@inproceedings{yu-shen-2026-budget,
    title = "Budget-Aware Compression Pipeline for Single-{GPU} {LLM} Inference: Methods, Trade-offs, and Coupling Effects",
    author = "Yu, Hongyu  and
      Shen, Yifei",
    editor = "Wang, Yimu  and
      Choi, Yee Man  and
      Wu, Di  and
      Ouyang, Siqi  and
      Azadani, Mozhgan Nasr  and
      Fung, Yi R. (May)",
    booktitle = "Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently ({G}round{LM} 2026)",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.groundlm-1.66/",
    pages = "911--922",
    ISBN = "979-8-89176-478-1"
}