About
Research
News
Careers
Contact
Get API Access
A leading body of world model research
Our explorations at the frontier of world models
Odyssey-3
Odyssey-3 is a foundation world model that can power robots, drive cars, train AIs, and more
Read more →
CaliBench
CaliBench tests whether world models reproduce the true distribution of physical outcomes
Agora-1
A multi-agent world model that enables multiple participants to interact within the same simulation
Starchild-1
A multimodal world model that generates audio-visual simulations
PROWL-1
A RL-driven adversarial framework to improve world model performance
Odyssey-2 Max
A general world model that advances the state-of-the-art in physical accuracy
Odyssey-2 Pro
A general world model with open-ended inputs
Odyssey-2
Odyssey-2 Alpha
A general world model with navigation input
Odyssey-1
A world model with navigation input and stability
Explorer
A purpose-built world model for film and gaming
Research presentation
A missing form of intelligence
Odyssey's CTO Jeff Hawke presents on Odyssey's research at RAAIS 2026
Research panel
The making of Starchild-1
Odyssey researchers discuss the core ideas and technical challenges behind Starchild-1
The next frontier in AI
Hear from Odyssey researchers about why general-purpose world models are a world-changing technology
World Model
Our most powerful foundation world model yet, materially advancing the state-of-the-art in physical accuracy of world models
Learn More
A step beyond world models that learn only from visual observation, toward systems that learn from richer multimodal interaction with the world
Technical Report
A multi-agent world model, enabling multiple participants—human or AI—to share and interact within the same world simulation in real-time
Try Agora-1
Reinforcement Learning
A novel RL-driven adversarial framework where an RL agent explores game environments with the objective to improve world model performance
Read the Paper
Company
Information
Legal
World Models
