@article{visionspeechmodelsteachingspeechmodels,
  title = {Vision-Speech Models: Teaching Speech Models to Converse about Images},
  author = {Amélie Royer and Moritz Böhle and Gabriel de Marmiesse and Laurent Mazaré and Neil Zeghidour and Alexandre Défossez and Patrick Pérez},
  year = {2025},
  eprint = {2503.15633},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.15633v1},
}