A world model is an AI system that learns a predictive representation of how an environment changes over time. It can use observations, actions, or language to estimate future states and possible outcomes before an agent acts. World models support planning in model-based reinforcement learning, robotics, embodied AI, autonomous driving, and interactive simulation. This site catalogs these systems with model records, research papers, benchmark context, and source links. Start with the world models database, compare systems on the leaderboard, or read the Performance Index methodology.
Editorial definition preserved directly in static HTML.
The capacity of an interactive world model to maintain a coherent state of the environment over extended time horizons. Genie 3 introduced explicit world memory of up to one minute, allowing scenes to remain consistent as agents revisit them.
World Memory is a glossary concept in the concepts layer of the world models knowledge base.
Static glossary definition snapshot for crawlers and no-JS readers.
| Attribute | Value |
|---|---|
| Term | World Memory |
| Category | Concepts |
| Definition | The capacity of an interactive world model to maintain a coherent state of the environment over extended time horizons. Genie 3 introduced explicit world memory of up to one minute, allowing scenes to remain consistent as agents revisit them. |
| Related Models | 2 |
| Related Research | 1 |
| Topic | Summary |
|---|---|
| Foundation World Models | How foundation world models such as Cosmos and Genie 2 bring large-scale learned simulation to robotics, autonomous driving, and physical AI. |
| Term | Category | Definition |
|---|---|---|
| Latent Dynamics | Architecture | The learned transition function within a latent space that predicts how hidden states evolve over time in response to actions. Latent dynamics models avoid computationally expensive pixel-level predictions by operating in compressed representation space. |
| Action Conditioning | Architecture | A property of a world model whose predictions of future states depend explicitly on the action taken by the agent. Action-conditioned models support interactive simulation and planning, distinguishing true world models from passive video generators. |
Short extractable summary preserved directly in static HTML.
Editorial provenance and refresh policy preserved directly in static HTML.
Published by world-models.io editorial board.
Lead editor Bernard Grenat.
This glossary page publishes stable definitions linked to related models, research topics, and primary-source context.
Each editorial page is assembled from primary sources, normalized into extractable summaries, checked for factual drift, and reviewed before publication or major refreshes. Last reviewed: 2026-09-27.
Pages are refreshed when a new paper, benchmark, release, architecture update, or stronger primary source materially changes the answer a reader or AI system should retrieve.
Each page links back to relevant primary sources and keeps a stable canonical URL so readers can verify claims, trace context, and reference the most up-to-date version. See the editorial policy.
Primary sources related to this term, surfaced directly in static HTML.