@article{lookmlookonceoptimizationinkvcachefor,
  title = {LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference},
  author = {Zhongwei Wan and Ziang Wu and Che Liu and Jinfa Huang and Zhihong Zhu and Peng Jin and Longyue Wang and Li Yuan},
  year = {2024},
  eprint = {2406.18139},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.18139v1},
}