@inproceedings{shahroor-etal-2026-memelens,
title = "{M}eme{L}ens: Multilingual Multitask {VLM}s for Memes",
author = "Shahroor, Ali Ezzat and
Kmainasi, Mohamed Bayan and
Hasnat, Abul and
Dimitrov, Dimitar Iliyanov and
Da San Martino, Giovanni and
Nakov, Preslav and
Alam, Firoj",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2290/",
pages = "52102--52128",
ISBN = "979-8-89176-459-0",
abstract = "Memes are a dominant medium for online communication and manipulation because meaning emerges from interactions between embedded text, imagery, and cultural context. Existing meme research is distributed across tasks (e.g., hate, misogyny, propaganda, sentiment, humour) and languages, which limits cross-domain generalization. To address this gap, we propose MemeLens, a unified multilingual, multitask explanation-enhanced Vision-Language Model (VLM) for meme understanding. We consolidate 38 public meme datasets, filter and map dataset-specific labels into a shared taxonomy of 20 tasks spanning harm, targets, figurative/pragmatic intent, and affect. We present a comprehensive empirical analysis across modeling paradigms, task categories, and datasets. Our findings suggest that robust meme understanding requires multimodal training, varies substantially across semantic categories, and remains sensitive to over-specialization when models are fine-tuned on individual datasets rather than trained in a unified setting. We make the experimental resources (Code: https://github.com/MohamedBayan/MemeLens | MemeLens-VLM: https://huggingface.co/QCRI/MemeLens-VLM | MemeLens-Datasets: https://huggingface.co/datasets/QCRI/MemeLens) publicly available to the community."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shahroor-etal-2026-memelens">
<titleInfo>
<title>MemeLens: Multilingual Multitask VLMs for Memes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="given">Ezzat</namePart>
<namePart type="family">Shahroor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="given">Bayan</namePart>
<namePart type="family">Kmainasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abul</namePart>
<namePart type="family">Hasnat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dimitar</namePart>
<namePart type="given">Iliyanov</namePart>
<namePart type="family">Dimitrov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Memes are a dominant medium for online communication and manipulation because meaning emerges from interactions between embedded text, imagery, and cultural context. Existing meme research is distributed across tasks (e.g., hate, misogyny, propaganda, sentiment, humour) and languages, which limits cross-domain generalization. To address this gap, we propose MemeLens, a unified multilingual, multitask explanation-enhanced Vision-Language Model (VLM) for meme understanding. We consolidate 38 public meme datasets, filter and map dataset-specific labels into a shared taxonomy of 20 tasks spanning harm, targets, figurative/pragmatic intent, and affect. We present a comprehensive empirical analysis across modeling paradigms, task categories, and datasets. Our findings suggest that robust meme understanding requires multimodal training, varies substantially across semantic categories, and remains sensitive to over-specialization when models are fine-tuned on individual datasets rather than trained in a unified setting. We make the experimental resources (Code: https://github.com/MohamedBayan/MemeLens | MemeLens-VLM: https://huggingface.co/QCRI/MemeLens-VLM | MemeLens-Datasets: https://huggingface.co/datasets/QCRI/MemeLens) publicly available to the community.</abstract>
<identifier type="citekey">shahroor-etal-2026-memelens</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2290/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>52102</start>
<end>52128</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MemeLens: Multilingual Multitask VLMs for Memes
%A Shahroor, Ali Ezzat
%A Kmainasi, Mohamed Bayan
%A Hasnat, Abul
%A Dimitrov, Dimitar Iliyanov
%A Da San Martino, Giovanni
%A Nakov, Preslav
%A Alam, Firoj
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F shahroor-etal-2026-memelens
%X Memes are a dominant medium for online communication and manipulation because meaning emerges from interactions between embedded text, imagery, and cultural context. Existing meme research is distributed across tasks (e.g., hate, misogyny, propaganda, sentiment, humour) and languages, which limits cross-domain generalization. To address this gap, we propose MemeLens, a unified multilingual, multitask explanation-enhanced Vision-Language Model (VLM) for meme understanding. We consolidate 38 public meme datasets, filter and map dataset-specific labels into a shared taxonomy of 20 tasks spanning harm, targets, figurative/pragmatic intent, and affect. We present a comprehensive empirical analysis across modeling paradigms, task categories, and datasets. Our findings suggest that robust meme understanding requires multimodal training, varies substantially across semantic categories, and remains sensitive to over-specialization when models are fine-tuned on individual datasets rather than trained in a unified setting. We make the experimental resources (Code: https://github.com/MohamedBayan/MemeLens | MemeLens-VLM: https://huggingface.co/QCRI/MemeLens-VLM | MemeLens-Datasets: https://huggingface.co/datasets/QCRI/MemeLens) publicly available to the community.
%U https://aclanthology.org/2026.emnlp-main.2290/
%P 52102-52128
Markdown (Informal)
[MemeLens: Multilingual Multitask VLMs for Memes](https://aclanthology.org/2026.emnlp-main.2290/) (Shahroor et al., EMNLP 2026)
ACL
- Ali Ezzat Shahroor, Mohamed Bayan Kmainasi, Abul Hasnat, Dimitar Iliyanov Dimitrov, Giovanni Da San Martino, Preslav Nakov, and Firoj Alam. 2026. MemeLens: Multilingual Multitask VLMs for Memes. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 52102–52128, Budapest, Hungary. Association for Computational Linguistics.