LaWM: Least Action World Models for Long-Horizon Physical Consistency from Visual Observations

ArXi:2605.08279v1 Announce Type: cross Learning predictive world models from visual observations is a core problem in embodied AI, with applications to model-based reinforcement learning and robotic planning. Existing latent world models typically generate future states with unconstrained neural transition functions, while modern video generation systems often prioritize perceptual plausibility or