World Models: The AI Technology Teaching Machines to Understand Physics
A new generation of AI systems can simulate gravity, predict collisions, and generate interactive 3D worlds. Here is what world models are, who is building them, and why they matter.
Key points
- Nvidia released Cosmos 3, a family of open-weight world model AI systems, in June 2026, with versions ranging from 16 billion to 64 billion parameters.
- Google DeepMind's Genie 3, introduced in August 2025, generates photorealistic interactive 3D worlds from a text description at 24 frames per second.
- Waymo adopted Genie 3 in February 2026 to simulate rare driving scenarios, such as unusual pedestrian behaviour, without putting a vehicle on public roads.
- World Labs raised $1 billion and Yann LeCun's AMI raised $1.03 billion to fund world model research in 2025 and 2026.
- Alibaba unveiled its world model, Happy Oyster, in April 2026, capable of generating three-minute in-world video clips.
Most AI you have heard about, the chatbots, the image generators, the writing assistants, works by predicting patterns in text or pixels. Ask it what happens when a ball rolls off a table and it will give you a plausible-sounding answer. But it does not actually know what gravity does. It has never modelled the physics.
World models are different. A world model is an AI system that builds an internal picture of an environment, complete with cause and effect, and uses that picture to predict what will happen next. Think of it as the difference between a parrot that can describe a chess game and a player who actually understands the consequences of each move.
Where did world models come from?
The idea is older than most people realise. Researcher Jürgen Schmidhuber introduced the concept in 1990, proposing neural networks (layers of software loosely inspired by the brain) that could predict future states of an environment. The concept was revived in a 2018 paper by David Ha and Schmidhuber, in which AI agents learned to drive virtual cars by practising inside simulations they generated themselves.
Meta's chief AI scientist Yann LeCun pushed the idea further in a 2022 paper arguing that true machine intelligence needs predictive world models, not just pattern matching. His team developed V-JEPA 2, which reached top performance on video understanding and physical reasoning and can guide a robot in a room it has never seen before.
What is actually being built right now?
The field has moved fast. Here is a snapshot of the major releases.
| Model / Product | Creator | Date | What it does |
|---|---|---|---|
| Genie 3 | Google DeepMind | August 2025 | Photorealistic interactive 3D worlds from text, at 24 fps |
| Waymo World Model | Waymo / DeepMind | February 2026 | Simulates rare driving edge cases for self-driving cars |
| Happy Oyster | Alibaba | April 2026 | Generates 3-minute in-world video; includes a directing mode |
| Spark 2.0 | World Labs | April 2026 | Open-source 3D rendering engine for smartphone-class hardware |
| Cosmos 3 | Nvidia | June 2026 | Combines physics reasoning, simulation, and action generation |
Nvidia's Cosmos 3 is the most technically ambitious entry. It processes text, images, video, audio, and physical action sequences together, rather than treating them as separate tasks. The smaller version, Cosmos3-Nano at 16 billion parameters (a parameter being a single adjustable value inside the model, with more parameters generally meaning more capability), is designed to run on a workstation. The larger Cosmos3-Super at 64 billion parameters targets research labs.
Cosmos 3 is released as open-weight, meaning anyone can download and inspect the model's internal values, which is significant for researchers who want to build on it without paying API fees.
What does this mean for ordinary people?
Most of the near-term impact lands in three places.
Self-driving cars get safer training. A robotaxi cannot wait to encounter a tornado or a toddler running into traffic before learning to handle it. World models let companies like Waymo simulate those situations thousands of times in software first.
Robotics gets cheaper to develop. Robots trained inside world model simulations can transfer those skills to the physical world, cutting the number of expensive and sometimes dangerous real-world trials.
Games and creative tools change shape. Genie 3 lets a user type a description and walk around inside the resulting environment seconds later. Game studios are already using this to prototype levels faster.
Scientific modelling also benefits: researchers can simulate physical or biological processes at a scale that would be impractical to test in a lab.
Funding is flowing heavily into this space. General Intuition closed a $133.7 million seed round, World Labs raised $1 billion, and LeCun's AMI raised $1.03 billion. When that much capital concentrates on a single approach, products tend to reach consumers faster than the underlying research timelines suggest.
Common questions
Is a world model the same as ChatGPT or Claude?
No. Large language models, the technology behind ChatGPT and Claude, predict the next word in a sequence and work almost entirely in text. World models predict what happens next in a physical environment, working with video, sensor data, and spatial information. They overlap in some architectures but serve different goals.
Can I use any of these tools today?
Nvidia's Cosmos 3 is available as open-weight software for researchers and developers. World Labs released Spark 2.0 as open-source. Consumer-facing products built on these systems are beginning to appear, but most current tools target developers and enterprise customers rather than everyday users.
Are world models safe?
Researchers note that video prediction accuracy or robot success rates inside a simulation do not always predict real-world performance, which is one reason safety testing remains a live concern. The field is still defining standards, and no major regulator has issued specific guidance on world models as of mid-2026.
