@inproceedings{wang-etal-2024-scaling,
    title = "Scaling Laws Across Model Architectures: A Comparative Analysis of Dense and {M}o{E} Models in Large Language Models",
    author = "Wang, Siqi  and
      Chen, Zhengyu  and
      Li, Bei  and
      He, Keqing  and
      Zhang, Min  and
      Wang, Jingang",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.emnlp-main.319/",
    doi = "10.18653/v1/2024.emnlp-main.319",
    pages = "5583--5595"
}