MemeLens: Multilingual Multitask VLMs for Memes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shahroor, Ali Ezzat, Kmainasi, Mohamed Bayan, Hasnat, Abul, Dimitrov, Dimitar, Martino, Giovanni Da San, Nakov, Preslav, Alam, Firoj
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909008979296256
author Shahroor, Ali Ezzat
Kmainasi, Mohamed Bayan
Hasnat, Abul
Dimitrov, Dimitar
Martino, Giovanni Da San
Nakov, Preslav
Alam, Firoj
author_facet Shahroor, Ali Ezzat
Kmainasi, Mohamed Bayan
Hasnat, Abul
Dimitrov, Dimitar
Martino, Giovanni Da San
Nakov, Preslav
Alam, Firoj
contents 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 (hate, misogyny, propaganda, sentiment, humour) and languages, which limits cross-domain generalization. To address this gap we propose MemeLens, a unified multilingual and 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, exhibits substantial variation 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 (https://github.com/MohamedBayan/MemeLens), model (https://huggingface.co/QCRI/MemeLens-VLM) and datasets (https://huggingface.co/datasets/QCRI/MemeLens) publicly available to the community.
format Preprint
id arxiv_https___arxiv_org_abs_2601_12539
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MemeLens: Multilingual Multitask VLMs for Memes
Shahroor, Ali Ezzat
Kmainasi, Mohamed Bayan
Hasnat, Abul
Dimitrov, Dimitar
Martino, Giovanni Da San
Nakov, Preslav
Alam, Firoj
Artificial Intelligence
Computation and Language
68T50
I.2.7
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 (hate, misogyny, propaganda, sentiment, humour) and languages, which limits cross-domain generalization. To address this gap we propose MemeLens, a unified multilingual and 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, exhibits substantial variation 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 (https://github.com/MohamedBayan/MemeLens), model (https://huggingface.co/QCRI/MemeLens-VLM) and datasets (https://huggingface.co/datasets/QCRI/MemeLens) publicly available to the community.
title MemeLens: Multilingual Multitask VLMs for Memes
topic Artificial Intelligence
Computation and Language
68T50
I.2.7
url https://arxiv.org/abs/2601.12539