Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges
:::info Stub — Full Engineering Breakdown Coming This paper was featured on Hugging Face Daily Papers on 2026-07-21 with 2 upvotes. A full breakdown with production viability rating, implementation notes, and honest limitations is being written. Subscribe to AI Letters → :::
| Authors | Tuo Liang et al. |
| Year | 2026 |
| HF Upvotes | 2 |
| arXiv | 2607.19011 |
| Download | |
| HF Page | View on Hugging Face |
Abstract
Multimodal humor in memes, cartoons, and comics remains difficult for AI systems because intended meaning depends on non-literal mechanisms, shared cultural knowledge, and communicative intent rather than literal scene description. This survey focuses on visual humor understanding in single-image and multi-panel artifacts, while treating humor generation as an emerging downstream frontier. We position the literature against prior humor, sarcasm, and general MLLM surveys and organize it using a capability-centric hierarchy spanning recognition, interpretation and reasoning, and generation. Under this lens, we synthesize benchmark design, evaluation protocols, and modeling paradigms, tracing the field's shift from task-specific fusion models to large-model approaches based on multimodal alignment, evidence-grounded reasoning, and controlled generation. We conclude by highlighting the main barriers to progress: shortcut-prone evaluation, limited cultural and narrative coverage, weak evidence grounding, and unresolved safety and ownership concerns.
Engineering Breakdown
The Problem
Multimodal humor in memes, cartoons, and comics remains difficult for AI systems because intended meaning depends on non-literal mechanisms, shared cultural knowledge, and communicative intent rather than literal scene description.
The Approach
This survey focuses on visual humor understanding in single-image and multi-panel artifacts, while treating humor generation as an emerging downstream frontier.
Key Results
We conclude by highlighting the main barriers to progress: shortcut-prone evaluation, limited cultural and narrative coverage, weak evidence grounding, and unresolved safety and ownership concerns.
Research Areas
This paper contributes to the following areas of AI/ML engineering:
- Machine learning
- Deep learning
- Neural networks
- Model optimization
- AI systems
- Computational
:::tip Subscribe Get weekly breakdowns of papers like this in AI Letters - the newsletter for engineers building production AI systems. :::