Teaching robots to imagine. Build IRIS, DINO-WM, and DIAMOND world models from scratch in Colab, then scale to real robots with LeWorld and DreamZero — the first open-sourced world-action model for SO-101.
Build three world model architectures from scratch and train them on robot manipulation tasks.
Build IRIS from scratch — VQ-VAE tokenization, autoregressive transformer, and imagination-based RL for Atari.
Open in ColabBuild DINO-WM from scratch — predict in DINO feature space instead of pixels for robust, generalizable world models.
Open in ColabBuild DIAMOND from scratch — diffusion-based world models that generate crisp future frames via iterative denoising.
Open in ColabApply DINO-WM to the PushT robot manipulation task — train a world model and plan actions in feature space.
Open in ColabTwo parts covering the full world models landscape — from game-playing agents to real-robot deployment.
Explore DreamZero's world-action model through an interactive gallery and research site.
Full research site with interactive rollout gallery, paper, and evaluation results for our open-source world-action model.
Visit site Interactive GalleryPick a training example, choose a prompt, and watch DreamZero imagine the robot's future actions and video frames.
Try it