@inproceedings{hu-etal-2026-beyond-flops,
    title = "Beyond {FLOP}s: Benchmarking Real Inference Acceleration of {LLM} Pruning under a {GEMM}-Centric Taxonomy",
    author = "Hu, Haozhe  and
      Wu, Hao  and
      Zhao, Anhao  and
      Ding, Longwei  and
      Yin, Peiran  and
      Ma, Yunpu  and
      Shen, Xiaoyu",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.1371/",
    pages = "31283--31310",
    ISBN = "979-8-89176-459-0"
}