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.
@article{arxiv.2603.10158,
title = {Cross-Hand Latent Representation for Vision-Language-Action Models},
author = {Guangqi Jiang and Yutong Liang and Jianglong Ye and Jia-Yang Huang and Changwei Jing and Rocky Duan and Pieter Abbeel and Xiaolong Wang and Xueyan Zou},
journal= {arXiv preprint arXiv:2603.10158},
year = {2026}
}