@inproceedings{warczynski-etal-2026-one,
    title = "One-step Nonautoregressive Natural Language Generation with Shortcut Flow Matching Models",
    author = "Warczy{\'n}ski, J{\k{e}}drzej  and
      Dusek, Ondrej  and
      Lango, Mateusz",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 2: Short Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-short.53/",
    pages = "646--655",
    ISBN = "979-8-89176-391-3",
    abstract = "While having a significant potential for parallel processing in theory, diffusion-based non-autoregressive text generation remains inefficient due to the need for multiple denoising steps. Performance degrades sharply if a low number of steps is used, such as in flow matching. To enable accurate one-step generation, we propose a novel shortcut flow-matching model that learns to directly predict multi-step denoising outcomes in a single step. Experiments conducted on three datasets demonstrate consistent improvements over classic flow-matching, with BLEU scores more than doubling on two datasets. We also tested five different ways of extending shortcut models with commonly used techniques."
}