<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="brisson-etal-2026-anandasky">
    <titleInfo>
        <title>AnandaSky: A Vision–Language Model for Line-Level Transcription of Historical Sinographic Documents</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Colin</namePart>
        <namePart type="family">Brisson</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ayoub</namePart>
        <namePart type="family">Kahfy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Frédéric</namePart>
        <namePart type="family">Constant</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marc</namePart>
        <namePart type="family">Bui</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Rachele</namePart>
            <namePart type="family">Sprugnoli</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marco</namePart>
            <namePart type="family">Passarotti</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resources Association (ELRA)</publisher>
            <place>
                <placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We present AnandaSky, a vision–language model for line-level transcription of historical sinographic documents. The model combines a compact high-resolution visual encoder with global attention, 10px patches, uncompressed visual prefix and a Qwen3-0.6B autoregressive decoder. It is trained at scale on 4M annotated lines from documents produced in China and Korea between the 8th and 20th centuries. Across in-domain and held-out public benchmarks, AnandaSky achieves sub-1% CER on five of eight datasets, sets a new state of the art on MTHv2 with 0.92% CER, and shows strong transfer to unseen collections. For EvaHan 2026, full fine-tuning on the organizers’ data to match task-specific annotation conventions reduces CER relative to the official baseline by 5.2% on prints and 12.1% on manuscripts, despite using one-tenth as many parameters.</abstract>
    <identifier type="citekey">brisson-etal-2026-anandasky</identifier>
    <identifier type="doi">10.63317/3pk7cv8hxzod</identifier>
    <location>
        <url>https://aclanthology.org/2026.lt4hala-1.32/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>311</start>
            <end>321</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T AnandaSky: A Vision–Language Model for Line-Level Transcription of Historical Sinographic Documents
%A Brisson, Colin
%A Kahfy, Ayoub
%A Constant, Frédéric
%A Bui, Marc
%Y Sprugnoli, Rachele
%Y Passarotti, Marco
%S Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F brisson-etal-2026-anandasky
%X We present AnandaSky, a vision–language model for line-level transcription of historical sinographic documents. The model combines a compact high-resolution visual encoder with global attention, 10px patches, uncompressed visual prefix and a Qwen3-0.6B autoregressive decoder. It is trained at scale on 4M annotated lines from documents produced in China and Korea between the 8th and 20th centuries. Across in-domain and held-out public benchmarks, AnandaSky achieves sub-1% CER on five of eight datasets, sets a new state of the art on MTHv2 with 0.92% CER, and shows strong transfer to unseen collections. For EvaHan 2026, full fine-tuning on the organizers’ data to match task-specific annotation conventions reduces CER relative to the official baseline by 5.2% on prints and 12.1% on manuscripts, despite using one-tenth as many parameters.
%R 10.63317/3pk7cv8hxzod
%U https://aclanthology.org/2026.lt4hala-1.32/
%U https://doi.org/10.63317/3pk7cv8hxzod
%P 311-321

Markdown (Informal)

[AnandaSky: A Vision–Language Model for Line-Level Transcription of Historical Sinographic Documents](https://aclanthology.org/2026.lt4hala-1.32/) (Brisson et al., LT4HALA 2026)

• AnandaSky: A Vision–Language Model for Line-Level Transcription of Historical Sinographic Documents (Brisson et al., LT4HALA 2026)

ACL

• Colin Brisson, Ayoub Kahfy, Frédéric Constant, and Marc Bui. 2026. AnandaSky: A Vision–Language Model for Line-Level Transcription of Historical Sinographic Documents. In Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026, pages 311–321, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).