@article{improvingvisualcommonsenseinlanguage,
  title = {Improving Visual Commonsense in Language Models via Multiple Image Generation},
  author = {Guy Yariv and Idan Schwartz and Yossi Adi and Sagie Benaim},
  year = {2024},
  eprint = {2406.13621},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.13621v1},
}