@article{shakingupvlmscomparingtransformersand,
  title = {Shaking Up VLMs: Comparing Transformers and Structured State Space Models for Vision & Language Modeling},
  author = {Georgios Pantazopoulos and Malvina Nikandrou and Alessandro Suglia and Oliver Lemon and Arash Eshghi},
  year = {2024},
  eprint = {2409.05395},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.05395v2},
}