@misc{cao2024what,
  title={What is the Visual Cognition Gap between Humans and Multimodal LLMs?},
  author={Xu Cao and Bolin Lai and Wenqian Ye and Yunsheng Ma and Joerg Heintz and Jintai Chen and Jianguo Cao and James M. Rehg},
  year={2024},
  eprint={2406.10424},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2406.10424}
}