Gemini Omni is a major leap in world understanding & multimodal editing! It can take photos, video & audio and build entirely new scenes. Over time it’ll be able to handle any input & any output - starting w/ video You can even give it your own videos & iterate on your ideas:

📢Our team @GoogleDeepMind is hiring a Research Scientist in MTV, NYC, or SF! Join us to push the frontiers of visual perception & spatial reasoning for multimodal foundation models like Gemini, Nano Banana, and more! Send your CV to gdm-3d-scene-understanding-job@google.com

Great use of Genie 3 from @waymo to create high-fidelity, interactive simulations of rare events that are nearly impossible to capture in the real world.

Super cool use case of Genie 3 simulations!

Incredibly excited to share our most recent work: the Waymo World Model. We leverage the broad world knowledge in Google DeepMind's Genie 3 and bring it into our most advanced autonomous driving simulator to date, with emergent transfer of world knowledge even into the 3D domain.

Exponential scaling ongoing – @Waymo has officially doubled our fully autonomous cities in a matter of weeks, reaching 10 cities with the newest additions of San Antonio and Orlando. This is a testament to the maturity and generalizability of the Waymo Driver, our deliberate, safety-first approach to scaling, and an important step as we prepare to serve more riders across more cities soon.

An early glimpse into the exciting future of fully generative AV world models ;)

🚗 Excited to present our paper "Drive&Gen: Co-Evaluating End-to-End Driving and Video Generation Models" at #IROS2025! 📅 Time: 10:55–11:00, Wed, 10.22.2025 📍 Room: 103C, Paper WeAT27.6 arxiv: arxiv.org/abs/2510.06209 #IROS2025 #WorldModels #AutonomousDriving #GenerativeAI

Can a single autonomous driving simulation world model jointly insert, delete, and control the behavior of all agents and traffic lights in a bird's-eye-view scene? For the first time, we show this is possible in SceneDiffuser , our CVPR '25 paper, w/ 60 second simulations.🧵

Genie 3 feels like a watershed moment for world models 🌐: we can now generate multi-minute, real-time interactive simulations of any imaginable world. This could be the key missing piece for embodied AGI… and it can also create beautiful beaches with my dog, playable real time

Exciting news: @Waymo is beginning public service on the Peninsula, starting with Palo Alto, Mountain View, and Los Altos! Initial service area below.