DDP-WM: Disentangled Dynamics Prediction for Efficient World Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910041398837248 |
|---|---|
| author | Yin, Shicheng Yin, Kaixuan Chen, Weixing Liu, Yang Li, Guanbin Lin, Liang |
| author_facet | Yin, Shicheng Yin, Kaixuan Chen, Weixing Liu, Yang Li, Guanbin Lin, Liang |
| contents | World models are essential for autonomous robotic planning. However, the substantial computational overhead of existing dense Transformerbased models significantly hinders real-time deployment. To address this efficiency-performance bottleneck, we introduce DDP-WM, a novel world model centered on the principle of Disentangled Dynamics Prediction (DDP). We hypothesize that latent state evolution in observed scenes is heterogeneous and can be decomposed into sparse primary dynamics driven by physical interactions and secondary context-driven background updates. DDP-WM realizes this decomposition through an architecture that integrates efficient historical processing with dynamic localization to isolate primary dynamics. By employing a crossattention mechanism for background updates, the framework optimizes resource allocation and provides a smooth optimization landscape for planners. Extensive experiments demonstrate that DDP-WM achieves significant efficiency and performance across diverse tasks, including navigation, precise tabletop manipulation, and complex deformable or multi-body interactions. Specifically, on the challenging Push-T task, DDP-WM achieves an approximately 9 times inference speedup and improves the MPC success rate from 90% to98% compared to state-of-the-art dense models. The results establish a promising path for developing efficient, high-fidelity world models. Codes is available at https://hcplab-sysu.github.io/DDP-WM/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_01780 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DDP-WM: Disentangled Dynamics Prediction for Efficient World Models Yin, Shicheng Yin, Kaixuan Chen, Weixing Liu, Yang Li, Guanbin Lin, Liang Computer Vision and Pattern Recognition Robotics World models are essential for autonomous robotic planning. However, the substantial computational overhead of existing dense Transformerbased models significantly hinders real-time deployment. To address this efficiency-performance bottleneck, we introduce DDP-WM, a novel world model centered on the principle of Disentangled Dynamics Prediction (DDP). We hypothesize that latent state evolution in observed scenes is heterogeneous and can be decomposed into sparse primary dynamics driven by physical interactions and secondary context-driven background updates. DDP-WM realizes this decomposition through an architecture that integrates efficient historical processing with dynamic localization to isolate primary dynamics. By employing a crossattention mechanism for background updates, the framework optimizes resource allocation and provides a smooth optimization landscape for planners. Extensive experiments demonstrate that DDP-WM achieves significant efficiency and performance across diverse tasks, including navigation, precise tabletop manipulation, and complex deformable or multi-body interactions. Specifically, on the challenging Push-T task, DDP-WM achieves an approximately 9 times inference speedup and improves the MPC success rate from 90% to98% compared to state-of-the-art dense models. The results establish a promising path for developing efficient, high-fidelity world models. Codes is available at https://hcplab-sysu.github.io/DDP-WM/. |
| title | DDP-WM: Disentangled Dynamics Prediction for Efficient World Models |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2602.01780 |