
Real-world models are here! Stoked to share how we're bringing real-world locations to life by integrating Street View into Genie. Try it now at labs.google/fx/projectgenie and read the blog for more info: blog.google/innovation-and-a…

ex-google brain and deepmind. phd in neural nonsense from stanford.

Real-world models are here! Stoked to share how we're bringing real-world locations to life by integrating Street View into Genie. Try it now at labs.google/fx/projectgenie and read the blog for more info: blog.google/innovation-and-a…

we're hiring research interns at GDM NYC! come spend a summer in NYC with a really fun crew (Noah Snavely, Zhengqi Li, Sai Bi, Andrew Liu, Linyi Jin, Stan Szymanowicz, Sherwin Bahmani, Philipp Henzler, Amir Hertz, and many more) DM if interested! (pic: view from the office)

I gave Fable 5.2 a PDF of one of Leonardo da Vinci’s 500-year-old notebooks and it made his inventions real for me to interact with. Such an exciting time for education. Anything from history that’s been stuck on a page can now be something you explore.

Checkout what we’ve been cooking 🧞♂️
This is Genie 4, our most realistic and interactive world model yet. 🌐 Explore dynamic environments in real time to see how the scene responds, sounds, and how the people in it move, react, and speak.

Genie 4 brings realistic dynamics and sound to realtime interactive world models! 🧞🚀🎶 This was the last project I worked on at Google 🥲, and the quality and dynamics are still so much better than the 3D creations from the latest frontier models. Bridging this gap to enable accurate, efficient, and high-quality simulations of the real world remains an open research challenge that is key to unlocking useful physical intelligence. Congrats to the whole team, and have fun exploring with Genie 4!
This is Genie 4, our most realistic and interactive world model yet. 🌐 Explore dynamic environments in real time to see how the scene responds, sounds, and how the people in it move, react, and speak.

We're hiring at SpAItial 🚀🚀🚀 Want to build AI that generates 3D worlds and understands their physics? 15 roles in London & Munich: 🧠 RS: World Models · 3D Diffusion · 3D Recon · Robot Learning 🛠️ RE: World Models · 3D Recon · Graphics ⚡ ML Infra · Inference Join us 👇

Woohoo big congrats to @KarlDeisseroth et al! Optogenetics is such an important tool for neuroscience. I was lucky to start off my PhD working with @logangrosenick @broxtronix and other great folks in the D-lab burning GPUs before it was cool on lightfield microscopy (cell.com/cell/fulltext/S0092… & biorxiv.org/content/10.1101/…)
BREAKING NEWS The 2026 #NobelPrize in Physiology or Medicine has been awarded to Karl Deisseroth, Peter Hegemann and Georg Nagel “for their discoveries concerning light-gated ion channels and optogenetics.”

Congratulations to our first #NobelPrize laureate of 2026 🎉 Early this morning Karl Deisseroth found out he was awarded this year's Nobel Prize in Physiology or Medicine. He seems very happy with the news!

I've been on a Blender kick with Opus 5.5. Its better 3D modeling and vision mean you can build an entire world from a single prompt. Historically accurate San Francisco Market street in 1906, pre-earthquake

I just realized Opus 5.5 can use Blender to make claymations with just a single prompt in claude dot ai now


❤️🚲💑
Got married in the park (in a bicycle parade) last weekend and @peterhartlaub put together such a lovely article about it! sfchronicle.com/totalsf/arti…

We are hiring research scientists and engineers🧑🔬 on the Gemini Omni team! Both in the US (Mountain View / SF) and Europe (London / Zürich). Apply here: google.com/about/careers/app…

Atlas is live! A spatial foundation model, trained in-house from scratch. After shipping RTFM last year, I was convinced a single camera-conditioned model could unify most spatial generation tasks. Atlas is that bet at scale. The core idea👇
Introducing Atlas: The world's first multimodal world model that generates image and video frames with pixel-perfect camera control and reconstructs them in 3D. Model the world, move the camera, and simulate space & time.

Two years later our first video model - FLUX 3 Video - is finally released🥹. This is such a strong, fun and versatile model made by the best team in the world @bfl_ai. We will add further variants and generation from references in the near future. I am also super excited about the upcoming open weight, action prediction and image variants of FLUX 3.

Fortunate to work with this team every day, ACT-2 is a big leap. Working on real Solves is a blast. Next Stop: Recursive Solve Improvement
Introducing ACT-2 Preview The first robotics model to unify broad generalization with high reliability. A single fine-tuning example can teach Memo a new behavior that generalizes. Zero shot, real unseen homes, 99% success rate.