# Dimensions of Vulnerability in Visual Working Memory: An AI-Driven Approach to Perceptual Comparison

arXiv: https://arxiv.org/abs/2507.22067 · HTML: https://mlsanity.com/paper/2507.22067/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 25 references that are in the map.
- First posted on arXiv 14 Jul 2025.

## Builds on (most cited first, 7 of 7)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Revealing interpretable object representations from human behavior](https://mlsanity.com/paper/1901.02915/) (2019)
- [VICE: Variational Interpretable Concept Embeddings](https://mlsanity.com/paper/2205.00756/) (2022)
- [CoCoG: Controllable Visual Stimuli Generation based on Human Concept Representations](https://mlsanity.com/paper/2404.16482/) (2024)
- [CoCoG-2: Controllable generation of visual stimuli for understanding human concept representation](https://mlsanity.com/paper/2407.14949/) (2024)
- [Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering and Manipulating Human Perceptual Variability](https://mlsanity.com/paper/2505.03641/) (2025)

## Abstract (arXiv)

Human memory exhibits significant vulnerability in cognitive tasks and daily life. Comparisons between visual working memory and new perceptual input (e.g., during cognitive tasks) can lead to unintended memory distortions. Previous studies have reported systematic memory distortions after perceptual comparison, but understanding how perceptual comparison affects memory distortions in real-world objects remains a challenge. Furthermore, identifying what visual features contribute to memory vulnerability presents a novel research question. Here, we propose a novel AI-driven framework that generates naturalistic visual stimuli grounded in behaviorally relevant object dimensions to elicit similarity-induced memory biases. We use two types of stimuli -- image wheels created through dimension editing and dimension wheels generated by dimension activation values -- in three visual working memory (VWM) experiments. These experiments assess memory distortions under three conditions: no perceptual comparison, perceptual comparison with image wheels, and perceptual comparison with dimension wheels. The results show that similar dimensions, like similar images, can also induce memory distortions. Specifically, visual dimensions are more prone to distortion than semantic dimensions, indicating that the object dimensions of naturalistic visual stimuli play a significant role in the vulnerability of memory.