# Visual Puns from Idioms: An Iterative LLM-T2IM-MLLM Framework

arXiv: https://arxiv.org/abs/2511.22943 · HTML: https://mlsanity.com/paper/2511.22943/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 28 Nov 2025.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 22 of 22)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025)
- [PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation](https://mlsanity.com/paper/2403.04692/) (2024)
- [Text-to-image Diffusion Models in Generative AI: A Survey](https://mlsanity.com/paper/2303.07909/) (2023)
- [Rich Human Feedback for Text-to-Image Generation](https://mlsanity.com/paper/2312.10240/) (2023)
- [Controllable Generation with Text-to-Image Diffusion Models: A Survey](https://mlsanity.com/paper/2403.04279/) (2024)
- [A Survey on Benchmarks of Multimodal Large Language Models](https://mlsanity.com/paper/2408.08632/) (2024)
- [PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement](https://mlsanity.com/paper/2403.04014/) (2024)
- [ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models](https://mlsanity.com/paper/2403.01807/) (2024)
- [RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model](https://mlsanity.com/paper/2309.00810/) (2023)
- [Capabilities of GPT-5 on Multimodal Medical Reasoning](https://mlsanity.com/paper/2508.08224/) (2025)
- [I Spy a Metaphor: Large Language Models and Diffusion Models Co-Create Visual Metaphors](https://mlsanity.com/paper/2305.14724/) (2023)
- [Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark](https://mlsanity.com/paper/2411.15488/) (2024)
- [Multimodal Pragmatic Jailbreak on Text-to-image Models](https://mlsanity.com/paper/2409.19149/) (2024)
- [Creating a Lens of Chinese Culture: A Multimodal Dataset for Chinese Pun Rebus Art Understanding](https://mlsanity.com/paper/2406.10318/) (2024)
- [Self-Rewarding Large Vision-Language Models for Optimizing Prompts in Text-to-Image Generation](https://mlsanity.com/paper/2505.16763/) (2025)
- [Can visual language models resolve textual ambiguity with visual cues? Let visual puns tell you!](https://mlsanity.com/paper/2410.01023/) (2024)

## Abstract (arXiv)

We study idiom-based visual puns--images that align an idiom's literal and figurative meanings--and present an iterative framework that coordinates a large language model (LLM), a text-to-image model (T2IM), and a multimodal LLM (MLLM) for automatic generation and evaluation. Given an idiom, the system iteratively (i) generates detailed visual prompts, (ii) synthesizes an image, (iii) infers the idiom from the image, and (iv) refines the prompt until recognition succeeds or a step limit is reached. Using 1,000 idioms as inputs, we synthesize a corresponding dataset of visual pun images with paired prompts, enabling benchmarking of both generation and understanding. Experiments across 10 LLMs, 10 MLLMs, and one T2IM (Qwen-Image) show that MLLM choice is the primary performance driver: GPT achieves the highest accuracies, Gemini follows, and the best open-source MLLM (Gemma) is competitive with some closed models. On the LLM side, Claude attains the strongest average performance for prompt generation.