@article{dovlmsneedvisiontransformersevaluatingst,
  title = {Do VLMs Need Vision Transformers? Evaluating State Space Models as Vision Encoders},
  author = {Shang-Jui Ray Kuo and Paola Cascante-Bonilla},
  year = {2026},
  eprint = {2603.19209},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.19209},
}