Firehose

21 JUL 2026 · Paper

Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges

This paper explores how to make AI systems understand and generate humor, particularly in visual formats like memes and comics, and why this is important for developing more human-like AI that can understand and create humor. Practitioners might care because humor is a key aspect of human communication and understanding.

multimodal LLMs humor understanding visual humor multimodal alignment continual learning AI safety

Browse by tag

Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges