mlsanityData to 14 Oct 2026

The Iconicity of the Generated Image

arXiv 2509.16473 ↗First posted 19 Sep 2025cs.CY cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

How humans interpret and produce images is influenced by the images we have been exposed to. Similarly, visual generative AI models are exposed to many training images and learn to generate new images based on this. Given the importance of iconic images in human visual communication, as they are widely seen, reproduced, and used as inspiration, we may expect that they may similarly have a proportionally large influence within the generative AI process. In this work we explore this question through a three-part analysis, involving data attribution, semantic similarity analysis, and a user-study. Our findings indicate that iconic images do not have an obvious influence on the generative process, and that for many icons it is challenging to reproduce an image which resembles it closely. This highlights an important difference in how humans and visual generative AI models draw on and learn from prior visual communication.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 21 of its 42 references that are in the map. First posted on arXiv 19 Sep 2025.

Builds on

21 of 42 references.

References · 21

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  4. 2025Qwen2.5-VL Technical Reportcited by 5,587
  5. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  6. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  7. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,555
  8. 2016Generative Adversarial Text to Image Synthesiscited by 735
  9. 2021Multimodal datasets: misogyny, pornography, and malignant stereotypescited by 327
  10. 2023Text-to-image Diffusion Models in Generative AI: A Surveycited by 265
  11. 2022Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scalecited by 262
  12. 2023Stable Bias: Analyzing Societal Representations in Diffusion Modelscited by 226
9 more
  1. 2023Uncurated Image-Text Datasets: Shedding Light on Demographic Biascited by 52
  2. 2023Evaluating Data Attribution for Text-to-Image Modelscited by 45
  3. 2023Stable Diffusion Exposed: Gender Bias from Prompt to Imagecited by 25
  4. 2024Data Attribution for Text-to-Image Models by Unlearning Synthesized Imagescited by 22
  5. 2024Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Modelscited by 22
  6. 2025Agonistic Image Generation: Unsettling the Hegemony of Intentioncited by 4
  7. 2024A Framework for Critical Evaluation of Text-to-Image Models: Integrating Art Historical Analysis, Artistic Exploration, and Critical Prompt Engineeringcited by 3
  8. 2025Exploring Language Patterns of Prompts in Text-to-Image Generation and Their Impact on Visual Diversitycited by 3
  9. 2025The erasure of intensive livestock farming in text-to-image generative AIcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025The Persistence of Cultural Memory: Investigating Multimodal Iconicity in Diffusion Modelscited by 0
  2. 2026MMArt: A Multi-Perspective Multimodal Dataset for Visual Art Understandingcited by 0