From World Models to World Action Models: A Concise Tutorial for Robotics
Classification
View four quadrants- Major category
- Related resources
- Quadrant
- Not applicable
- Architecture
- Not applicable
- Prediction paradigm
- Not applicable
- Subcategories
- Surveys & technical resources
- Source review status
- Verified from primary sources
Category review. This 2026 tutorial compares multiple prediction-to-action interfaces without introducing its own model. A modern tutorial is a related reference resource, not pre-2026 foundational research or a reusable model component. Reading evidence
Contribution
Rather than providing an exhaustive survey, this paper presents a concise tutorial on world models and world action models for robotics.
Abstract
Rather than providing an exhaustive survey, this paper presents a concise tutorial on world models and world action models for robotics. After reading the tutorial, readers should have a clear understanding of what constitutes a "world", how world models and world action models are defined, and what roles they play within robotic AI systems. The tutorial also develops a unified perspective for comparing representative approaches, such as World Labs' spatial intelligence models, Yann LeCun's JEPA framework, and NVIDIA's Cosmos platform, and clarifies how these models differ in their representations, predictive capabilities, and interaction mechanisms.
Affiliations
School of Automation and Intelligent Manufacturing, Southern University of Science and Technology, Shenzhen, China; LimX Dynamics, Shenzhen, China