@inproceedings{huang-etal-2026-generative,
title = "Generative Text-to-Image Retrieval via Hierarchical Identifiers and Semantic Internalization",
author = "Huang, Jie and
Wang, Junjie and
Liao, Xin and
Jiang, Ziyou and
Wang, Wenshuo and
Li, Shoubin and
Wang, Qing",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.632/",
pages = "12972--12986",
ISBN = "979-8-89176-395-1",
abstract = "Generative Retrieval (GR) has emerged as a promising text-to-image paradigm, yet it suffers from limited semantic discriminability, alignment bias, and closed-set restrictions. To address these challenges, we propose SIGMA, a novel framework for Semantic Internalization for Generative Multimodal Alignment. SIGMA constructs multi-granularity hierarchical identifiers to ensure unique, semantically consistent image representations. We further introduce a progressive semantic internalization training strategy augmented with semantic soft labels, which captures fine-grained text-image affinities and enables inductive identifier assignment for unseen samples realizing open-set dynamic indexing capabilities. Experiments on the Flickr30K and MS-COCO datasets demonstrate that SIGMA outperforms state-of-the-art baselines, achieving average Recall@1, Recall@5, and Recall@10 improvements of 10.65{\%}, 8.50{\%}, and 7.00{\%}, respectively."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2026-generative">
<titleInfo>
<title>Generative Text-to-Image Retrieval via Hierarchical Identifiers and Semantic Internalization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junjie</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziyou</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenshuo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shoubin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qing</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>Generative Retrieval (GR) has emerged as a promising text-to-image paradigm, yet it suffers from limited semantic discriminability, alignment bias, and closed-set restrictions. To address these challenges, we propose SIGMA, a novel framework for Semantic Internalization for Generative Multimodal Alignment. SIGMA constructs multi-granularity hierarchical identifiers to ensure unique, semantically consistent image representations. We further introduce a progressive semantic internalization training strategy augmented with semantic soft labels, which captures fine-grained text-image affinities and enables inductive identifier assignment for unseen samples realizing open-set dynamic indexing capabilities. Experiments on the Flickr30K and MS-COCO datasets demonstrate that SIGMA outperforms state-of-the-art baselines, achieving average Recall@1, Recall@5, and Recall@10 improvements of 10.65%, 8.50%, and 7.00%, respectively.</abstract>
<identifier type="citekey">huang-etal-2026-generative</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.632/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>12972</start>
<end>12986</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generative Text-to-Image Retrieval via Hierarchical Identifiers and Semantic Internalization
%A Huang, Jie
%A Wang, Junjie
%A Liao, Xin
%A Jiang, Ziyou
%A Wang, Wenshuo
%A Li, Shoubin
%A Wang, Qing
%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 huang-etal-2026-generative
%X Generative Retrieval (GR) has emerged as a promising text-to-image paradigm, yet it suffers from limited semantic discriminability, alignment bias, and closed-set restrictions. To address these challenges, we propose SIGMA, a novel framework for Semantic Internalization for Generative Multimodal Alignment. SIGMA constructs multi-granularity hierarchical identifiers to ensure unique, semantically consistent image representations. We further introduce a progressive semantic internalization training strategy augmented with semantic soft labels, which captures fine-grained text-image affinities and enables inductive identifier assignment for unseen samples realizing open-set dynamic indexing capabilities. Experiments on the Flickr30K and MS-COCO datasets demonstrate that SIGMA outperforms state-of-the-art baselines, achieving average Recall@1, Recall@5, and Recall@10 improvements of 10.65%, 8.50%, and 7.00%, respectively.
%U https://aclanthology.org/2026.findings-acl.632/
%P 12972-12986
Markdown (Informal)
[Generative Text-to-Image Retrieval via Hierarchical Identifiers and Semantic Internalization](https://aclanthology.org/2026.findings-acl.632/) (Huang et al., Findings 2026)
ACL
- Jie Huang, Junjie Wang, Xin Liao, Ziyou Jiang, Wenshuo Wang, Shoubin Li, and Qing Wang. 2026. Generative Text-to-Image Retrieval via Hierarchical Identifiers and Semantic Internalization. In Findings of the Association for Computational Linguistics: ACL 2026, pages 12972–12986, San Diego, California, United States. Association for Computational Linguistics.