The making of Starchild-1
Odyssey researchers Jeff Hawke, Jenny Seidenschwarz, and Vighnesh Birodkar discuss the core ideas and technical challenges behind Starchild-1
Our most recent news
What we've been working on recently
Our most recent news
What we've been working on recently
World Model
Odyssey-3
Our most powerful foundation world model yet, materially advancing the state-of-the-art in physical accuracy of world models
World Model
Agora-2
A multi-agent world model, enabling multiple participants—human or AI—to share and interact within the same world simulation in real-time
Reinforcement Learning
PROWL-2
PROWL-2 is the first framework in which a team of agents and its world model each learn from their own curriculum, continually and within a single training loop
World Model
Starchild-1
A step beyond world models that learn only from visual observation, toward systems that learn from richer multimodal interaction with the world
World Model
Odyssey-3
Our most powerful foundation world model yet, materially advancing the state-of-the-art in physical accuracy of world models
World Model
Agora-2
A multi-agent world model, enabling multiple participants—human or AI—to share and interact within the same world simulation in real-time
Reinforcement Learning
PROWL-2
PROWL-2 is the first framework in which a team of agents and its world model each learn from their own curriculum, continually and within a single training loop
World Model
Starchild-1
A step beyond world models that learn only from visual observation, toward systems that learn from richer multimodal interaction with the world
World Model
Odyssey-3
Our most powerful foundation world model yet, materially advancing the state-of-the-art in physical accuracy of world models
World Model
Agora-2
A multi-agent world model, enabling multiple participants—human or AI—to share and interact within the same world simulation in real-time
Reinforcement Learning
PROWL-2
PROWL-2 is the first framework in which a team of agents and its world model each learn from their own curriculum, continually and within a single training loop
World Model
Starchild-1
A step beyond world models that learn only from visual observation, toward systems that learn from richer multimodal interaction with the world
World Model
Odyssey-3
Our most powerful foundation world model yet, materially advancing the state-of-the-art in physical accuracy of world models
World Model
Agora-2
A multi-agent world model, enabling multiple participants—human or AI—to share and interact within the same world simulation in real-time
Reinforcement Learning
PROWL-2
PROWL-2 is the first framework in which a team of agents and its world model each learn from their own curriculum, continually and within a single training loop
World Model
Starchild-1
A step beyond world models that learn only from visual observation, toward systems that learn from richer multimodal interaction with the world