@article{anchorvla4dananchorbasedspatialtemporalv,
  title = {AnchorVLA4D: an Anchor-Based Spatial-Temporal Vision-Language-Action Model for Robotic Manipulation},
  author = {Juan Zhu and Zhanying Shao and Xiaoqi Li and Ethan Morgan and Jiadong Xu and Hongwei Fan and Hao Dong},
  year = {2026},
  eprint = {2603.12730},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.12730},
}