Introducing Magenta RealTime, our open weights live music model! Like Lyria RealTime, this model provides the user continuous control of the musical flow 🌊. We will be sharing some of our favorite ways to extend these models over the next few weeks. Can't wait to see what you

Today Google releases an open weights, live performance oriented music model magenta.withgoogle.com/magenta-realti… Check it out, super fun to play with!

Want to work on cutting-edge #AI? We have several fully-funded 𝐏𝐡𝐃 & 𝐏𝐨𝐬𝐭𝐃𝐨𝐜 𝐨𝐩𝐞𝐧𝐢𝐧𝐠𝐬 in our Visual Computing & AI Lab in Munich! Apply here: application.vc.in.tum.de Topics have a strong focus on Generative AI, 3DGs, NeRFs, Diffusion, LLMs, etc.

Separately from my Google role, I'm excited to help Laude Institute identify and fund non-profit computer science research to have a major impact in the world, with Andy Konwinski and fellow board members Joelle Pineau and Dave Patterson.

Very excited to be helping out with this!

demo combining gaussian splat rendering from spark with a collider mesh baked out from the gaussians, using rapier physics in Three.js

Why More Researchers Should be Content Creators Just trying something new! I recorded one of my recent talks, sharing what I learned from starting as a small content creator. youtu.be/0W_7tJtGcMI We all benefit when there are more content creators!

Imagen 4 is now available via AI Studio for developers. Get your images, now via minimal python code! ai.google.dev/gemini-api/doc…

Building on more than 10 years of robotics research and engineering at Google DeepMind, Google Research and Google AI, we're delighted to announce our Gemini Robotics On-Device system. A really capable vision-language-action model that can run entirely without network access. ⬇️

Porting over some HLSL point cloud shaders over to spark, a gaussian splatting renderer for Three.js. Some of the effects look a bit messy with 3DGS, but fun to play around with! Also using their new depth of field here which looks really nice. Demo coming soon!

if you know how to code, and want to learn AI, this is what you should do: lucky for you the field has gotten *less* deep and much easier to learn about over the last few years. most lab roles require specific knowledge (model training, CUDA kernels, etc.). each takes ~18 months

Say hello to the gemini-cli, a local CLI to help you build and maintain software with 1,000 free Gemini 2.5 Pro requests per day : )

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

Calling all students in 🇺🇸🇬🇧🇯🇵🇮🇩🇧🇷 Still time to sign up and get Google Gemini App + a full year FREE of the Google AI Pro plan, do it before the June 30th deadline 👇

High quality image editing no longer needs closed models We release FLUX.1 Kontext [dev] - an open weights model for proprietary-level image editing performance. Runs on consumer chips. ✓ Open weights available ✓ Best in-class performance ✓ Self-serve commercial licensing

FLUX.1 Kontext [dev] is out, which means we can train LoRAs for it, which means we can give anyone a broccoli haircut. Link in the thread 👇

So about a month ago, Percy posted a version of this plot of our Marin 32B pretraining run. We got a lot of feedback, both public and private, that the spikes were bad. (This is a thread about how we fixed the spikes. Bear with me. )

Check out the blog to see how to create a dataset for the FLUX.1 Kontext [dev] trainer blog.fal.ai/announcing-flu… Short answer is you want a lot of pairs of images that show how to make the edit. This is tricky to find in the wild, so we explain how to utilize Kontext itself to

🚀 Career Update After years pushing the boundaries of Generative AI at some of the world’s top companies -> I’m going startup. I’ve joined Decart as a founding team member, leading the charge to build our San Francisco office from the ground up. decart.ai

good trajectory++ ⭐️🍿