@inproceedings{yousaf-2026-slpgfjwuwarda,
title = "{SLPGFJWUW}arda at {S}em{E}val-2026 Task 1: A Multimodal Vision-Language Approach for Humor Generation Using Fine-Tuned {BLIP}",
author = "Yousaf, Warda",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.156/",
pages = "1144--1146",
ISBN = "979-8-89176-414-9",
abstract = "We present a BLIP-based multimodal system for image-based humor generation submitted to SemEval-2026 Task 1 (MWAHAHA), focusing on Task B1. Our approach fine-tunes a vision{--}language model on meme-style captions and handles animated GIFs via representative frame extraction to generate culturally grounded humorous captions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yousaf-2026-slpgfjwuwarda">
<titleInfo>
<title>SLPGFJWUWarda at SemEval-2026 Task 1: A Multimodal Vision-Language Approach for Humor Generation Using Fine-Tuned BLIP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Warda</namePart>
<namePart type="family">Yousaf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>We present a BLIP-based multimodal system for image-based humor generation submitted to SemEval-2026 Task 1 (MWAHAHA), focusing on Task B1. Our approach fine-tunes a vision–language model on meme-style captions and handles animated GIFs via representative frame extraction to generate culturally grounded humorous captions.</abstract>
<identifier type="citekey">yousaf-2026-slpgfjwuwarda</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.156/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1144</start>
<end>1146</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SLPGFJWUWarda at SemEval-2026 Task 1: A Multimodal Vision-Language Approach for Humor Generation Using Fine-Tuned BLIP
%A Yousaf, Warda
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F yousaf-2026-slpgfjwuwarda
%X We present a BLIP-based multimodal system for image-based humor generation submitted to SemEval-2026 Task 1 (MWAHAHA), focusing on Task B1. Our approach fine-tunes a vision–language model on meme-style captions and handles animated GIFs via representative frame extraction to generate culturally grounded humorous captions.
%U https://aclanthology.org/2026.semeval-1.156/
%P 1144-1146
Markdown (Informal)
[SLPGFJWUWarda at SemEval-2026 Task 1: A Multimodal Vision-Language Approach for Humor Generation Using Fine-Tuned BLIP](https://aclanthology.org/2026.semeval-1.156/) (Yousaf, SemEval 2026)
ACL