MemeLens-VLM

MemeLens is a unified multilingual, multitask Vision-Language Model (VLM) for meme understanding. It is fine-tuned from Qwen3-VL-8B-Instruct using a classify-then-explain training strategy on the MemeLens dataset, which consolidates 38 public meme datasets across 20 tasks and 9 languages.

Paper: MemeLens: Multilingual Multitask VLMs for Memes

Overview

Base model	Qwen3-VL-8B-Instruct
Training	Classify-then-explain (multi-stage)
Tasks	20 tasks: harm, targets, figurative/pragmatic intent, affect
Languages	AR, BN, DE, EN, ES, HI, RO, RU, ZH
Datasets	38 consolidated public meme datasets

Results

Overall Comparison

Model / Modality	Acc	M-F1	W-F1
Uni-modal (Text)	65.0	0.460	0.590
Uni-modal (Image)	63.6	0.472	0.600
Multi-modal (Seq-Classification)	71.0	0.580	0.680
GPT-4.1 (Zero-Shot)	61.2	0.533	0.599
Qwen3-VL-8B-Instruct (Zero-Shot)	55.1	0.482	0.539
InternVL3.5-8B (Zero-Shot)	55.4	0.476	0.545
Gemma-3-12B (Zero-Shot)	48.2	0.439	0.485
Qwen3-2B (Zero-Shot)	45.6	0.394	0.431
Phi-3.5-Vision-4.2B (Zero-Shot)	43.8	0.393	0.447
MemeLens (Ours)	74.1	0.625	0.720

