@article{whatdovisionlanguagemodelsseeinthecontex,
  title = {What do vision-language models see in the context? Investigating multimodal in-context learning},
  author = {Gabriel O. dos Santos and Esther Colombini and Sandra Avila},
  year = {2025},
  eprint = {2510.24331},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.24331},
}