AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

HumorDB: Can AI understand graphical humor?

Vedaant V Jain, Gabriel Kreiman, Felipe dos Santos Alves Feitosa

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fine-tune LLaVA instead of zero-shotLLaVA · HumorDB Range task (testAllSet)RMSE: 2.95 -> 1.70Improved
add human keywords prefix when fine-tuning (ablation)LLaVA · HumorDB Range task (testAllSet)RMSE: 1.70 -> 1.68Improved
add human keywords prefix when fine-tuning (ablation)BLIP · HumorDB Range task (testAllSet)RMSE: 1.94 -> 1.92No clear effect
add human keywords prefix when fine-tuning (ablation)LLaVA · HumorDB Binary task (Photoshopped images)accuracy (%): 76 -> 83Improved
add human keywords prefix when fine-tuning (ablation)LLaVA · HumorDB Binary task (Photos images)accuracy (%): 72 -> 79Improved
fine-tune LLaVA instead of zero-shotLLaVA · HumorDB Binary task (Cartoons images)accuracy (%): 52 -> 65Improved
add pretraining to vision modelsvision-only models · HumorDB Binary taskaccuracy (%)Improved
restrict evaluation to paired images onlyvision models · HumorDB Binary taskaccuracy (%)Hurt
evaluate only on original images, excluding modified imagesGPT-4o · HumorDB Binary taskaccuracy (%): 10% improvementImproved
sketch images versus other image typesall models · HumorDB Binary task (Sketches images)accuracy (%): 47 - 54Hurt
replace ViT-Huge by ViTG-14 (larger model)vision-only fine-tuned · HumorDB Range task (testAllSet)RMSE: 1.88 -> 1.76Improved
use large VLM Gemini-Flash zero-shot instead of GPT-4o zero-shotzero-shot VLM · HumorDB Range task (testAllSet)RMSE: 2.61 -> 2.06Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy