@article{sittaasemanticimagetextalignmentfor,
  title = {Linear Alignment of Vision-language Models for Image Captioning},
  author = {Fabian Paischer and Markus Hofmarcher and Sepp Hochreiter and Thomas Adler},
  year = {2023},
  eprint = {2307.05591},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2307.05591v3},
}