@inproceedings{maiti-chowdhury-2026-modality,
title = "Modality-Specific and Relation-Aware Modeling for Scientific Figure Linking",
author = "Maiti, Bodhisatta and
Chowdhury, Debshree",
editor = "Accomazzi, Alberto and
Ghosal, Tirthankar and
Grezes, Felix and
Lockhart, Kelly and
Alkan, Atilla Kaan",
booktitle = "Proceedings of the 4th Workshop on Artificial Intelligence for Scientific Publications",
month = nov,
year = "2026",
address = "Hengqin, Zhuhai, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wasp-1.27/",
pages = "262--271",
ISBN = "979-8-89176-456-9",
abstract = "We present a modality-specific system for the AstroCLIMB shared task, which predicts relations among astronomical figures and captions. Caption{--}caption, image{--}image, and image{--}caption pairs use different combinations of frozen pretrained representations and supervised classifiers. Image{--}caption prediction first applies a Qwen3-VL 4B/8B exact correspondence gate before classifying the remaining paper relations. Subsequent improvements add astronomy-domain sentence embeddings to the caption branch and a learned visual-projection specialist to the image branch. Across eight Kaggle submissions, macro-F1 increases from 0.3641 to 0.6096. Adding astronomy-specific caption features improves five-fold pooled out-of-fold (OOF) macro-F1 from 0.6071 to 0.6388; the image specialist offers a smaller incremental test-set gain. The direct citation relation, related{\_}papers, remains the most difficult. Results support selecting representations and decision mechanisms according to modality, while highlighting the limitations of recovering citation links from isolated content."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maiti-chowdhury-2026-modality">
<titleInfo>
<title>Modality-Specific and Relation-Aware Modeling for Scientific Figure Linking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bodhisatta</namePart>
<namePart type="family">Maiti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debshree</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Artificial Intelligence for Scientific Publications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Accomazzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Ghosal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Grezes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kelly</namePart>
<namePart type="family">Lockhart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atilla</namePart>
<namePart type="given">Kaan</namePart>
<namePart type="family">Alkan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, Zhuhai, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-456-9</identifier>
</relatedItem>
<abstract>We present a modality-specific system for the AstroCLIMB shared task, which predicts relations among astronomical figures and captions. Caption–caption, image–image, and image–caption pairs use different combinations of frozen pretrained representations and supervised classifiers. Image–caption prediction first applies a Qwen3-VL 4B/8B exact correspondence gate before classifying the remaining paper relations. Subsequent improvements add astronomy-domain sentence embeddings to the caption branch and a learned visual-projection specialist to the image branch. Across eight Kaggle submissions, macro-F1 increases from 0.3641 to 0.6096. Adding astronomy-specific caption features improves five-fold pooled out-of-fold (OOF) macro-F1 from 0.6071 to 0.6388; the image specialist offers a smaller incremental test-set gain. The direct citation relation, related_papers, remains the most difficult. Results support selecting representations and decision mechanisms according to modality, while highlighting the limitations of recovering citation links from isolated content.</abstract>
<identifier type="citekey">maiti-chowdhury-2026-modality</identifier>
<location>
<url>https://aclanthology.org/2026.wasp-1.27/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>262</start>
<end>271</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modality-Specific and Relation-Aware Modeling for Scientific Figure Linking
%A Maiti, Bodhisatta
%A Chowdhury, Debshree
%Y Accomazzi, Alberto
%Y Ghosal, Tirthankar
%Y Grezes, Felix
%Y Lockhart, Kelly
%Y Alkan, Atilla Kaan
%S Proceedings of the 4th Workshop on Artificial Intelligence for Scientific Publications
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, Zhuhai, China
%@ 979-8-89176-456-9
%F maiti-chowdhury-2026-modality
%X We present a modality-specific system for the AstroCLIMB shared task, which predicts relations among astronomical figures and captions. Caption–caption, image–image, and image–caption pairs use different combinations of frozen pretrained representations and supervised classifiers. Image–caption prediction first applies a Qwen3-VL 4B/8B exact correspondence gate before classifying the remaining paper relations. Subsequent improvements add astronomy-domain sentence embeddings to the caption branch and a learned visual-projection specialist to the image branch. Across eight Kaggle submissions, macro-F1 increases from 0.3641 to 0.6096. Adding astronomy-specific caption features improves five-fold pooled out-of-fold (OOF) macro-F1 from 0.6071 to 0.6388; the image specialist offers a smaller incremental test-set gain. The direct citation relation, related_papers, remains the most difficult. Results support selecting representations and decision mechanisms according to modality, while highlighting the limitations of recovering citation links from isolated content.
%U https://aclanthology.org/2026.wasp-1.27/
%P 262-271
Markdown (Informal)
[Modality-Specific and Relation-Aware Modeling for Scientific Figure Linking](https://aclanthology.org/2026.wasp-1.27/) (Maiti & Chowdhury, WASP 2026)
ACL