Per-Dataset Breakdown

Dataset	Task	Lang.	Text-Only (Acc/Ma/W)	Image-Only (Acc/Ma/W)	MM-Seq (Acc/Ma/W)	MemeLens (Acc/Ma/W)
BanglaAbuse	Abuse	BN	.660/.564/.615	.680/.628/.663	.731/.698/.723	.787/.759/.782
RoMemes	Deepfake	RO	.634/.259/.493	.645/.399/.630	.575/.338/.551	.770/.491/.753
HarMeme (Co)	Harmful	EN	.712/.499/.706	.703/.443/.677	.811/.546/.797	.748/.523/.740
HarMeme	Harmful	EN	.499/.338/.489	.535/.362/.527	.590/.400/.590	.622/.467/.617
Prop2Hate	Propaganda	AR	.746/.427/.637	.743/.426/.636	.800/.650/.760	.772/.546/.703
MUTE	Propaganda	BN	.642/.556/.602	.688/.659/.682	.730/.710/.730	.719/.700/.718
Multi3Hate	Hateful	DE	.590/.371/.438	.557/.504/.533	.720/.710/.720	.754/.731/.745
MIMIC_Isl	Hateful	EN	.647/.633/.635	.580/.576/.577	.510/.340/.350	.707/.707/.707
MMHS	Hateful	EN	.631/.387/.488	.621/.495/.561	.630/.500/.570	.614/.516/.568
Multi3Hate	Hateful	EN	.574/.573/.573	.508/.507/.507	.770/.770/.770	.741/.735/.734
FHM	Hateful	EN	.633/.541/.592	.623/.507/.567	.760/.740/.760	.798/.782/.798
Multi3Hate	Hateful	ES	.557/.358/.399	.672/.661/.668	.620/.600/.610	.800/.796/.799
Multi3Hate	Hateful	HI	.656/.579/.618	.574/.528/.559	.750/.750/.760	.754/.724/.744
Multi3Hate	Hateful	ZH	.639/.390/.499	.574/.470/.535	.640/.610/.640	.770/.740/.765
Memotion	Humor	EN	.353/.204/.276	.325/.235/.297	.350/.250/.310	.352/.248/.316
MET-Meme	Intention	EN	.464/.353/.444	.383/.295/.363	.320/.220/.340	.524/.442/.514
MET-Meme	Intention	ZH	.621/.443/.611	.443/.212/.376	.670/.470/.660	.710/.521/.701
MET-Meme	Metaphor	EN	.810/.725/.796	.814/.724/.797	.870/.820/.870	.867/.821/.863
MET-Meme	Metaphor	ZH	.847/.838/.846	.678/.636/.662	.900/.890/.890	.866/.859/.865
MAMI	Misogyny	EN	.623/.620/.620	.628/.611/.611	.750/.740/.740	.849/.849/.849
MIMIC2024	Misogyny (Cat.)	HI-EN	.470/.146/.412	.470/.146/.412	.660/.290/.430	.766/.592/.659
MIMIC2024	Misogyny	HI-EN	.673/.671/.671	.630/.246/.570	.850/.850/.850	.899/.899/.899
Memotion	Motivational	EN	.647/.399/.512	.608/.451/.537	.640/.450/.540	.637/.450/.545
MAMI	Objectification	EN	.670/.503/.590	.732/.671/.714	.810/.780/.810	.835/.797/.826
Memotion	Offensive	EN	.388/.140/.217	.371/.227/.334	.390/.220/.330	.386/.215/.325
MET-Meme	Offensive	EN	.748/.242/.667	.742/.233/.658	.740/.310/.710	.748/.309/.708
MET-Meme	Offensive	ZH	.803/.485/.787	.742/.223/.684	.810/.500/.790	.830/.535/.819
RoMemes	Political	RO	.677/.404/.547	.656/.524/.613	.830/.780/.820	.867/.834/.858
ArMeme	Propaganda	AR	.755/.639/.734	.735/.554/.685	.790/.690/.770	.789/.679/.765
BanglaAbuse	Sarcasm	BN	.639/.568/.599	.656/.636/.651	.680/.660/.670	.674/.661/.672
Memotion	Sarcasm	EN	.502/.167/.335	.468/.195/.352	.510/.170/.340	.501/.167/.337
MAMI	Shaming	EN	.854/.461/.787	.834/.610/.819	.870/.710/.870	.898/.719/.883
MAMI	Stereotype	EN	.661/.561/.624	.729/.336/.707	.740/.700/.730	.784/.739/.772
HarMeme (Co)	Target	EN	.777/.449/.788	.729/.336/.707	.870/.550/.870	.823/.420/.840
HarMeme	Target	EN	.485/.314/.479	.451/.204/.404	.590/.350/.580	.562/.493/.565
Toxic	Toxic	RU	.826/.493/.771	.839/.495/.777	.860/.700/.850	.866/.691/.853
MAMI	Violence	EN	.853/.504/.793	.722/.618/.702	.910/.770/.890	.923/.809/.914
BanglaAbuse	Vulgar	BN	.743/.680/.740	.743/.680/.740	.800/.750/.800	.827/.772/.821
Average			0.650/0.460/0.590	0.636/0.472/0.600	0.706/0.579/0.678	0.741/0.625/0.720

Acc = Accuracy, Ma = Macro-F1, W = Weighted-F1. Bold indicates best performance for the dataset's official evaluation metric.

Supported Tasks

The model supports 20 meme understanding tasks across multiple categories:

Category	Tasks
Harm	Hateful, Harmful, Toxic, Abusive, Vulgar
Targets	Target identification, Misogyny, Misogyny Categories, Objectification, Shaming, Stereotype, Violence
Figurative/Pragmatic	Propaganda, Metaphor, Intention, Sarcasm, Deepfake, Political
Affect	Humor, Offensive, Motivational, Sentiment

