RS at Google DeepMind and Honorary Lecturer at UCL. Building general world models to solve AGI :)
Jack Parker-Holder
From first person real world scenes, to third person driving environments, Genie 2 generates worlds in 720p 📷. Given an image, Genie 2 simulates world dynamics, creating a consistent environment playable with keyboard and mouse inputs ⌨️.
deepmind.google/discover/blo...
If you have not seen this yet, you are missing a lot!
Genie 3 by Google DeepMind was unveiled today &delivers in abundance.
Of course my fav example is ego x world model.
It is video gen x modeling "out of the frame".
Many congrats @jparkerholder.bsky.social & team
deepmind.google/discover/blo...
Jack Parker-Holder
Genie 2 can also turbocharge environment design for humans, making it possible to step in and play from concept art 🎨, such as the beautiful work below from one of our rockstar designers.
Finally, this would not have been possible without the amazing diversity of incredible collaborative people at Google DeepMind 🫶🫶🫶. Shout out to the team that made this possible, from the Genie 2 team, the Generalist Agents team and SIMA. Exciting times ahead!!
Introducing 🧞Genie 2 🧞 - our most capable large-scale foundation world model, which can generate a diverse array of consistent worlds, playable for up to a minute. We believe Genie 2 could unlock the next wave of capabilities for embodied agents 🧠.
To illustrate the potential of this for embodied agents, consider the world below, generated using Imagen 3. The SIMA team tested whether their latest agent could follow language instructions, such as going to the red or blue door 🚪.
🤯🤯🤯… And just like that, we have a path to unlimited environments for training and evaluating our embodied agents! We tried creating another world with three arches, and once again Genie 2 was able to simulate the world and SIMA solved the task ✅.
Dima Damen
Video
Now that @jeffclune.bsky.social and @joelbot3000.bsky.social are here, time for an Open-Endedness starter pack.
go.bsky.app/MdVxrtD
Jack Parker-Holder
Jack Parker-Holder
Jack Parker-Holder
Jack Parker-Holder
Jack Parker-Holder
Tim Rocktäschel
Generating unlimited diverse training environments for future general agents
