMind @GoogleDeepMind]

We’re helping to unlock the mysteries of the universe with AI. 🌌

Our novel Deep Loop Shaping method
published in @ScienceMagazine could help astronomers observe more events like collisions and mergers of black holes in greater detail, and gather more data about rare space phenomena. 🧵

[Dhruv Shah @shahdhruv_]

Yesterday, we live demo-ed a “generalist” VLA for (I think) the first time ever to a broad audience @RoboticsSciSys.

Bring any object. Ask anything.

New environment, new instructions, no fine-tuning. Just impeccable vibes! ✨

[Google DeepMind @GoogleDeepMind]

We’re bringing powerful AI directly onto robots with Gemini Robotics On-Device. 🤖

It’s our first vision-language-action model to help make robots faster, highly efficient, and adaptable to new tasks and environments - without needing a constant internet connection. 🧵

[Oriol Vinyals @OriolVinyalsML]

Hello Gemini 2.5 Flash-Lite! So fast, it codes *each screen* on the fly (Neural OS concept 👇).

The frontier isn't always about large models and beating benchmarks. In this case, a super fast & good model can unlock drastic use cases.

Read more: https://t.co/kbkC8CtVYb

[Convergent Research @Convergent_FROs]

we made a map!

https://t.co/YtwACsfSiP is a tool we built to help you explore the landscape of R&D gaps holding back science - and the bridge-scale fundamental development efforts that might allow humanity to solve them, across almost two dozen fields

[Serkan Cabi @serkancabi]

LLMs can now touch the world.
Finally, we are sharing what we have been working on for a while. There is so much to explore about what Gemini Robotics can do. Check out the videos and the tech report.
https://t.co/3eDqV6gfT8

[Google DeepMind @GoogleDeepMind]

Meet Gemini Robotics: our latest AI models designed for a new generation of helpful robots. 🤖

Based on Gemini 2.0, they bring capabilities such as better reasoning, interactivity, dexterity and generalization into the physical world. 🧵 https://t.co/n230QbZpnd

[Google DeepMind @GoogleDeepMind]

Introducing 2️⃣ new AI systems for robotics:

🤖 ALOHA Unleashed to perform two-armed manipulation tasks
🦾 DemoStart to control a multi-fingered robotic hand

They learned to tackle a range of actions requiring dexterity. Here's how. 🧵 https://t.co/0EtlvsNWjZ

[Serkan Cabi @serkancabi]

Best internet rabbit hole I've been to recently. Thanks @CJHandmer
https://t.co/wg94eblEtv