@article{towardsmultimodalincontextlearningfor,
  title = {Towards Multimodal In-Context Learning for Vision & Language Models},
  author = {Sivan Doveh and Shaked Perek and M. Jehanzeb Mirza and Wei Lin and Amit Alfassy and Assaf Arbelle and Shimon Ullman and Leonid Karlinsky},
  year = {2024},
  eprint = {2403.12736},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.12736v2},
}