Usage

from transformers import Qwen3VLForConditionalGeneration, AutoProcessor
from PIL import Image

model = Qwen3VLForConditionalGeneration.from_pretrained("QCRI/MemeLens-VLM", torch_dtype="auto", device_map="auto")
processor = AutoProcessor.from_pretrained("QCRI/MemeLens-VLM")

image = Image.open("path/to/meme.jpg")

messages = [
    {"role": "system", "content": "You are an expert social media image analyzer specializing in identifying hateful content in memes."},
    {"role": "user", "content": [
        {"type": "image"},
        {"type": "text", "text": (
            "Analyze the content of the meme to see if it promotes or displays hateful views against "
            "specific individuals or groups. Look for discriminatory, prejudiced, or hate speech elements "
            "associated with protected characteristics, including race, religion, and gender. "
            "Classify as: 'hateful' if present, or 'not-hateful' if absent.\n\n"
            "IMPORTANT: Your response must strictly follow this format:\n"
            "'Label: <label>\nExplanation: <explanation>'\n"
            "where <label> is your classification and <explanation> provides a brief justification "
            "for your decision based on the visual and textual content.\n\n"
            "Text extracted from meme: <OCR text here>"
        )}
    ]}
]

text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = processor(text=[text], images=[image], padding=True, return_tensors="pt").to(model.device)

output_ids = model.generate(**inputs, max_new_tokens=512)
output_text = processor.batch_decode(output_ids[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)[0]
print(output_text)

Prompt Format

The model uses a system prompt + user instruction format. Each task has a specific system prompt and instruction template.

Output format (all tasks):

Label: <label>
Explanation: <explanation>

Task Prompts Reference

Note: All user prompts must end with the following suffix (omitted below for brevity):

IMPORTANT: Your response must strictly follow this format:
'Label: <label>
Explanation: <explanation>'
where <label> is your classification and <explanation> provides a brief justification
for your decision based on the visual and textual content.

Text extracted from meme: <OCR text>

Arabic (AR)

Hateful Content Detection (Prop2Hate)

System: You are an expert social media image analyzer specializing in identifying hateful content in memes. Instruction: <image> Analyze the content of the Arabic meme and determine if it includes hateful language. Consider whether it displays hatred, discrimination, or bias based on identity or protected traits. Classify as: 'Hateful' if applicable, otherwise 'not-hateful'. Labels: Hateful, not-hateful

Propaganda Detection (ArMeme)

System: You are an expert social media analyst specializing in identifying propaganda techniques in memes. Instruction: <image> Identify if the given Arabic meme is an example of propaganda by checking for biased or misleading narratives intended to affect political or ideological perspectives. Select: 'propaganda' or 'not-propaganda' as appropriate. Labels: propaganda, not-propaganda

Bengali (BN)

Abuse Detection (BanglaAbuseMeme)

System: You are an expert social media image analyzer specializing in identifying abusive content in memes. Instruction: <image> Examine the Bengali meme and decide whether it features abusive content. This includes any form of verbal abuse or personal offense. Classify as: 'abusive' or 'not-abusive'. Labels: abusive, not-abusive

Hateful Content Detection (MUTE)

System: You are an expert social media image analyzer specializing in identifying hateful content in memes. Instruction: <image> Is the provided Bengali meme hateful in nature? Review the meme for any content that expresses discrimination or prejudice. After your review, select one of the two possible classifications. Classify as: 'hateful' or 'not-hateful'. Labels: hateful, not-hateful

Sarcasm Detection (BanglaAbuseMeme)

System: You are an expert social media image analyzer specializing in identifying abusive content in memes. Instruction: <image> Assess the communication style of the Bengali meme. Does it rely on sarcasm to make its point? If the meme is straightforward and means exactly what it says, it is not sarcastic. Classify the content as: 'sarcasm' or 'not-sarcasm'. Labels: sarcasm, not-sarcasm

Sentiment Analysis (BanglaAbuseMeme)

System: You are an expert social media image analyzer specializing in identifying abusive content in memes. Instruction: <image> Examine the Bengali meme and identify the sentiment it conveys. Classify the emotion as: 'positive', 'negative', or 'neutral'. Labels: positive, negative, neutral

Vulgar Content Detection (BanglaAbuseMeme)

System: You are an expert social media image analyzer specializing in identifying abusive content in memes. Instruction: <image> Evaluate the Bengali meme to see if vulgarity is present. Search for crude, obscene, or improper language or images. Classify as: 'vulgar' if such content is found, otherwise use 'not-vulgar'. Labels: vulgar, not-vulgar

