@article{voilaaaligningvisionlanguagemodelswith,
  title = {Voila-A: Aligning Vision-Language Models with User's Gaze Attention},
  author = {Kun Yan and Lei Ji and Zeyu Wang and Yuntao Wang and Nan Duan and Shuai Ma},
  year = {2023},
  eprint = {2401.09454},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2401.09454v1},
}