Odyssey
odyssey.ml · 110 words · saved by 1 readers
Odyssey is an AI lab pioneering general world models: causal, multimodal systems that learn to understand and simulate the world.
What if AI could learn from the world? What is Odyssey-2? A world simulator that dreams in video Prompt with an image or text, and Odyssey-2 rolls out minutes-long interactive simulations A Nascent World Simulator Odyssey-2 is early, but it's learned from decades of video to simulate the world Odyssey-2 streams multi-minute simulations, not 10 second clips What makes Odyssey-2 different? Odyssey-2 generates long-running interactive simulations in real-time Traditional video models Fixed 10 second clips Takes minutes to generate No interactivity Odyssey-2 Generated in 50ms…
saved by
related reading
- Odysseyodyssey.systems
- Interaction Models: A Scalable Approach to Human-AI Collaboration - Thinking Machines Labthinkingmachines.ai
- The Model That Dreams the Worldmoe-capital.com
- World Models | Rohit Bandarurohitbandaru.github.io
- World Models: Computing the Uncomputablenotboring.co
- Project Edentripo3d.ai
- Voyager | An Open-Ended Embodied Agent with Large Language Modelsvoyager.minedojo.org
- Are Video Generation Models World Simulators? · Artificial Cognitionartificialcognition.net
- Midcentury | Data and Simulation Infra for Physical AImidcentury.xyz
- Marble: A Multimodal World Model | World Labsworldlabs.ai
- Causal Video Models Are Data-Efficient Robot Policy Learners | Rhoda AIrhoda.ai
- A Functional Taxonomy of World Models - Dr. Fei-Fei Lidrfeifei.substack.com