@article{automotaunifiedvisionlanguageactionmodel,
  title = {AutoMoT: A Unified Vision-Language-Action Model with Asynchronous Mixture-of-Transformers for End-to-End Autonomous Driving},
  author = {Wenhui Huang and Songyan Zhang and Qihang Huang and Zhidong Wang and Zhiqi Mao and Collister Chua and Zhan Chen and Long Chen and Chen Lv},
  year = {2026},
  eprint = {2603.14851},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.14851},
}