@misc{chen2023towards,
  title={Towards End-to-End Embodied Decision Making via Multi-modal Large Language Model: Explorations with GPT4-Vision and Beyond},
  author={Liang Chen and Yichi Zhang and Shuhuai Ren and Haozhe Zhao and Zefan Cai and Yuchi Wang and Tianyu Liu and Baobao Chang},
  year={2023},
  eprint={2310.02071},
  archivePrefix={arXiv},
  primaryClass={cs.AI},
  url={https://arxiv.org/abs/2310.02071}
}