@inproceedings{wu-etal-2026-mmclip,
title = "{MMCLIP}: Cross-Modal Attention Masked Modelling for Medical Language-Image Pre-Training",
author = "Wu, Biao and
Xie, Yutong and
Zhang, Zeyu and
Phan, Vu Minh Hieu and
Chen, Qi and
Chen, Ling and
Wu, Qi",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.113/",
pages = "2440--2455",
ISBN = "979-8-89176-390-6",
abstract = "Vision-and-language pretraining (VLP) in medicine leverages contrastive learning on image{--}text pairs, often enhanced with masked modeling. However, existing methods face two challenges: difficulty reconstructing key pathological features due to limited data, and reliance on either paired or image-only datasets without combining both. To address this, we propose **MMCLIP** (**M**asked **M**edical **C**ontrastive **L**anguage{--}**I**mage **P**re-training), which introduces two modules: **AttMIM**: Masks image features highly correlated with text to improve reconstruction of fine medical details. **EntMLM**: Masks key medical entities in text and reconstructs them using visual cues. Furthermore, **MMCLIP** incorporates unpaired data through disease-kind prompts, achieving state-of-the-art performance in zero-shot and fine-tuning across five benchmarks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2026-mmclip">
<titleInfo>
<title>MMCLIP: Cross-Modal Attention Masked Modelling for Medical Language-Image Pre-Training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Biao</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yutong</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vu</namePart>
<namePart type="given">Minh</namePart>
<namePart type="given">Hieu</namePart>
<namePart type="family">Phan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ling</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Wu</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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Vision-and-language pretraining (VLP) in medicine leverages contrastive learning on image–text pairs, often enhanced with masked modeling. However, existing methods face two challenges: difficulty reconstructing key pathological features due to limited data, and reliance on either paired or image-only datasets without combining both. To address this, we propose **MMCLIP** (**M**asked **M**edical **C**ontrastive **L**anguage–**I**mage **P**re-training), which introduces two modules: **AttMIM**: Masks image features highly correlated with text to improve reconstruction of fine medical details. **EntMLM**: Masks key medical entities in text and reconstructs them using visual cues. Furthermore, **MMCLIP** incorporates unpaired data through disease-kind prompts, achieving state-of-the-art performance in zero-shot and fine-tuning across five benchmarks.</abstract>
<identifier type="citekey">wu-etal-2026-mmclip</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.113/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2440</start>
<end>2455</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MMCLIP: Cross-Modal Attention Masked Modelling for Medical Language-Image Pre-Training
%A Wu, Biao
%A Xie, Yutong
%A Zhang, Zeyu
%A Phan, Vu Minh Hieu
%A Chen, Qi
%A Chen, Ling
%A Wu, Qi
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F wu-etal-2026-mmclip
%X Vision-and-language pretraining (VLP) in medicine leverages contrastive learning on image–text pairs, often enhanced with masked modeling. However, existing methods face two challenges: difficulty reconstructing key pathological features due to limited data, and reliance on either paired or image-only datasets without combining both. To address this, we propose **MMCLIP** (**M**asked **M**edical **C**ontrastive **L**anguage–**I**mage **P**re-training), which introduces two modules: **AttMIM**: Masks image features highly correlated with text to improve reconstruction of fine medical details. **EntMLM**: Masks key medical entities in text and reconstructs them using visual cues. Furthermore, **MMCLIP** incorporates unpaired data through disease-kind prompts, achieving state-of-the-art performance in zero-shot and fine-tuning across five benchmarks.
%U https://aclanthology.org/2026.acl-long.113/
%P 2440-2455
Markdown (Informal)
[MMCLIP: Cross-Modal Attention Masked Modelling for Medical Language-Image Pre-Training](https://aclanthology.org/2026.acl-long.113/) (Wu et al., ACL 2026)
ACL
- Biao Wu, Yutong Xie, Zeyu Zhang, Vu Minh Hieu Phan, Qi Chen, Ling Chen, and Qi Wu. 2026. MMCLIP: Cross-Modal Attention Masked Modelling for Medical Language-Image Pre-Training. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2440–2455, San Diego, California, United States. Association for Computational Linguistics.