{"ID":5551718,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T11:43:16.960862486Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00836","arxiv_id":"2607.00836","title":"From World Models to World Action Models: A Concise Tutorial for Robotics","abstract":"World models are increasingly used in embodied intelligence and generative simulation, yet their scope remains ambiguous across communities. This tutorial presents a design-space view of world models as action-conditioned predictive models that estimate the future evolution of task-relevant observations or states. We categorize existing methods into observation-space and state-space world models, comparing their trade-offs in visual fidelity, spatial structure, physical interpretability, and control usability. We further introduce world action models, which connect predicted futures with executable robot actions, and summarize four representative paradigms: imagine-then-execute, video-feature-conditioned action prediction, joint video-action modeling, and auxiliary video prediction for policy learning. The goal of this tutorial is to clarify the conceptual scope of world (action) models and provide a structured taxonomy for embodied prediction and control.","short_abstract":"World models are increasingly used in embodied intelligence and generative simulation, yet their scope remains ambiguous across communities. This tutorial presents a design-space view of world models as action-conditioned predictive models that estimate the future evolution of task-relevant observations or states. We c...","url_abs":"https://arxiv.org/abs/2607.00836","url_pdf":"https://arxiv.org/pdf/2607.00836v1","authors":"[\"Xiaoxiong Zhang\",\"Xiong Zeng\",\"Wei Zhang\"]","published":"2026-07-01T11:56:54Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\",\"eess.SY\"]","methods":"[]","has_code":false}