ST4VLA: Spatially Guided Training for Vision-Language-Action Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918331442790400 |
|---|---|
| author | Ye, Jinhui Wang, Fangjing Gao, Ning Yu, Junqiu Zhu, Yangkun Wang, Bin Zhang, Jinyu Jin, Weiyang Fu, Yanwei Zheng, Feng Chen, Yilun Pang, Jiangmiao |
| author_facet | Ye, Jinhui Wang, Fangjing Gao, Ning Yu, Junqiu Zhu, Yangkun Wang, Bin Zhang, Jinyu Jin, Weiyang Fu, Yanwei Zheng, Feng Chen, Yilun Pang, Jiangmiao |
| contents | Large vision-language models (VLMs) excel at multimodal understanding but fall short when extended to embodied tasks, where instructions must be transformed into low-level motor actions. We introduce ST4VLA, a dual-system Vision-Language-Action framework that leverages Spatial Guided Training to align action learning with spatial priors in VLMs. ST4VLA includes two stages: (i) spatial grounding pre-training, which equips the VLM with transferable priors via scalable point, box, and trajectory prediction from both web-scale and robot-specific data, and (ii) spatially guided action post-training, which encourages the model to produce richer spatial priors to guide action generation via spatial prompting. This design preserves spatial grounding during policy learning and promotes consistent optimization across spatial and action objectives. Empirically, ST4VLA achieves substantial improvements over vanilla VLA, with performance increasing from 66.1 -> 84.6 on Google Robot and from 54.7 -> 73.2 on WidowX Robot, establishing new state-of-the-art results on SimplerEnv. It also demonstrates stronger generalization to unseen objects and paraphrased instructions, as well as robustness to long-horizon perturbations in real-world settings. These results highlight scalable spatially guided training as a promising direction for robust, generalizable robot learning. Source code, data and models are released at https://internrobotics.github.io/internvla-m1.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_10109 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ST4VLA: Spatially Guided Training for Vision-Language-Action Models Ye, Jinhui Wang, Fangjing Gao, Ning Yu, Junqiu Zhu, Yangkun Wang, Bin Zhang, Jinyu Jin, Weiyang Fu, Yanwei Zheng, Feng Chen, Yilun Pang, Jiangmiao Robotics Large vision-language models (VLMs) excel at multimodal understanding but fall short when extended to embodied tasks, where instructions must be transformed into low-level motor actions. We introduce ST4VLA, a dual-system Vision-Language-Action framework that leverages Spatial Guided Training to align action learning with spatial priors in VLMs. ST4VLA includes two stages: (i) spatial grounding pre-training, which equips the VLM with transferable priors via scalable point, box, and trajectory prediction from both web-scale and robot-specific data, and (ii) spatially guided action post-training, which encourages the model to produce richer spatial priors to guide action generation via spatial prompting. This design preserves spatial grounding during policy learning and promotes consistent optimization across spatial and action objectives. Empirically, ST4VLA achieves substantial improvements over vanilla VLA, with performance increasing from 66.1 -> 84.6 on Google Robot and from 54.7 -> 73.2 on WidowX Robot, establishing new state-of-the-art results on SimplerEnv. It also demonstrates stronger generalization to unseen objects and paraphrased instructions, as well as robustness to long-horizon perturbations in real-world settings. These results highlight scalable spatially guided training as a promising direction for robust, generalizable robot learning. Source code, data and models are released at https://internrobotics.github.io/internvla-m1.github.io/ |
| title | ST4VLA: Spatially Guided Training for Vision-Language-Action Models |
| topic | Robotics |
| url | https://arxiv.org/abs/2602.10109 |