<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="warczynski-etal-2026-one">
    <titleInfo>
        <title>One-step Nonautoregressive Natural Language Generation with Shortcut Flow Matching Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jędrzej</namePart>
        <namePart type="family">Warczyński</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ondrej</namePart>
        <namePart type="family">Dusek</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mateusz</namePart>
        <namePart type="family">Lango</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-391-3</identifier>
    </relatedItem>
    <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.</abstract>
    <identifier type="citekey">warczynski-etal-2026-one</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-short.53/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>646</start>
            <end>655</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T One-step Nonautoregressive Natural Language Generation with Shortcut Flow Matching Models
%A Warczyński, Jędrzej
%A Dusek, Ondrej
%A Lango, Mateusz
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-391-3
%F warczynski-etal-2026-one
%X 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.
%U https://aclanthology.org/2026.acl-short.53/
%P 646-655

Markdown (Informal)

[One-step Nonautoregressive Natural Language Generation with Shortcut Flow Matching Models](https://aclanthology.org/2026.acl-short.53/) (Warczyński et al., ACL 2026)

• One-step Nonautoregressive Natural Language Generation with Shortcut Flow Matching Models (Warczyński et al., ACL 2026)

ACL

• Jędrzej Warczyński, Ondrej Dusek, and Mateusz Lango. 2026. One-step Nonautoregressive Natural Language Generation with Shortcut Flow Matching Models. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 646–655, San Diego, California, United States. Association for Computational Linguistics.