Vision-language-action (VLA) models have enabled language-conditioned, long-horizon robot manipulation, but most existing systems are limited to grippers. Scaling VLA policies to bimanual robots with high degree-of-freedom (DoF) dexterous hands remains challenging due to the expanded action space, frequent hand-object occlusions, and the cost of collecting real-robot data. We present GR-Dexter, a holistic hardware-model-data framework for VLA-based generalist manipulation on a bimanual dexterous-hand robot. Our approach combines the design of a compact 21-DoF robotic hand, an intuitive bimanual teleoperation system for real-robot data collection, and a training recipe that leverages teleoperated robot trajectories together with large-scale vision-language and carefully curated cross-embodiment datasets. Across real-world evaluations spanning long-horizon everyday manipulation and generalizable pick-and-place, GR-Dexter achieves strong in-domain performance and improved robustness to unseen objects and unseen instructions. We hope GR-Dexter serves as a practical step toward generalist dexterous-hand robotic manipulation.
@article{arxiv.2512.24210,
title = {GR-Dexter Technical Report},
author = {Ruoshi Wen and Guangzeng Chen and Zhongren Cui and Min Du and Yang Gou and Zhigang Han and Liqun Huang and Mingyu Lei and Yunfei Li and Zhuohang Li and Wenlei Liu and Yuxiao Liu and Xiao Ma and Hao Niu and Yutao Ouyang and Zeyu Ren and Haixin Shi and Wei Xu and Haoxiang Zhang and Jiajun Zhang and Xiao Zhang and Liwei Zheng and Weiheng Zhong and Yifei Zhou and Zhengming Zhu and Hang Li},
journal= {arXiv preprint arXiv:2512.24210},
year = {2026}
}