Scaling World Model for Hierarchical Manipulation Policies
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911442161106944 |
|---|---|
| author | Long, Qian Wang, Yueze Song, Jiaxi Zhang, Junbo Li, Peiyan Wang, Wenxuan Wang, Yuqi Li, Haoyang Xie, Shaoxuan Yao, Guocai Zhang, Hanbo Wang, Xinlong Wang, Zhongyuan Lan, Xuguang Liu, Huaping Li, Xinghang |
| author_facet | Long, Qian Wang, Yueze Song, Jiaxi Zhang, Junbo Li, Peiyan Wang, Wenxuan Wang, Yuqi Li, Haoyang Xie, Shaoxuan Yao, Guocai Zhang, Hanbo Wang, Xinlong Wang, Zhongyuan Lan, Xuguang Liu, Huaping Li, Xinghang |
| contents | Vision-Language-Action (VLA) models are promising for generalist robot manipulation but remain brittle in out-of-distribution (OOD) settings, especially with limited real-robot data. To resolve the generalization bottleneck, we introduce a hierarchical Vision-Language-Action framework \our{} that leverages the generalization of large-scale pre-trained world model for robust and generalizable VIsual Subgoal TAsk decomposition VISTA. Our hierarchical framework \our{} consists of a world model as the high-level planner and a VLA as the low-level executor. The high-level world model first divides manipulation tasks into subtask sequences with goal images, and the low-level policy follows the textual and visual guidance to generate action sequences. Compared to raw textual goal specification, these synthesized goal images provide visually and physically grounded details for low-level policies, making it feasible to generalize across unseen objects and novel scenarios. We validate both visual goal synthesis and our hierarchical VLA policies in massive out-of-distribution scenarios, and the performance of the same-structured VLA in novel scenarios could boost from 14% to 69% with the guidance generated by the world model. Results demonstrate that our method outperforms previous baselines with a clear margin, particularly in out-of-distribution scenarios. Project page: \href{https://vista-wm.github.io/}{https://vista-wm.github.io} |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_10983 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Scaling World Model for Hierarchical Manipulation Policies Long, Qian Wang, Yueze Song, Jiaxi Zhang, Junbo Li, Peiyan Wang, Wenxuan Wang, Yuqi Li, Haoyang Xie, Shaoxuan Yao, Guocai Zhang, Hanbo Wang, Xinlong Wang, Zhongyuan Lan, Xuguang Liu, Huaping Li, Xinghang Robotics Vision-Language-Action (VLA) models are promising for generalist robot manipulation but remain brittle in out-of-distribution (OOD) settings, especially with limited real-robot data. To resolve the generalization bottleneck, we introduce a hierarchical Vision-Language-Action framework \our{} that leverages the generalization of large-scale pre-trained world model for robust and generalizable VIsual Subgoal TAsk decomposition VISTA. Our hierarchical framework \our{} consists of a world model as the high-level planner and a VLA as the low-level executor. The high-level world model first divides manipulation tasks into subtask sequences with goal images, and the low-level policy follows the textual and visual guidance to generate action sequences. Compared to raw textual goal specification, these synthesized goal images provide visually and physically grounded details for low-level policies, making it feasible to generalize across unseen objects and novel scenarios. We validate both visual goal synthesis and our hierarchical VLA policies in massive out-of-distribution scenarios, and the performance of the same-structured VLA in novel scenarios could boost from 14% to 69% with the guidance generated by the world model. Results demonstrate that our method outperforms previous baselines with a clear margin, particularly in out-of-distribution scenarios. Project page: \href{https://vista-wm.github.io/}{https://vista-wm.github.io} |
| title | Scaling World Model for Hierarchical Manipulation Policies |
| topic | Robotics |
| url | https://arxiv.org/abs/2602.10983 |