@article{flashmoereducingssdiobottlenecksviamlbas,
  title = {FlashMoE: Reducing SSD I/O Bottlenecks via ML-Based Cache Replacement for Mixture-of-Experts Inference on Edge Devices},
  author = {Byeongju Kim and Jungwan Lee and Donghyeon Han and Hoi-Jun Yoo and Sangyeob Kim},
  year = {2026},
  eprint = {2601.17063},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.17063},
}