We use World Models to evaluate and train robots. This enables you to test your policy checkpoints easily, as well as augmenting your training dataset. Scaling GPUs is much cheaper than scaling robot arms and humans needed to moniter them.
From the launch
Moving Atoms is a world model lab, whose models are currently allowing labs to evaluate and train policy checkpoints in simulation rather than on physical hardware. Moving Atoms: YC Summer 2026: Moving Atoms : World Models for Robots
