CLAW: Learning Continuous Latent Action World Models via Adversarial Latent Regularization
For robotics and embodied AI, this work enables learning action representations and world models from passive video data, reducing the need for costly action annotations.
CLAW learns continuous latent action representations and a world model from action-free videos via adversarial latent regularization and diffusion-based video generation, enabling imitation learning and goal-directed planning without action labels. It outperforms existing methods across diverse tasks.
We introduce CLAW, a fully end-to-end self-supervised framework for learning a world model jointly with continuous latent action representations directly from action-free videos. Our approach leverages adversarial latent regularization and diffusion-based video generation to capture structured and semantically meaningful action representations while modeling rich, predictive environment dynamics, without relying on any action labels or annotations. By simultaneously training the Latent Action Model and world model, CLAW learns to reason about how inferred actions induce environment transitions from visual observations alone. We show that the resulting latent action world model supports both imitation learning from observation and goal-directed planning. In imitation learning, latent actions extracted from raw videos enable behavior cloning. For planning, CLAW generates sequences of latent actions and maps them to executable actions to reach desired goals. Extensive experiments across diverse tasks and embodiments demonstrate that CLAW produces semantically meaningful latent action representations, supports effective action transfer, and enables planning and imitation from observation, outperforming existing methods.