@article{specmoeafastandefficientmixtureofexperts,
  title = {SpecMoE: A Fast and Efficient Mixture-of-Experts Inference via Self-Assisted Speculative Decoding},
  author = {Jehyeon Bang and Eunyeong Cho and Ranggi Hwang and Jinha Chung and Minsoo Rhu},
  year = {2026},
  eprint = {2604.10152},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.10152},
}