@article{dovisionlanguagemodelsunderstandhumaneng,
  title = {Do Vision Language Models Understand Human Engagement in Games?},
  author = {Ziyi Wang and Qizan Guo and Rishitosh Singh and Xiyang Hu},
  year = {2026},
  eprint = {2603.18480},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.18480},
}