# Nepotistically Trained Generative-AI Models Collapse

arXiv: https://arxiv.org/abs/2311.12202 · HTML: https://mlsanity.com/paper/2311.12202/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 31 references that are in the map.
- First posted on arXiv 20 Nov 2023.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [The Curse of Recursion: Training on Generated Data Makes Models Forget](https://mlsanity.com/paper/2305.17493/) (2023)
- [SinGAN: Learning a Generative Model from a Single Natural Image](https://mlsanity.com/paper/1905.01164/) (2019)
- [Detecting and Simulating Artifacts in GAN Fake Images](https://mlsanity.com/paper/1907.06515/) (2019)
- [Poisoning Web-Scale Training Datasets is Practical](https://mlsanity.com/paper/2302.10149/) (2023)
- [WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning](https://mlsanity.com/paper/2103.01913/) (2021)
- [On the detection of synthetic images generated by diffusion models](https://mlsanity.com/paper/2211.00680/) (2022)
- [What makes fake images detectable? Understanding properties that generalize](https://mlsanity.com/paper/2008.10588/) (2020)
- [Self-Consuming Generative Models Go MAD](https://mlsanity.com/paper/2307.01850/) (2023)
- [Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data](https://mlsanity.com/paper/2007.08457/) (2020)
- [Poisoning and Backdooring Contrastive Learning](https://mlsanity.com/paper/2106.09667/) (2021)
- [Are GAN generated images easy to detect? A critical analysis of the state-of-the-art](https://mlsanity.com/paper/2104.02617/) (2021)
- [Will Large-scale Generative Models Corrupt Future Datasets?](https://mlsanity.com/paper/2211.08095/) (2022)
- [Towards Understanding the Interplay of Generative Artificial Intelligence and the Internet](https://mlsanity.com/paper/2306.06130/) (2023)
- [Combining Generative Artificial Intelligence (AI) and the Internet: Heading towards Evolution or Degradation?](https://mlsanity.com/paper/2303.01255/) (2023)

## Built on by (most cited first, 27 of 27)

- [Collapse or Thrive? Perils and Promises of Synthetic Data in a Self-Generating World](https://mlsanity.com/paper/2410.16713/) (2024)
- [LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models](https://mlsanity.com/paper/2410.09732/) (2024)
- [AI and the Problem of Knowledge Collapse](https://mlsanity.com/paper/2404.03502/) (2024)
- [Position: Model Collapse Does Not Mean What You Think](https://mlsanity.com/paper/2503.03150/) (2025)
- [A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective](https://mlsanity.com/paper/2509.16499/) (2025)
- [Superficial Self-Improved Reasoners Benefit from Model Merging](https://mlsanity.com/paper/2503.02103/) (2025)
- [When Models Don't Collapse: On the Consistency of Iterative MLE](https://mlsanity.com/paper/2505.19046/) (2025)
- [Model Collapse in the Self-Consuming Chain of Diffusion Finetuning: A Novel Perspective from Quantitative Trait Modeling](https://mlsanity.com/paper/2407.17493/) (2024)
- [Preventing Model Collapse Under Overparametrization: Optimal Mixing Ratios for Interpolation Learning and Ridge Regression](https://mlsanity.com/paper/2509.22341/) (2025)
- [LLM Web Dynamics: Tracing Model Collapse in a Network of LLMs](https://mlsanity.com/paper/2506.15690/) (2025)
- [Guidance Watermarking for Diffusion Models](https://mlsanity.com/paper/2509.22126/) (2025)
- [Language Generation with Replay: A Learning-Theoretic View of Model Collapse](https://mlsanity.com/paper/2603.11784/) (2026)
- [Convergence and Stability Analysis of Self-Consuming Generative Models with Heterogeneous Human Curation](https://mlsanity.com/paper/2511.09002/) (2025)
- [Learning by Surprise: Adaptive Mitigation of Model Collapse in Large Language Models](https://mlsanity.com/paper/2410.12341/) (2024)
- [Convergence Dynamics and Stabilization Strategies of Co-Evolving Generative Models](https://mlsanity.com/paper/2503.08117/) (2025)
- [Recursive Training Loops in LLMs: How training data properties modulate distribution shift in generated data?](https://mlsanity.com/paper/2504.03814/) (2025)
- [Emergent Specialization: Rare Token Neurons in Language Models](https://mlsanity.com/paper/2505.12822/) (2025)
- [When Does Model Collapse Occur in Structured Interactive Learning?](https://mlsanity.com/paper/2605.20151/) (2026)
- [Distributed Specialization: Rare-Token Neurons in Large Language Models](https://mlsanity.com/paper/2509.21163/) (2025)
- [From Collapse to Improvement: Statistical Perspectives on the Evolutionary Dynamics of Iterative Training on Contaminated Sources](https://mlsanity.com/paper/2602.10531/) (2026)
- [Drift and selection in LLM text ecosystems](https://mlsanity.com/paper/2604.08554/) (2026)
- [Position: the Stochastic Parrot in the Coal Mine. Model Collapse is a Threat to Low-Resource Communities](https://mlsanity.com/paper/2605.04127/) (2026)
- [FissionVAE: Federated Non-IID Image Generation with Latent Space and Decoder Decomposition](https://mlsanity.com/paper/2408.17090/) (2024)
- [A Markovian View of Iterative-Feedback Loops in Image Generative Models: Neural Resonance and Model Collapse](https://mlsanity.com/paper/2602.19033/) (2026)
- [Optimal Self-Distillation for Rectified Flow via Linear Probing](https://mlsanity.com/paper/2607.14947/) (2026)
- [SynthSentry: Detecting Synthetic Data Contamination in Language Model Training Data](https://mlsanity.com/paper/2609.12353/) (2026)
- [Feature Selective Model Collapse in Diffusion Models: Total Replacement versus Fixed-Budget Training](https://mlsanity.com/paper/2610.01318/) (2026)

## Abstract (arXiv)

Trained on massive amounts of human-generated content, AI-generated image synthesis is capable of reproducing semantically coherent images that match the visual appearance of its training data. We show that when retrained on even small amounts of their own creation, these generative-AI models produce highly distorted images. We also show that this distortion extends beyond the text prompts used in retraining, and that once affected, the models struggle to fully heal even after retraining on only real images.