@article{blinkmultimodallargelanguagemodelscan,
  title = {BLINK: Multimodal Large Language Models Can See but Not Perceive},
  author = {Xingyu Fu and Yushi Hu and Bangzheng Li and Yu Feng and Haoyu Wang and Xudong Lin and Dan Roth and Noah A. Smith and Wei-Chiu Ma and Ranjay Krishna},
  year = {2024},
  eprint = {2404.12390},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.12390v4},
}