Chinese (ZH)

Hateful Content Detection (Multi3Hate)

System: You are an expert social media image analyzer specializing in identifying hateful content in memes. Instruction: <image> Your objective is to classify the Chinese meme based on its content. Determine if it conveys a hateful message targeting any specific group. Use one of the two provided labels: 'hateful' or 'not-hateful'. Labels: hateful, not-hateful

Intention Detection (MET-Meme)

System: You are an expert social media image analyzer specializing in detecting intentions in memes. Instruction: <image> Please review the Chinese meme and decide on the main reason it was created. Categorize its purpose using one of the provided labels which are: 'Entertaining' for amusement, 'Expressive' for emotional expression, 'Interactive' for engagement, 'Offensive' for provocative intent, or 'Other' for unclear intentions. Labels: Entertaining, Expressive, Interactive, Offensive, Other

Metaphor Detection (MET-Meme)

System: You are an expert social media image analyzer specializing in identifying metaphors in memes. Instruction: <image> Identify whether the Chinese meme exemplifies metaphorical communication by spotting elements of indirect meaning or symbolism, as opposed to stating facts directly. Classify as: 'Metaphorical' if you find figurative elements, otherwise choose 'Literal'. Labels: Metaphorical, Literal

Offensive Content Detection (MET-Meme)

System: You are an expert social media image analyzer specializing in identifying offensive content in memes. Instruction: <image> Identify the degree of offensiveness in the supplied Chinese meme. Choose one of the following precise classifications: 'not-offensive', 'slightly-offensive', 'moderately-offensive', or 'very-offensive'. Labels: not-offensive, slightly-offensive, moderately-offensive, very-offensive

Sentiment Category (MET-Meme)

System: You are an expert social media image analyzer specializing in sentiment analysis of memes. Instruction: <image> Classify the provided Chinese meme based on its primary emotional content. Your selection must be one of the following: 'Happiness', 'Sorrow', 'Anger', 'Fear', 'Surprise', 'Love', or 'Hate'. Labels: Happiness, Sorrow, Anger, Fear, Surprise, Love, Hate

Sentiment Degree (MET-Meme)

System: You are an expert social media image analyzer specializing in sentiment analysis of memes. Instruction: <image> Please examine the Chinese meme and classify how strongly its sentiment is expressed. Use the following labels for the intensity: 'slightly' for a low degree, 'moderately' for a medium degree, and 'very' for a high degree of emotional expression. Labels: slightly, moderately, very

English (EN)

Harmful Content Detection (HarMeme)

System: You are an expert social media image analyzer specializing in identifying harmful content in memes. Instruction: <image> Categorize the meme based on a three-point scale of harmfulness. Scrutinize the image and text to make your judgment. Classify as: 'not-harmful', 'partially-harmful', or 'very-harmful'. Labels: not-harmful, partially-harmful, very-harmful

Harmful Content Detection — COVID-19 (HarMeme)

System: You are an expert social media image analyzer specializing in identifying harmful content in memes. Instruction: <image> Assess the meme's content concerning the COVID-19 crisis and decide on its classification. The categories reflect increasing levels of potential harm, from none to severe. Classify the meme as either: 'not-harmful', 'partially-harmful', or 'very-harmful'. Labels: not-harmful, partially-harmful, very-harmful

Hateful Content Detection (FHM)

System: You are an expert social media image analyzer specializing in identifying hateful content in memes. Instruction: <image> Analyze the content of the meme to see if it promotes or displays hateful views against specific individuals or groups. Look for discriminatory, prejudiced, or hate speech elements associated with protected characteristics, including race, religion, and gender. Classify as: 'hateful' if present, or 'not-hateful' if absent. Labels: hateful, not-hateful

Hateful Content Detection (MMHS)

System: You are an expert social media image analyzer specializing in identifying hateful content in memes. Instruction: <image> Examine the meme and determine if it contains any form of hate speech. Classify as: 'hateful' if the content is discriminatory or disparaging towards a person or group, and 'not-hateful' if it is not. Labels: hateful, not-hateful

