Skip to content
conftrace_
2026 EMNLP EMNLP 2026

MemeLens: Multilingual Multitask VLMs for Memes

AbstractMemes 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.

More from EMNLP 2026

All EMNLP 2026 papers →