AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

When ‘Yes’ Meets ‘But’: Can AI Comprehend Contradictory Humor in Comics?

Tuo Liang, Zhe Hu, Jing Li, Hao Zhang, Yiren Lu, Yunlai Zhou, Yiran Qiao, Disheng Liu, Jierui Peng, Jing Ma, Yu Yin

TPAMI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Chain-of-thought multimodal reasoning · 8 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
scale up model size within a familyQwen2-VL / LLaVA-OneVision · YesBut-V2 Title matchingaccuracy: 74.72 -> 81.25 (Qwen2-VL 7B to 72B)Improved
use human oracle literal descriptions instead of VLM-generated ones for LLM reasoningLLMs · YesBut-V2 deep reasoningaccuracyImproved
use descriptions from stronger VLMs (GPT-4o, Qwen2-VL-72B) instead of LLaVA-Next-13BLLMs · YesBut-V2 deep reasoningaccuracyImproved
add two-stage decomposition with model-generated description (ablation)VLMs · YesBut-V2 Title matchingaccuracyHurt
add two-stage decomposition with model-generated description (ablation)LLaVA-OneVision-72B · YesBut-V2 Title matching (single image)accuracy: 77.10 -> 58.56Hurt
add two-stage decomposition with model-generated description (ablation)Qwen2-VL-72B · YesBut-V2 Underlying Symbolism (single image)accuracy: 79.98 -> 76.66Hurt
add decomposition on LLaVA-OneVision-0.5B (ablation)LLaVA-OneVision-0.5B · YesBut-V2 Title matching (single image)accuracy: 38.53 -> 46.44Improved
replace composite image by split multi-image panels (ablation)VLMs · YesBut-V2 deep reasoningaccuracy: LLaVA-OneVision-7B symbolism 67.64 -> 65.45Hurt
finetune language component on 20,000 synthetic text-only comic descriptions (ablation)LLaVA-Next-7B · YesBut-V2 Underlying Symbolismaccuracy: +8.56 percentage pointsImproved
finetune language component on synthetic text-only data (ablation)LLaVA-Next-13B · YesBut-V2 Underlying Symbolismaccuracy: +4.89 percentage pointsImproved
add annotated social knowledge to prompt (ablation)VLMs · YesBut-V2 deep reasoningaccuracyImproved
add translated embedded text (ablation)GPT-4o · YesBut-V2 Title matchingaccuracy: 77.42 -> 88.73Improved

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