Hateful Content Detection (Multi3Hate)

System: You are an expert social media image analyzer specializing in identifying hateful content in memes. Instruction: <image> Analyze the provided English meme to determine if it contains any form of hate speech, prejudice, or discriminatory content. Based on your analysis, categorize the meme using one of the following labels. Classify as: 'hateful' or 'not-hateful'. Labels: hateful, not-hateful

Hateful Content Detection — Islamophobia (MIMIC)

System: You are an expert social media image analyzer specializing in identifying hateful content in memes. Instruction: <image> Please evaluate the provided meme. Your task is to determine if it communicates hateful or discriminatory messages specifically targeting Islam or its adherents. Classify as: 'hateful' or 'not-hateful'. Labels: hateful, not-hateful

Humor Classification (Memotion)

System: You are an expert social media image analyzer specializing in emotion recognition in memes. Instruction: <image> Classify the level of humor in the meme. Analyze how funny the content is based on its comedic elements. Classify as: 'not-funny' for unfunny content, 'funny' for mildly humorous, 'very-funny' for highly humorous, or 'hilarious' for extremely funny content. Labels: not-funny, funny, very-funny, hilarious

Intention Detection (MET-Meme)

System: You are an expert social media image analyzer specializing in detecting intentions in memes. Instruction: <image> Categorize the primary purpose of the meme. What was the creator's main goal in making it? Please classify the intention as: 'Entertaining', 'Expressive', 'Interactive', or 'Offensive'. Labels: Entertaining, Expressive, Interactive, Offensive

Metaphor Detection (MET-Meme)

System: You are an expert social media image analyzer specializing in identifying metaphors in memes. Instruction: <image> Determine whether the meme uses metaphorical or literal language. Analyze if the content relies on figurative language, symbolism, or indirect meaning. Classify as: 'Metaphorical' if it uses figurative language, or 'Literal' if the meaning is direct and straightforward. Labels: Metaphorical, Literal

Misogyny Detection (MAMI)

System: You are an expert social media image analyzer specializing in identifying misogynistic content in memes. Instruction: <image> Scrutinize the meme to detect any indication of misogynous content, including aspects like prejudice, discrimination, objectification, or aversion towards women. Label the meme 'misogynous' when identified, or 'not-misogynous' if none are observed. Labels: misogynous, not-misogynous

Motivational Detection (Memotion)

System: You are an expert social media image analyzer specializing in emotion recognition in memes. Instruction: <image> Assess if the meme fits the motivational category by checking for inspirational, encouraging, or uplifting content. Classify using: 'motivational' for memes with these features, 'not-motivational' otherwise. Labels: motivational, not-motivational

Objectification Detection (MAMI)

System: You are an expert social media image analyzer specializing in identifying objectification in memes. Instruction: <image> Evaluate the meme for signs that it depicts women as objects, prioritizes appearance over character, or undermines their autonomy. Classify as: 'objectification' when such elements are present; otherwise, use 'not-objectification'. Labels: objectification, not-objectification

Offensive Content Detection (Memotion)

System: You are an expert social media image analyzer specializing in identifying offensive content in memes. Instruction: <image> Carefully read the meme and judge how objectionable the material is. Then, classify it as: 'not-offensive', 'slightly-offensive', 'very-offensive', or 'hateful-offensive', based on the degree of offensiveness present. Labels: not-offensive, slightly-offensive, very-offensive, hateful-offensive

Offensive Content Detection (MET-Meme)

System: You are an expert social media image analyzer specializing in identifying offensive content in memes. Instruction: <image> Judge the degree of offensiveness present in the meme. Evaluate how inappropriate or offensive the content is, and assign one of the following labels: 'not-offensive', 'slightly-offensive', 'moderately-offensive', or 'very-offensive'. Labels: not-offensive, slightly-offensive, moderately-offensive, very-offensive

Sarcasm Detection (Memotion)

