# VisAnalog: A Diagnostic Suite for Visual Concept Transfer on Natural Images

arXiv: https://arxiv.org/abs/2605.23141 · HTML: https://mlsanity.com/paper/2605.23141/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 22 May 2026.

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

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [Show-o: One Single Transformer to Unify Multimodal Understanding and Generation](https://mlsanity.com/paper/2408.12528/) (2024)
- [A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge](https://mlsanity.com/paper/2206.01718/) (2022)
- [BLINK: Multimodal Large Language Models Can See but Not Perceive](https://mlsanity.com/paper/2404.12390/) (2024)
- [What's "up" with vision-language models? Investigating their struggle with spatial reasoning](https://mlsanity.com/paper/2310.19785/) (2023)
- [Emergent Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2212.09196/) (2022)
- [RAVEN: A Dataset for Relational and Analogical Visual rEasoNing](https://mlsanity.com/paper/1903.02741/) (2019)
- [FVQA: Fact-based Visual Question Answering](https://mlsanity.com/paper/1606.05433/) (2016)
- [The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain](https://mlsanity.com/paper/2305.07141/) (2023)
- [Comparing Humans, GPT-4, and GPT-4V On Abstraction and Reasoning Tasks](https://mlsanity.com/paper/2311.09247/) (2023)
- [In-Context Analogical Reasoning with Pre-Trained Language Models](https://mlsanity.com/paper/2305.17626/) (2023)
- [AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogies](https://mlsanity.com/paper/2402.12370/) (2024)
- [ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation](https://mlsanity.com/paper/2511.01163/) (2025)
- [BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception](https://mlsanity.com/paper/2510.09361/) (2025)
- [Can Large Reasoning Models do Analogical Reasoning under Perceptual Uncertainty?](https://mlsanity.com/paper/2503.11207/) (2025)
- [VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical Reasoning](https://mlsanity.com/paper/2503.00043/) (2025)

## Abstract (arXiv)

A useful test of visual concept learning is not just whether a model can recognize a concept in a single image, but whether it can preserve and manipulate concept-level properties under transformation and transfer them to new scenes. We introduce VisAnalog, a controlled suite for this setting on natural images. Each example instantiates A!:!B::C!:,?: images B and a hidden target image D are produced by applying the same deterministic transformation sequence to source images A and C. Given A, B, and C, a model must answer a multiple-choice question about D. The benchmark contains 617 human-validated questions spanning one- to four-step transformations such as zoom, quadrant swap, rotation, flip, and hue rotation. Across strong proprietary and open-source VLMs, end-to-end accuracy is substantially lower than oracle accuracy when D is directly shown, and degrades sharply as transformation depth increases, while human performance remains near the ceiling. A program-conditioned evaluation further separates failures of relation inference from failures of transformation application, showing that inferring the visual relation from A rightarrow B is the dominant bottleneck, with additional application errors emerging on harder multi-step cases. The dataset is publicly available at https://huggingface.co/datasets/zli99/VisAnalog.