When Tokens Talk Too Much: A Survey of Multimodal Long-Context Token Compression across Images, Videos, and Audios
BibTex
Copy
@misc{you2025whentokenstalk,
title={When Tokens Talk Too Much: A Survey of Multimodal Long-Context Token Compression across Images, Videos, and Audios},
author={Haoxuan You and Can Qin and Huan Wang and Mu Cai and Yuzhang Shang and Yang Sui and Kejia Zhang and Kele Shao and Keda Tao and Sicheng Feng},
year={2025},
eprint={2507.20198},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2507.20198},
}