System: You are an expert social media image analyzer specializing in emotion recognition in memes. Instruction: <image> Your objective is to identify the type of sarcasm used in the meme. Determine if the content is straightforward or if it uses irony to convey its message. Please assign a classification based on the complexity of the sarcasm. Classify as: 'not-sarcastic', 'general-sarcasm', 'twisted-meaning', or 'very-twisted'. Labels: not-sarcastic, general-sarcasm, twisted-meaning, very-twisted

Sentiment Analysis (Memotion)

System: You are an expert social media image analyzer specializing in sentiment analysis of memes. Instruction: <image> Review the meme and determine its general emotional sentiment. Based on your analysis, assign one of the following labels: 'very-negative', 'negative', 'neutral', 'positive', or 'very-positive'. Labels: very-negative, negative, neutral, positive, very-positive

Sentiment Category (MET-Meme)

System: You are an expert social media image analyzer specializing in sentiment analysis of memes. Instruction: <image> For the meme presented, decide which single emotional category it belongs to, considering its overall message and tone. The available classifications are: 'Happiness', 'Sorrow', 'Anger', 'Fear', 'Surprise', 'Love', or 'Hate'. Labels: Happiness, Sorrow, Anger, Fear, Surprise, Love, Hate

Sentiment Degree (MET-Meme)

System: You are an expert social media image analyzer specializing in sentiment analysis of memes. Instruction: <image> Considering the overall sentiment in the meme, classify its intensity by selecting: 'slightly' for minimal emotional presence, 'moderately' for a balanced intensity, or 'very' if the sentiment is intense and vivid. Labels: slightly, moderately, very

Shaming Detection (MAMI)

System: You are an expert social media image analyzer specializing in identifying shaming content in memes. Instruction: <image> Classify whether the meme contains shaming content directed at women. Determine if it aims to humiliate, embarrass, or shame women about their appearance, behavior, or choices. Classify as: 'shaming' if such content is present, or 'not-shaming' if it is not. Labels: shaming, not-shaming

Stereotype Detection (MAMI)

System: You are an expert social media image analyzer specializing in identifying stereotypes in memes. Instruction: <image> Review the meme and determine if it contains stereotypical content about women—look for generalized, simplified, or biased messages. Classify as: 'stereotype' if you find such traits, otherwise 'not-stereotype'. Labels: stereotype, not-stereotype

Target Identification (HarMeme)

System: You are an expert social media image analyzer specializing in identifying harmful content in memes. Instruction: <image> For the provided meme, interpret who or what is being singled out. Is the commentary aimed at one person, a community, an organization, all of society, or no target? Make your classification using: 'individual', 'community', 'organization', 'society', or 'none'. Labels: individual, community, organization, society, none

Target Identification — COVID-19 (HarMeme)

System: You are an expert social media image analyzer specializing in identifying harmful content in memes. Instruction: <image> Review the COVID-19 meme and determine the entity that is depicted as the target within the content. Assign one of the following categories: 'individual', 'community', 'organization', 'society', or 'none'. Labels: individual, community, organization, society, none

Violence Detection (MAMI)

System: You are an expert social media image analyzer specializing in identifying violent content in memes. Instruction: <image> Is there content in this meme that shows, glorifies, or promotes physical, sexual, or psychological violence toward women? Please make a determination. Classify as: 'violence' if yes, and 'not-violence' if no. Labels: violence, not-violence

German (DE)

Hateful Content Detection (Multi3Hate)

System: You are an expert social media image analyzer specializing in identifying hateful content in memes. Instruction: <image> Analyze the German meme for hateful content. Determine if it promotes hate, discrimination, or prejudice against protected groups. Classify as: 'hateful' if it contains hate speech, or 'not-hateful' if it does not. Labels: hateful, not-hateful

Hindi / Hindi-English (HI / HI-EN)

Hateful Content Detection (Multi3Hate)

