AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

MetaGPT: A Large Vision-Language Model for Meme Metaphor Understanding

Bo Xu, Chenyuan Wang, Xinyu Chen, Hongfei Lin, Feng Xia

AAAI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces MetaGPT, described as the first vision-language model for meme metaphor understanding, aimed at recognizing and comprehending metaphors in memes without manual annotation.

Problem

Metaphor understanding in memes relies heavily on manual annotation, and mainstream vision-language models still struggle to recognize and comprehend meme metaphors.

Approach

A vision-language model dedicated to meme metaphor understanding, intended to reduce dependence on manual metaphor annotations. Details beyond the abstract are not available.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add OCR meme text as extra input (ablation)MetaGPT · MEMECAP metaphor domain extraction (tau=0.5)macro F1: 29.13 -> 26.44Hurt
replace inpainted patches with segmented original image regions (ablation)MetaGPT · MEMECAP metaphor domain extraction (tau=0.5)macro F1: 29.13 -> 27.46Hurt
add shallow and mid-level CLIP layer features (ablation)MetaGPT · MEMECAP metaphor domain extraction (tau=0.5)macro F1: 29.13 -> 28.33 / 28.63 / 28.03Hurt
add shallow and mid-level CLIP layer features (ablation)MetaGPT · MET-Meme metaphor detectionweighted F1: 87.33 -> 86.54 / 86.83 / 86.96No clear effect
add OCR meme text as extra input (ablation)MetaGPT · MEMECAP meme interpretationaverage of 8 metrics: 55.89 -> 51.36Hurt
add MetaClean module (inpainting plus quadrant patches) (ablation)MetaGPT · MEMECAP metaphor domain extraction (tau=0.5)macro F1Improved
add MetaClean module (ablation)MetaGPT · MET-Meme metaphor detectionF1No clear effect
increase MUnd training data ratio (ablation)MetaGPT · all three taskstask metricsImproved
fine-tune LLaVA-v1.5-7B on MUnd with MetaClean vs larger baselinesMetaGPT · MET-Meme metaphor detectionweighted F1: 68.53 -> 87.33Improved
scale model parameters without metaphor trainingLLaVA-v1.6 / CogVLM · MET-Meme metaphor detectionweighted F1: 19.19 and 12.18No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy