<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-2026-fbs">
    <titleInfo>
        <title>FBS: Modeling Native Parallel Reading inside a Transformer</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tongxi</namePart>
        <namePart type="family">Wang</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>Findings of the Association for Computational Linguistics: ACL 2026</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">979-8-89176-395-1</identifier>
    </relatedItem>
    <abstract>Large language models (LLMs) excel across many tasks, yet inference is still dominated by strictly token-by-token autoregression. Existing acceleration methods largely patch this pipeline and miss core human-reading ingredients: content-adaptive foresight, chunk-structure-aware compute allocation, and train–test consistency for preview/skimming. We propose the Fovea–Block–Skip Transformer (FBS), which injects a causal, trainable loop into Transformers via Parafovea-Attention Window (PAW), Chunk-Head (CH), and Skip-Gate (SG). Across diverse benchmarks, FBS improves the quality-efficiency trade-off without increasing parameters, and ablations show the three modules are complementary.</abstract>
    <identifier type="citekey">wang-2026-fbs</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-acl.200/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>4106</start>
            <end>4137</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T FBS: Modeling Native Parallel Reading inside a Transformer
%A Wang, Tongxi
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F wang-2026-fbs
%X Large language models (LLMs) excel across many tasks, yet inference is still dominated by strictly token-by-token autoregression. Existing acceleration methods largely patch this pipeline and miss core human-reading ingredients: content-adaptive foresight, chunk-structure-aware compute allocation, and train–test consistency for preview/skimming. We propose the Fovea–Block–Skip Transformer (FBS), which injects a causal, trainable loop into Transformers via Parafovea-Attention Window (PAW), Chunk-Head (CH), and Skip-Gate (SG). Across diverse benchmarks, FBS improves the quality-efficiency trade-off without increasing parameters, and ablations show the three modules are complementary.
%U https://aclanthology.org/2026.findings-acl.200/
%P 4106-4137

Markdown (Informal)

[FBS: Modeling Native Parallel Reading inside a Transformer](https://aclanthology.org/2026.findings-acl.200/) (Wang, Findings 2026)

• FBS: Modeling Native Parallel Reading inside a Transformer (Wang, Findings 2026)

ACL

• Tongxi Wang. 2026. FBS: Modeling Native Parallel Reading inside a Transformer. In Findings of the Association for Computational Linguistics: ACL 2026, pages 4106–4137, San Diego, California, United States. Association for Computational Linguistics.