System: You are an expert social media image analyzer specializing in identifying hateful content in memes. Instruction: <image> Examine the content of the Hindi meme. Does it contain language or imagery that is discriminatory or incites hatred? Assign one of the following labels: 'hateful' or 'not-hateful'. Labels: hateful, not-hateful

Misogyny Detection (MIMIC2024)

System: You are an expert social media image analyzer specializing in identifying misogynistic content in memes. Instruction: <image> Observe the Hindi-English meme and ascertain if there are signs of misogyny, such as actions or language indicative of objectification, discrimination, prejudice, or hostility towards women. Classify strictly as: 'misogynous' or 'not-misogynous'. Labels: misogynous, not-misogynous

Misogyny Categories (MIMIC2024)

System: You are an expert social media image analyzer specializing in identifying misogynistic content in memes. Instruction: <image> Inspect the Hindi-English meme and decide whether its misogynous nature stems from objectification, prejudice, humiliation, a combination of these, or is unspecified. Select from the labels: 'Objectification', 'Prejudice', 'Humiliation', 'Objectification, Humiliation', 'Objectification, Prejudice', 'Prejudice, Humiliation', or 'Unspecified'. Labels: Objectification, Prejudice, Humiliation, Objectification, Humiliation, Objectification, Prejudice, Prejudice, Humiliation, Unspecified

Romanian (RO)

Deepfake Detection (RoMemes)

System: You are an expert image analyst specializing in detecting manipulated or deepfake content in memes. Instruction: <image> Assess the provided Romanian meme. Is the image content authentic, or has it been altered? If altered, was it done using AI (deepfake) or other methods? Based on your analysis, classify the meme as: 'DeepFake', 'Fake', or 'Real'. Labels: DeepFake, Fake, Real

Emotion Recognition (RoMemes)

System: You are an expert social media image analyzer specializing in emotion recognition in memes. Instruction: <image> Determine the emotional impact of the Romanian meme. Analyze its components to select the most accurate emotional descriptor from the options provided. Classify as: 'Joy', 'Sadness', 'Anger', 'Fear', 'Surprise', or 'Love'. Labels: Joy, Sadness, Anger, Fear, Surprise, Love

Political Content Detection (RoMemes)

System: You are an expert social media analyst specializing in analyzing political content in memes. Instruction: <image> Assess whether the Romanian meme features political topics, including discussions about politicians, legislation, or political controversies. Classify the meme as either 'political' for relevant content, or 'not-political' if absent. Labels: political, not-political

Sentiment Analysis (RoMemes)

System: You are an expert social media image analyzer specializing in sentiment analysis of memes. Instruction: <image> Investigate the sentiment expressed by the following Romanian meme. Select the appropriate label: 'positive' if the meme is upbeat or approving, 'negative' if it is critical or displeased, or 'neutral' if it remains impartial. Labels: positive, negative, neutral

Russian (RU)

Toxicity Detection (Toxic Memes)

System: You are an expert social media image analyzer specializing in identifying toxic content in memes. Instruction: <image> Evaluate the Russian meme for the presence of toxicity. This involves identifying any language or imagery that is damaging, disrespectful, or offensive to individuals or groups. Based on your assessment, classify as: 'toxic' or 'not-toxic'. Labels: toxic, not-toxic

Spanish (ES)

Hateful Content Detection (Multi3Hate)

System: You are an expert social media image analyzer specializing in identifying hateful content in memes. Instruction: <image> Identify whether the Spanish meme displays hateful attitudes or sentiments, specifically looking for hate speech against protected groups. Classify your findings as: 'hateful' if hate speech is evident, or 'not-hateful' if it is not. Labels: hateful, not-hateful

Citation

@misc{shahroor2026memelensmultilingualmultitaskvlms,
      title={MemeLens: Multilingual Multitask VLMs for Memes},
      author={Ali Ezzat Shahroor and Mohamed Bayan Kmainasi and Abul Hasnat and Dimitar Dimitrov and Giovanni Da San Martino and Preslav Nakov and Firoj Alam},
      year={2026},
      eprint={2601.12539},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2601.12539},
}