@article{vocotunleashingvisuallygroundedmultistep,
  title = {VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models},
  author = {Zejun Li and Ruipu Luo and Jiwen Zhang and Minghui Qiu and Zhongyu Wei},
  year = {2024},
  eprint = {2405.16919},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.16919v2},
}