---
title: "Video World Models | AI Models That Understand Video."
canonical: "https://world-models.io/en/video-world-models/"
description: "Explore video world models: AI systems that learn world dynamics from video data, including Sora, Cosmos, Genie 2, and V-JEPA."
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

# Video World Models

Video world models learn to understand and generate video as a representation of world dynamics and physics, from temporal structure to object permanence.

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/).

## How to use this evidence

A practical interpretation framework for readers comparing fast-moving world-model research.

**Scope.** Video World Models is evaluated as a focused research and discovery surface, not as a claim that every listed system is directly comparable. Architecture, task, observation modality, action conditioning, training data, and evaluation protocol determine which comparisons are meaningful.

**Evidence method.** Prefer original papers, official technical reports, project pages, and versioned benchmark protocols. A reported score is retained with its source and context; it should only influence a ranking when the task, metric, unit, split, and protocol are compatible.

**Limitations.** World-model terminology changes across reinforcement learning, video generation, robotics, autonomous driving, and embodied AI. Use the linked model and methodology pages to check freshness, reproducibility, availability, and domain fit before treating an editorial summary as a deployment recommendation.

## External Sources

Primary references and official sources surfaced directly in static HTML for crawlers and no-JS readers.

- [Sora technical report](https://openai.com/index/video-generation-models-as-world-simulators/) Video as world simulation
- [Genie 3 announcement](https://deepmind.google/discover/blog/genie-3-a-new-frontier-for-world-models/) Interactive video world models
- [V-JEPA paper](https://arxiv.org/abs/2404.08471) Predictive video world modeling