New: the Timeline is live. Track world model releases, papers, and benchmark updates in real time.
world-models.io
The Knowledge Hub for AI World Models

World Models: A Comprehensive Survey

A structured overview of the world models landscape covering taxonomy, key systems across eras, open research challenges, and future directions toward foundation-scale world simulation.

robotics model-based-rl simulation embodied-ai

Research Snapshot

Static research summary generated from local editorial content.

AttributeValue
TopicWorld Models: A Comprehensive Survey
SummaryA survey of AI world models covering taxonomy, leading architectures, landmark systems, open challenges, and future research directions.
Related Models8
Citations4

What Are AI World Models? Scope and Main Families

Editorial body section preserved directly in static HTML.

World models span a wide range of AI systems: from latent dynamics models for RL (RSSM, Dreamer) to abstract planning models (Predictron, MuZero), from generative environment simulators (Cosmos, Genie 2) to self-supervised visual models (V-JEPA). This survey organizes them by architecture, learning paradigm, and application domain.

Taxonomy of AI World Models

Editorial body section preserved directly in static HTML.

We organize world models along three axes: (1) Architecture: RSSM-based, autoregressive, diffusion-based, abstract; (2) Learning paradigm: RL-based, self-supervised, supervised; (3) Domain: games, robotics, autonomous driving, general-purpose. Each axis captures different trade-offs and design choices.

Key World Model Systems by Research Era

Editorial body section preserved directly in static HTML.

Foundational (2017-2019): Predictron, I2A, Ha & Schmidhuber's World Models, PlaNet/RSSM. Scaling (2020-2022): MuZero, DreamerV2. Generalization (2023-present): DreamerV3, TD-MPC2, IRIS, UniSim, NVIDIA Cosmos, Genie 2, V-JEPA. Each era brought fundamental shifts in capabilities.

Open Challenges in World Model Research

Editorial body section preserved directly in static HTML.

Persistent challenges include: long-horizon prediction stability, sample efficiency in complex real-world domains, bridging the reality gap for robotics, scaling world models to open-ended environments, and integrating world models with language understanding for broader reasoning.

Future Directions for AI World Models

Editorial body section preserved directly in static HTML.

The field is converging toward foundation world models trained at massive scale on video data, combining physical understanding with language reasoning. The integration of world models with LLMs, the development of universal simulators, and the push toward embodied general intelligence are key research frontiers.

Related Models

ModelLabCategoryIndex v1.1
DreamerV3Google DeepMindModel-Based RL88/100
MuZeroGoogle DeepMindModel-Based RL78/100
NVIDIA CosmosNVIDIAFoundation World Model87/100
Genie 2Google DeepMindGenerative World Model79/100
V-JEPAMetaSelf-Supervised World Model70/100
World Models (Ha & Schmidhuber)Google Brain / IDSIAModel-Based RL48/100
PlaNetGoogleModel-Based RL57/100
PredictronGoogle DeepMindModel-Based RL43/100

Frequently Asked Questions

FAQ answers rendered directly into static HTML for extractable responses.

How many world model architectures exist?

There are dozens of distinct world model architectures, but they cluster into a few families: RSSM-based (Dreamer), search-based (MuZero), autoregressive (IRIS), diffusion-based (Cosmos, UniSim), and joint embedding (V-JEPA). Each family has its own strengths and trade-offs.

What is the most influential world model paper?

Ha & Schmidhuber's 'World Models' (2018) is the most cited and conceptually influential. For practical impact, DreamerV3 (2023) demonstrated the first domain-general world model agent.

Quick Answer

Short extractable summary preserved directly in static HTML.

  • World Models: A Comprehensive Survey explains the core definition, methods, and systems involved in this research area.
  • This topic highlights the main trade-offs, open challenges, and practical implications for world models.
  • Related models and references connect the concept to concrete systems and primary sources.

Editorial Trust Signals

Editorial provenance and refresh policy preserved directly in static HTML.

Published by world-models.io editorial board.

Lead editor Bernard Grenat.

This research page curates topic explanations, linked models, and citations grounded in primary research sources.

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: 2026-06-21.

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 onlyLast reviewed date visibleMethodology documentedSource links included

External Sources

Primary research citations embedded in static HTML.

References

  1. [1] Hafner et al., 2023. Mastering Diverse Domains through World Models.
  2. [2] Ha & Schmidhuber, 2018. World Models.
  3. [3] LeCun, 2022. A Path Towards Autonomous Machine Intelligence.
  4. [4] Schrittwieser et al., 2020. MuZero.