MoS-VLA: A Vision-Language-Action Model with One-Shot Skill Adaptation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912659350224896 |
|---|---|
| author | Zhao, Ruihan Ingebrand, Tyler Chinchali, Sandeep Topcu, Ufuk |
| author_facet | Zhao, Ruihan Ingebrand, Tyler Chinchali, Sandeep Topcu, Ufuk |
| contents | Vision-Language-Action (VLA) models trained on large robot datasets promise general-purpose, robust control across diverse domains and embodiments. However, existing approaches often fail out-of-the-box when deployed in novel environments, embodiments, or tasks. We introduce Mixture of Skills VLA (MoS-VLA), a framework that represents robot manipulation policies as linear combinations of a finite set of learned basis functions. During pretraining, MoS-VLA jointly learns these basis functions across datasets from the Open X-Embodiment project, producing a structured skill space. At test time, adapting to a new task requires only a single expert demonstration. The corresponding skill representation is then inferred via a lightweight convex optimization problem that minimizes the L1 action error, without requiring gradient updates. This gradient-free adaptation incurs minimal overhead while enabling rapid instantiation of new skills. Empirically, MoS-VLA achieves lower action-prediction error on five out of five unseen datasets and succeeds in both simulation and real-robot tasks where a pretrained VLA model fails outright. Project page: mos-vla.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_16617 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MoS-VLA: A Vision-Language-Action Model with One-Shot Skill Adaptation Zhao, Ruihan Ingebrand, Tyler Chinchali, Sandeep Topcu, Ufuk Robotics Vision-Language-Action (VLA) models trained on large robot datasets promise general-purpose, robust control across diverse domains and embodiments. However, existing approaches often fail out-of-the-box when deployed in novel environments, embodiments, or tasks. We introduce Mixture of Skills VLA (MoS-VLA), a framework that represents robot manipulation policies as linear combinations of a finite set of learned basis functions. During pretraining, MoS-VLA jointly learns these basis functions across datasets from the Open X-Embodiment project, producing a structured skill space. At test time, adapting to a new task requires only a single expert demonstration. The corresponding skill representation is then inferred via a lightweight convex optimization problem that minimizes the L1 action error, without requiring gradient updates. This gradient-free adaptation incurs minimal overhead while enabling rapid instantiation of new skills. Empirically, MoS-VLA achieves lower action-prediction error on five out of five unseen datasets and succeeds in both simulation and real-robot tasks where a pretrained VLA model fails outright. Project page: mos-vla.github.io/ |
| title | MoS-VLA: A Vision-Language-Action Model with One-Shot Skill Adaptation |
| topic | Robotics |
| url | https://arxiv.org/abs/2510.16617 |