Google DeepMind has just revealed Genie 2, a world-modelling AI capable of creating 3D worlds and sustaining those environments for significantly longer. It's a diffusion model that generates images as the player (either a human being or another AI agent) moves through the world the software is simulating. All it needs to start is a single image prompt either generated by AI or from a real-world photo. There are limitations: DeepMind says the model can generate "consistent" worlds for up to 60 seconds, with the majority of the examples the company shared on Wednesday running for significantly less time -- most videos are between 10 to 20 seconds long. Image quality also softens and comes undone the longer Genie 2 needs to maintain the illusion of a consistent world.

AI algorithms capable of generating a simulated environment in real-time -- represent one of the more impressive applications of machine learning. In the last year, there's been a lot of movement in the field, and to that end, Google DeepMind announced Genie 2 on Wednesday. Where its predecessor was limited to generating 2D worlds, the new model can create 3D ones and sustain them for significantly longer. Genie 2 isn't a game engine; instead, it's a diffusion model that generates images as the player (either a human being or another AI agent) moves through the world the software is simulating. As it generates frames, Genie 2 can infer ideas about the environment, giving it the capability to model water, smoke and physics effects -- though some of those interactions can be very gamey.

It took just a few years for AI art to evolve from text to 2D imagery to generated 3D video. Today, it's taken the next step with Google's Genie 2, which can generate playable 3D game worlds that are constructed on the fly, all from a simple text prompt. Google's Genie 2 is the evolution of its Generative Interactive Environments, which uses AI to construct new, interactive environments on the fly. Genie 1, which Google released in February, could construct 2D environments. Now, Genie 2, which Google announced today, takes that into 3D space.

Protein diffusion models have emerged as a promising approach for protein design. One such pioneering model is Genie, a method that asymmetrically represents protein structures during the forward and backward processes, using simple Gaussian noising for the former and expressive SE(3)-equivariant attention for the latter. In this work we introduce Genie 2, extending Genie to capture a larger and more diverse protein structure space through architectural innovations and massive data augmentation. Genie 2 adds motif scaffolding capabilities via a novel multi-motif framework that designs co-occurring motifs with unspecified inter-motif positions and orientations. This makes possible complex protein designs that engage multiple interaction partners and perform multiple functions. On both unconditional and conditional generation, Genie 2 achieves state-of-the-art performance, outperforming all known methods on key design metrics including designability, diversity, and novelty. Genie 2 also solves more motif scaffolding problems than other methods and does so with more unique and varied solutions. Taken together, these advances set a new standard for structure-based protein design.