@article{siamesevisiontransformersarescalable,
  title = {Siamese Vision Transformers are Scalable Audio-visual Learners},
  author = {Yan-Bo Lin and Gedas Bertasius},
  year = {2024},
  eprint = {2403.19638},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.19638v1},
}