Genie 3: A new frontier for world models — Google DeepMind
Today we are announcing Genie 3, a general purpose world model that can generate an unprecedented diversity of interactive environments. Given a text prompt, Genie 3 can generate dynamic worlds that you can navigate in real time at 24 frames per second, retaining consistency for a few minutes at a resolution of 720p.
August 5, 2025 Models Jack Parker-Holder and Shlomi Fruchter Today we are announcing Genie 3, a general purpose world model that can generate an unprecedented diversity of interactive environments. Given a text prompt, Genie 3 can generate dynamic worlds that you can navigate in real time at 24 frames per second, retaining consistency for a few minutes at a resolution of 720p. Towards world simulation At Google DeepMind, we have been pioneering research in simulated environments for over a decade, from training agents to master real-time strategy games to developing simulated…
saved by
related reading
- Google’s Genie 3 Is What Science Fiction Looks Likethealgorithmicbridge.com
- Genie 2: A large-scale foundation world modeldeepmind.google
- Genie: Generative Interactive Environmentsdeepmind.google
- [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
- The Waymo World Model: A New Frontier For Autonomous Driving Simulationwaymo.com
- RTFM: A Real-Time Frame Model | World Labsworldlabs.ai
- Marble: A Multimodal World Model | World Labsworldlabs.ai
- [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
- Generalist - GEN-0 / Embodied Foundation Models That Scale with Physical Interactiongeneralistai.com
- Generalist - GEN-1: Scaling Embodied Foundation Models to Masterygeneralistai.com
- GEN-1.5: Embodied Foundation Models are One-Shot Learners - Generalist AIgeneralistai.com
- A Functional Taxonomy of World Models - Dr. Fei-Fei Lidrfeifei.substack.com