@article{canlargevisionlanguagemodelsunderstandmu,
  title = {Can Large Vision-Language Models Understand Multimodal Sarcasm?},
  author = {Xinyu Wang and Yue Zhang and Liqiang Jing},
  year = {2025},
  eprint = {2508.03654},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.03654},
}