@article{aimadaptiveinferenceofmultimodalllms,
  title = {AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning},
  author = {Yiwu Zhong and Zhuoming Liu and Yin Li and LiWei Wang},
  year = {2024},
  eprint = {2412.03248},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.03248v1},
}