@article{vistadatasetdovisionlanguagemodels,
  title = {ViSTa Dataset: Do vision-language models understand sequential tasks?},
  author = {Evžen Wybitul and Evan Ryan Gunter and Mikhail Seleznyov and David Lindner},
  year = {2024},
  eprint = {2411.13211},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.13211v2},
}