@article{mmsllamaefficientllmbasedaudiovisual1,
  title = {MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens},
  author = {Jeong Hun Yeo and Hyeongseop Rha and Se Jin Park and Yong Man Ro},
  year = {2025},
  eprint = {2503.11315},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.11315v2},
}