Mettle: Meta-Token Learning for Memory-Efficient Audio-Visual Adaptation

@misc{han2025mettlemetatokenlearning,
      title={Mettle: Meta-Token Learning for Memory-Efficient Audio-Visual Adaptation},
      author={Mingfei Han and Xiaojun Chang and Zhihui Li and Meng Wang and Jinxing Zhou and Ruohao Guo and Yuxin Mao and Guangyao Li and Yanghao Zhou and Yongqiang Yu},
      year={2025},
      eprint={2506.23271},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2506.23271},
}