Skip to content
conftrace_
2026 SemEval SemEval 2026

SLPGFJWUWarda at SemEval-2026 Task 1: A Multimodal Vision-Language Approach for Humor Generation Using Fine-Tuned BLIP

Abstract

AbstractWe 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.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Computer Vision

Authors

Warda Yousaf

Topics

Computer Vision > Generation > Image Captioning Computer Vision > Core AI > Multimodal Learning Artificial Intelligence > Core AI > Vision-Language Models

Keywords

multimodal learning image captioning vision-language model humor generation frame extraction
Download PDF

More from SemEval 2026

All SemEval 2026 papers →
CSECU-DSG at SemEval-2026 Task 10: Fine-Tuning DeBERTa Transformer Model for Conspiracy Detection
CUET-823 at SemEval-2026 Task 9: LoRA-Based Instruction Fine-Tuning of LLMs vs. Transformer Models for Bengali Polarization Detection
H-RAG at SemEval-2026 Task 8: Hierarchical Parent–Child Retrieval for Multi-Turn RAG Conversations
hllwan at SemEval-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis via LLM Feature Fusion and Test-Time Adaptation
CITD@UIT at SemEval-2026 Task 4: Structured Reasoning and Metric Specialization for Narrative Similarity
YNU-HPCC at SemEval-2026 Task 5: Rating Plausibility of Word Senses in Ambiguous Stories through Narrative Understanding