@article{3dmix_2026,
title={3D-Mix for VLA: A Plug-and-Play Module for Integrating VGGT-based 3D Information into Vision-Language-Action Models},
author={Yu, Bin and Lian, Shijie and Lin, Xiaopeng and Shen, Zhaolong and Wei, Yuliang and Liu, Haishan and Wu, Changti and Yuan, Hang and Wang, Bailing and Huang, Cong and others},
journal={arXiv preprint arXiv:2603.24393},
year={2026}
}