@inproceedings{wang-etal-2025-language-model,
    title = "Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers",
    author = "Wang, Juncheng  and
      Xu, Chao  and
      Yu, Cheng  and
      Hu, Zhe  and
      Xie, Haoyu  and
      Yu, Guoqi  and
      Shang, Lei  and
      Wang, Shujun",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1322/",
    pages = "26036--26054",
    ISBN = "979-8-89176-332-6"
}