@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://preview.aclanthology.org/ingest-acl-workshops/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."
}