@article{effectivemoebasedllmcompressionbyexploit,
  title = {Effective MoE-based LLM Compression by Exploiting Heterogeneous Inter-Group Experts Routing Frequency and Information Density},
  author = {Zhendong Mi and Yixiao Chen and Pu Zhao and Xiaodong Yu and Hao Wang and Yanzhi Wang and Shaoyi Huang},
  year = {2026},
  eprint = {2602.09316},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.09316},
}