@article{3dvlaa3dvisionlanguageactiongenerative,
  title = {3D-VLA: A 3D Vision-Language-Action Generative World Model},
  author = {Haoyu Zhen and Xiaowen Qiu and Peihao Chen and Jincheng Yang and Xin Yan and Yilun Du and Yining Hong and Chuang Gan},
  year = {2024},
  eprint = {2403.09631},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.09631v1},
}