#artificial intelligence
Apr 2026
Learning to Think Like a Cartoon Captionist: Incongruity-Resolution Supervision for Multimodal Humor Understanding
Grounded in incongruity-resolution theory and expert captionist practice, IRS supervises intermediate reasoning process through structured traces that make the path from visual perception to humorous interpretation explicit and learnable.
Hatice Vural, Doga Kukul, Ege Erdem Ozlu et al.
· arXiv.org · 0 citations