{"ID":5443908,"CreatedAt":"2026-07-01T02:07:11.383974684Z","UpdatedAt":"2026-07-03T17:47:04.346850254Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.32028","arxiv_id":"2606.32028","title":"DVG-WM: Disentangled Video Generation Enables Efficient Embodied World Model for Robotic Manipulation","abstract":"Video-based embodied world models provide an appealing substrate for robotic manipulation by predicting future states, yet current approaches remain limited by a fundamental entanglement: accurately modeling dynamics typically requires low-level temporal reasoning, while producing high-resolution frames demands expansive visual synthesis according to high-level semantics. This entanglement results in slow inference speed for iterative planning or too coarse predictions to retain contact-rich details. To solve this dilemma, we present Disentangled Video Generation World Model (DVG-WM), an efficient framework that explicitly decomposes world modeling into dynamics learning and visual synthesis. Conditioned on an initial observation and a language instruction, our model first generates a plausible sequence of intermediate visual states to preview the physical interaction and refines them to obtain high-fidelity videos. Furthermore, an efficient cascading mechanism is proposed, where DVG-WM uses flow matching to directly map the dynamics to video latents, and introduces a latent degradation mechanism to regenerate contact-rich details. Experiments on LIBERO and real-world platforms demonstrate improved video quality with up to 3.97 times acceleration, validating that disentangled video generation can be an efficient embodied world model for robotic manipulation.","short_abstract":"Video-based embodied world models provide an appealing substrate for robotic manipulation by predicting future states, yet current approaches remain limited by a fundamental entanglement: accurately modeling dynamics typically requires low-level temporal reasoning, while producing high-resolution frames demands expansi...","url_abs":"https://arxiv.org/abs/2606.32028","url_pdf":"https://arxiv.org/pdf/2606.32028v1","authors":"[\"Ziyu Shan\",\"Zhenyu Wu\",\"Xiaofeng Wang\",\"Zheng Zhu\",\"Ziwei Wang\"]","published":"2026-06-30T17:54:32Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[]","has_code":false}