Cross-Hand Latent Representation for Vision-Language-Action Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912960036732928 |
|---|---|
| author | Jiang, Guangqi Liang, Yutong Ye, Jianglong Huang, Jia-Yang Jing, Changwei Duan, Rocky Abbeel, Pieter Wang, Xiaolong Zou, Xueyan |
| author_facet | Jiang, Guangqi Liang, Yutong Ye, Jianglong Huang, Jia-Yang Jing, Changwei Duan, Rocky Abbeel, Pieter Wang, Xiaolong Zou, Xueyan |
| contents | Dexterous manipulation is essential for real-world robot autonomy, mirroring the central role of human hand coordination in daily activity. Humans rely on rich multimodal perception--vision, sound, and language-guided intent--to perform dexterous actions, motivating vision-based, language-conditioned manipulation systems for robots. However, training reliable vision-language-action (VLA) models for dexterous manipulation requires large-scale demonstrations across many robotic hands. In addition, as new dexterous embodiments appear rapidly, collecting data for each becomes costly and impractical, creating a need for scalable cross-embodiment learning. We introduce XL-VLA, a vision-language-action framework integrated with a unified latent action space shared across diverse dexterous hands. This embodiment-invariant latent space is directly pluggable into standard VLA architectures, enabling seamless cross-embodiment training and efficient reuse of both existing and newly collected data. Experimental results demonstrate that XL-VLA consistently outperforms baseline VLA models operating in raw joint spaces, establishing it as an effective solution for scalable cross-embodiment dexterous manipulation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_10158 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Cross-Hand Latent Representation for Vision-Language-Action Models Jiang, Guangqi Liang, Yutong Ye, Jianglong Huang, Jia-Yang Jing, Changwei Duan, Rocky Abbeel, Pieter Wang, Xiaolong Zou, Xueyan Robotics Dexterous manipulation is essential for real-world robot autonomy, mirroring the central role of human hand coordination in daily activity. Humans rely on rich multimodal perception--vision, sound, and language-guided intent--to perform dexterous actions, motivating vision-based, language-conditioned manipulation systems for robots. However, training reliable vision-language-action (VLA) models for dexterous manipulation requires large-scale demonstrations across many robotic hands. In addition, as new dexterous embodiments appear rapidly, collecting data for each becomes costly and impractical, creating a need for scalable cross-embodiment learning. We introduce XL-VLA, a vision-language-action framework integrated with a unified latent action space shared across diverse dexterous hands. This embodiment-invariant latent space is directly pluggable into standard VLA architectures, enabling seamless cross-embodiment training and efficient reuse of both existing and newly collected data. Experimental results demonstrate that XL-VLA consistently outperforms baseline VLA models operating in raw joint spaces, establishing it as an effective solution for scalable cross-embodiment dexterous manipulation. |
| title | Cross-Hand Latent Representation for Vision-Language-Action Models |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.10158 |