Here's a nice "proof without words": The sum of the squares of several positive values can never be bigger than the square of their sum. This picture helps make sense of how ℓ₁ and ℓ₂ norms regularize and sparsify solutions (resp.). [1/n]

Video, meet audio. 🎥🤝🔊 With Veo 3, our new state-of-the-art generative video model, you can add soundtracks to clips you make. Create talking characters, include sound effects, and more while developing videos in a range of cinematic styles. 🧵

Veo3 is out! deepmind.google/models/veo/ This model is awesome! It now generates audio as well as video. I'm really impressed by the background audio and music, and the synchronization of sound effects to the video. Try it out using Flow! labs.google/flow/about

Reference-powered Veo lets you go for walks in the Himalayas with your dog!

image ⇒ video ⇒ 3D/4D I'm super excited to build the next generation of models that understand and can imagine the world like we do at SpAItial with amazing people. Sounds fun? We are hiring! spaitial.ai

Bolt3D is accepted to #ICCV2025 🥳 see you in Hawaii!

For everyone interested in precise 📷camera control 📷 in transformers [e.g., video / world model etc] Stop settling for Plücker raymaps -- use camera-aware relative PE in your attention layers, like RoPE (for LLMs) but for cameras! Paper & code: liruilong.cn/prope/

Modern AI is confined to the digital world. At Skild AI, we are building towards AGI for the real world, unconstrained by robot type or task — a single, omni-bodied brain. Today, we are sharing our journey, starting with early milestones, with more to come in the weeks ahead.

Last year, my ring bearer was a Skild robot. Excited to see how far they've come!!

Our team at Google DeepMind Foundational Research has an opening for a full-time Research Scientist! Areas of Interest are Multimodal, 3D and Spatial Reasoning, Self-improving Agents. Looking for candidates with strong publications at top ML and CV conferences. Email:

Excited to introduce Genie 3, our general purpose world model that creates interactive, playable environments from any text prompt. It can generate dynamic worlds at 720p and 24 FPS, with each frame created in response to user actions in *real-time*.

The generative 3D/video corner of Google DeepMind that I run in is now hiring research scientists. If you're on the market for full-time roles in that space, email us! [email protected]