@article{explainingmultimodallargelanguagemodels,
  title = {Explaining Multi-modal Large Language Models by Analyzing their Vision Perception},
  author = {Loris Giulivi and Giacomo Boracchi},
  year = {2024},
  eprint = {2405.14612},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.14612v2},
}