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.- Anthology ID:
- 2026.semeval-1.156
- Volume:
- Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
- Month:
- July
- Year:
- 2026
- Address:
- San Diego, California, USA
- Editors:
- Ekaterina Kochmar, Debanjan Ghosh, Kai North, Mamoru Komachi
- Venues:
- SemEval | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1144–1146
- Language:
- URL:
- https://preview.aclanthology.org/acl-awards/2026.semeval-1.156/
- DOI:
- 10.18653/v1/2026.semeval-1.156
- Cite (ACL):
- Warda Yousaf. 2026. SLPGFJWUWarda at SemEval-2026 Task 1: A Multimodal Vision-Language Approach for Humor Generation Using Fine-Tuned BLIP. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 1144–1146, San Diego, California, USA. Association for Computational Linguistics.
- Cite (Informal):
- SLPGFJWUWarda at SemEval-2026 Task 1: A Multimodal Vision-Language Approach for Humor Generation Using Fine-Tuned BLIP (Yousaf, SemEval 2026)
- PDF:
- https://preview.aclanthology.org/acl-awards/2026.semeval-1.156.pdf