<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qi-etal-2026-cluster">
    <titleInfo>
        <title>Cluster-Level Attention-Guided Parallel Decoding for Masked Diffusion Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Heqiang</namePart>
        <namePart type="family">Qi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wei</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mingyuan</namePart>
        <namePart type="family">Bai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiangming</namePart>
        <namePart type="family">Meng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Masked diffusion language models (MDLMs) enable parallel decoding by predicting all masked positions at each denoising step, yet existing training-free samplers usually decide which positions to commit at token-level granularity. We revisit this granularity and observe that reliable predictions often emerge as contiguous high-confidence spans, suggesting that the unit of parallel commitment can be larger than a single token. We first group adjacent high-confidence candidates into confidence-induced clusters (CICs) as span-level update units. We then use self-attention maps from the same forward pass to estimate inter-cluster dependencies, enabling conflict-aware selection of mutually compatible CICs for parallel commitment. This yields CLAD (**C**luster-**L**evel **A**ttention-Guided **D**ecoding), a training-free cluster-level decoder for MDLMs. Experiments on LLaDA and Dream model families across four reasoning and code-generation benchmarks show that CLAD achieves 1.77\times–8.47\times speedups over Vanilla decoding while maintaining broadly comparable task accuracy in most settings.</abstract>
    <identifier type="citekey">qi-etal-2026-cluster</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.275/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>5785</start>
            <end>5805</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Cluster-Level Attention-Guided Parallel Decoding for Masked Diffusion Language Models
%A Qi, Heqiang
%A Huang, Wei
%A Bai, Mingyuan
%A Meng, Xiangming
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F qi-etal-2026-cluster
%X Masked diffusion language models (MDLMs) enable parallel decoding by predicting all masked positions at each denoising step, yet existing training-free samplers usually decide which positions to commit at token-level granularity. We revisit this granularity and observe that reliable predictions often emerge as contiguous high-confidence spans, suggesting that the unit of parallel commitment can be larger than a single token. We first group adjacent high-confidence candidates into confidence-induced clusters (CICs) as span-level update units. We then use self-attention maps from the same forward pass to estimate inter-cluster dependencies, enabling conflict-aware selection of mutually compatible CICs for parallel commitment. This yields CLAD (**C**luster-**L**evel **A**ttention-Guided **D**ecoding), a training-free cluster-level decoder for MDLMs. Experiments on LLaDA and Dream model families across four reasoning and code-generation benchmarks show that CLAD achieves 1.77\times–8.47\times speedups over Vanilla decoding while maintaining broadly comparable task accuracy in most settings.
%U https://aclanthology.org/2026.findings-emnlp.275/
%P 5785-5805

Markdown (Informal)

[Cluster-Level Attention-Guided Parallel Decoding for Masked Diffusion Language Models](https://aclanthology.org/2026.findings-emnlp.275/) (Qi et al., Findings 2026)

• Cluster-Level Attention-Guided Parallel Decoding for Masked Diffusion Language Models (Qi et al., Findings 2026)

ACL

• Heqiang Qi, Wei Huang, Mingyuan Bai, and Xiangming Meng. 2026. Cluster-Level Attention-Guided Parallel Decoding for Masked Diffusion Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 5785–5805, Budapest, Hungary. Association for Computational Linguistics.