@article{clusteringdrivenmemorycompressionforonde,
  title = {Clustering-driven Memory Compression for On-device Large Language Models},
  author = {Ondrej Bohdal and Pramit Saha and Umberto Michieli and Mete Ozay and Taha Ceritli},
  year = {2026},
  eprint = {2601.17443},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.17443},
}