@article{pruningonemoretokenisenoughleveraging,
  title = {Pruning One More Token is Enough: Leveraging Latency-Workload Non-Linearities for Vision Transformers on the Edge},
  author = {Nick John Eliopoulos and Purvish Jajal and James C. Davis and Gaowen Liu and George K. Thiravathukal and Yung-Hsiang Lu},
  year = {2024},
  eprint = {2407.05941},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.05941v4},
}