EMNLP 2026 paper teaches multimodal LLMs to get cartoons via incongruity-resolution supervision
aykuterdemml · x · 2026-10-23
Accepted to EMNLP 2026 main conference, "Learning to Think Like a Cartoon Captionist" targets why multimodal LLMs fail at New Yorker cartoons — not vision, but reasoning from image to punchline — using Incongruity–Resolution supervision for multimodal humor understanding.
More from Multimodal
- Same prompt, 2.4x cost gap: AI UGC videos at $0.75 vs $1.78 — miilesus · 2026-10-23
- Open-source Phosphene renders Hailuo H3 2.3x faster locally on Mac — cocktailpeanut · 2026-10-23
- Canva launches Craft, its first in-house frontier image generation model for design — EXM7777 · 2026-10-23
- MiniMax-H3 hailed as favorite open release of the year, runs fully local — AdinaYakup · 2026-10-23
- Michal Malewicz experiments with depth maps in his creative workflow — michalmalewicz · 2026-10-23
- One-Shot Tunable Style Transfer on Flux3 Via Reference Latent + Node — Winter_unmuted · 2026-10-23