---
title: "Autoregressive Model | Glossary | world-models.io"
canonical: "https://world-models.io/en/glossary/autoregressive-model/"
description: "Definition of autoregressive models in world modeling: models that generate outputs one element at a time."
author: "Bernard Grenat"
generated: "2026-10-30"
---

New: the Timeline is live. Track world model releases, papers, and benchmark updates in real time.

The Knowledge Hub for AI World Models

# Autoregressive Model

A model that generates outputs one element at a time, where each output depends on previous elements. IRIS treats world modeling as autoregressive token prediction.

robotics

model-based-rl

simulation

embodied-ai

## What is a world model?

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](https://world-models.io/en/world-models-database/), compare systems on the [leaderboard](https://world-models.io/en/leaderboard/), or read the [Performance Index methodology](https://world-models.io/en/methodology/performance-index/).

## What Is Autoregressive Model?

Editorial definition preserved directly in static HTML.

A model that generates outputs one element at a time, where each output depends on previous elements. IRIS treats world modeling as autoregressive token prediction, bridging language modeling and world modeling techniques.

Autoregressive Model is a glossary concept in the architecture layer of the world models knowledge base.

## Term Snapshot

Static glossary definition snapshot for crawlers and no-JS readers.

| Attribute | Value |
| --- | --- |
| Term | Autoregressive Model |
| Category | Architecture |
| Definition | A model that generates outputs one element at a time, where each output depends on previous elements. IRIS treats world modeling as autoregressive token prediction, bridging language modeling and world modeling techniques. |
| Related Models | 2 |
| Related Research | 1 |

## Related Models

| Model | Lab | Category |
| --- | --- | --- |
| [IRIS](https://world-models.io/en/models/iris/) | Microsoft Research | Model-Based RL |
| [NVIDIA Cosmos](https://world-models.io/en/models/nvidia-cosmos/) | NVIDIA | Foundation World Model |

## Related Research

| Topic | Summary |
| --- | --- |
| [Foundation World Models](https://world-models.io/en/research/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. |

## Related Terms

| Term | Category | Definition |
| --- | --- | --- |
| [Diffusion Model](https://world-models.io/en/glossary/diffusion-model/) | Architecture | A generative model that learns to produce data by reversing a gradual noising process. In world models, diffusion-based architectures (used in NVIDIA Cosmos and UniSim) generate high-fidelity video frames representing possible future states of the environment. |
| [Tokenizer](https://world-models.io/en/glossary/tokenizer/) | Architecture | A component that converts continuous data (images, video frames, states) into discrete tokens that can be processed by transformer-based architectures. In world models like IRIS, visual tokenizers convert image observations into sequences of discrete tokens for autoregressive prediction. |

## Quick Answer

Short extractable summary preserved directly in static HTML.

- Autoregressive Model is a glossary concept used across world-models.io to clarify language, methods, and architectural ideas in the field.
- Use this page to get the definition quickly, then continue into related models, research topics, and adjacent terms for context.

## 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 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.](https://world-models.io/en/editorial-policy/)

Primary sources only

Last reviewed date visible

Methodology documented

Source links included

Correction channel published

Review date visible

## Reference Sources

Primary sources related to this term, surfaced directly in static HTML.

- [IRIS paper](https://arxiv.org/abs/2209.00588) Microsoft Research primary research source
- [IRIS cited source](https://arxiv.org/abs/1803.10122) Micheli et al., 2023. Transformers are Sample-Efficient World Models. ICLR 2023.
- [NVIDIA Cosmos paper](https://arxiv.org/abs/2501.03575) NVIDIA primary research source
- [NVIDIA Cosmos official page](https://www.nvidia.com/en-us/ai/cosmos/) NVIDIA official page