Meet Llama4 Scout & Maverick: the next generation of Llama 🦙 🚀. Download: llama.com/llama-download… Blog: ai.meta.com/blog/llama-4-m…

🌎🌏🌍 We are organizing a workshop on Building Physically Plausible World Models at ICML Conference 2025! We have a great lineup of speakers, and are inviting you to submit your papers with a May 10 deadline. Website: physical-world-modeling.github.io

📢 We are organizing a workshop at ICML on Building Physically Plausible World Models. Join us by submitting your cool papers in this area 😃

1/ Model architectures have been mostly treated as fixed post-training. 🌱 Introducing Grafting: A new way to edit pretrained diffusion transformers, allowing us to customize architectural designs on a small compute budget. 🌎 grafting.stanford.edu Co-led with Michael Poli

🤖🌎 We are organizing a workshop on Robotics World Modeling at Conference on Robot Learning 2025! We have an excellent group of speakers and panelists, and are inviting you to submit your papers with a July 13 deadline. Website: robot-world-modeling.github.io

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

watch out!

This is game engine 2.0. Some day, all the complexity of UE5 will be absorbed by a data-driven blob of attention weights. Those weights take as input game controller commands and directly animate a spacetime chunk of pixels. Agrim and I were close friends and coauthors back at

real-time interactive really feels magical

absolutely love this world!

genie3 taking control of a world generated by veo3

good knight has good memory

another amazing capability: blending two worlds, one specified by the prompt, and another specified by the starting frames. the model does an amazing job even when the two are very very different!

interactive minecraft, multi-player, real-time, would unlock a lot of cool research!

Excited that we are launching Gemini Robotics 1.5, a pair of models that can work together to solve long horizon tasks. Gemini Robotics-ER 1.5, the high-level reasoning brain, is available for public preview in AIStudio and Gemini API for robotics developers around the world: