@article{st3acceleratingmultimodallargelanguage,
  title = {ST$^3$: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming},
  author = {Jiedong Zhuang and Lu Lu and Ming Dai and Rui Hu and Jian Chen and Qiang Liu and Haoji Hu},
  year = {2024},
  eprint = {2412.20105},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.20105v1},
}