@article{prefixkvadaptiveprefixkvcacheiswhat,
  title = {PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation},
  author = {Ao Wang and Hui Chen and Jianchao Tan and Kefeng Zhang and Xunliang Cai and Zijia Lin and Jungong Han and Guiguang Ding},
  year = {2024},
  eprint = {2412.03409},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.03409v2},
}