@article{mixtureofscalesmemoryefficienttoken,
  title = {Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models},
  author = {Dongwon Jo and Taesu Kim and Yulhwa Kim and Jae-Joon Kim},
  year = {2024},
  eprint = {2406.12311},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.12311v2},
}