@inproceedings{gupta-etal-2026-beyond,
title = "Beyond Visual Similarity: Rule-Guided Multimodal Clustering with explicit domain rules",
author = "Gupta, Kishor Datta and
Haque, Mohd Ariful and
Kamal, Marufa and
Hasan, Ahmed Rafi and
Rahman, Md. Mahfuzur and
George, Roy",
editor = "Yan, Qianqi and
Montariol, Syrielle and
Fan, Yue and
Gu, Jing and
Pan, Jiayi and
Li, Manling and
Kordjamshidi, Parisa and
Suhr, Alane and
Wang, Xin Eric",
booktitle = "Proceedings of the 4th Workshop on Advances in Language and Vision Research ({ALVR})",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.alvr-main.16/",
pages = "199--208",
ISBN = "979-8-89176-398-2",
abstract = "Traditional clustering techniques often rely solely on similarity in the input data, limiting their ability to capture structural or semantic constraints that are critical in many domains. We introduce the Domain-Aware Rule-Triggered Variational Autoencoder (DART-VAE), a rule-guided multimodal clustering framework that incorporates domain-specific constraints directly into the representation learning process. DART-VAE extends the VAE architecture by embedding explicit rules, semantic representations, and data-driven features into a unified latent space, while enforcing constraint compliance through rule-consistency and violation penalties in the loss function. Unlike conventional clustering methods that rely only on visual similarity or apply rules as post-hoc filters, DART-VAE treats rules as first-class learning signals. The rules are generated by LLMs, structured into knowledge graphs, and enforced through a loss function combining reconstruction, KL divergence, consistency, and violation penalties. Experiments on aircraft and automotive datasets demonstrate that rule-guided clustering produces more operationally meaningful and interpretable clusters{---}for example, isolating UAVs, unifying stealth aircraft, or separating SUVs from sedans{---}while improving traditional clustering metrics. However, the framework faces challenges: LLM-generated rules may hallucinate or conflict, excessive rules risk overfitting, and scaling to complex domains increases computational and consistency difficulties. By combining rule encodings with learned representations, DART-VAE achieves more meaningful and consistent clustering outcomes than purely data-driven models, highlighting the utility of constraint-guided multimodal clustering for complex, knowledge-intensive settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-etal-2026-beyond">
<titleInfo>
<title>Beyond Visual Similarity: Rule-Guided Multimodal Clustering with explicit domain rules</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kishor</namePart>
<namePart type="given">Datta</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohd</namePart>
<namePart type="given">Ariful</namePart>
<namePart type="family">Haque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marufa</namePart>
<namePart type="family">Kamal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="given">Rafi</namePart>
<namePart type="family">Hasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Mahfuzur</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roy</namePart>
<namePart type="family">George</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 4th Workshop on Advances in Language and Vision Research (ALVR)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qianqi</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Syrielle</namePart>
<namePart type="family">Montariol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiayi</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manling</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parisa</namePart>
<namePart type="family">Kordjamshidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alane</namePart>
<namePart type="family">Suhr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="given">Eric</namePart>
<namePart type="family">Wang</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, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-398-2</identifier>
</relatedItem>
<abstract>Traditional clustering techniques often rely solely on similarity in the input data, limiting their ability to capture structural or semantic constraints that are critical in many domains. We introduce the Domain-Aware Rule-Triggered Variational Autoencoder (DART-VAE), a rule-guided multimodal clustering framework that incorporates domain-specific constraints directly into the representation learning process. DART-VAE extends the VAE architecture by embedding explicit rules, semantic representations, and data-driven features into a unified latent space, while enforcing constraint compliance through rule-consistency and violation penalties in the loss function. Unlike conventional clustering methods that rely only on visual similarity or apply rules as post-hoc filters, DART-VAE treats rules as first-class learning signals. The rules are generated by LLMs, structured into knowledge graphs, and enforced through a loss function combining reconstruction, KL divergence, consistency, and violation penalties. Experiments on aircraft and automotive datasets demonstrate that rule-guided clustering produces more operationally meaningful and interpretable clusters—for example, isolating UAVs, unifying stealth aircraft, or separating SUVs from sedans—while improving traditional clustering metrics. However, the framework faces challenges: LLM-generated rules may hallucinate or conflict, excessive rules risk overfitting, and scaling to complex domains increases computational and consistency difficulties. By combining rule encodings with learned representations, DART-VAE achieves more meaningful and consistent clustering outcomes than purely data-driven models, highlighting the utility of constraint-guided multimodal clustering for complex, knowledge-intensive settings.</abstract>
<identifier type="citekey">gupta-etal-2026-beyond</identifier>
<location>
<url>https://aclanthology.org/2026.alvr-main.16/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>199</start>
<end>208</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Visual Similarity: Rule-Guided Multimodal Clustering with explicit domain rules
%A Gupta, Kishor Datta
%A Haque, Mohd Ariful
%A Kamal, Marufa
%A Hasan, Ahmed Rafi
%A Rahman, Md. Mahfuzur
%A George, Roy
%Y Yan, Qianqi
%Y Montariol, Syrielle
%Y Fan, Yue
%Y Gu, Jing
%Y Pan, Jiayi
%Y Li, Manling
%Y Kordjamshidi, Parisa
%Y Suhr, Alane
%Y Wang, Xin Eric
%S Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-398-2
%F gupta-etal-2026-beyond
%X Traditional clustering techniques often rely solely on similarity in the input data, limiting their ability to capture structural or semantic constraints that are critical in many domains. We introduce the Domain-Aware Rule-Triggered Variational Autoencoder (DART-VAE), a rule-guided multimodal clustering framework that incorporates domain-specific constraints directly into the representation learning process. DART-VAE extends the VAE architecture by embedding explicit rules, semantic representations, and data-driven features into a unified latent space, while enforcing constraint compliance through rule-consistency and violation penalties in the loss function. Unlike conventional clustering methods that rely only on visual similarity or apply rules as post-hoc filters, DART-VAE treats rules as first-class learning signals. The rules are generated by LLMs, structured into knowledge graphs, and enforced through a loss function combining reconstruction, KL divergence, consistency, and violation penalties. Experiments on aircraft and automotive datasets demonstrate that rule-guided clustering produces more operationally meaningful and interpretable clusters—for example, isolating UAVs, unifying stealth aircraft, or separating SUVs from sedans—while improving traditional clustering metrics. However, the framework faces challenges: LLM-generated rules may hallucinate or conflict, excessive rules risk overfitting, and scaling to complex domains increases computational and consistency difficulties. By combining rule encodings with learned representations, DART-VAE achieves more meaningful and consistent clustering outcomes than purely data-driven models, highlighting the utility of constraint-guided multimodal clustering for complex, knowledge-intensive settings.
%U https://aclanthology.org/2026.alvr-main.16/
%P 199-208
Markdown (Informal)
[Beyond Visual Similarity: Rule-Guided Multimodal Clustering with explicit domain rules](https://aclanthology.org/2026.alvr-main.16/) (Gupta et al., ALVR 2026)
ACL