# Active Divergence with Generative Deep Learning -- A Survey and Taxonomy

arXiv: https://arxiv.org/abs/2107.05599 · HTML: https://mlsanity.com/paper/2107.05599/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 85 references that are in the map.
- First posted on arXiv 12 Jul 2021.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?](https://mlsanity.com/paper/1904.03189/) (2019)
- [A Neural Algorithm of Artistic Style](https://mlsanity.com/paper/1508.06576/) (2015)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [Multi-Agent Cooperation and the Emergence of (Natural) Language](https://mlsanity.com/paper/1612.07182/) (2016)
- [Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature](https://mlsanity.com/paper/1505.00855/) (2015)
- [DDSP: Differentiable Digital Signal Processing](https://mlsanity.com/paper/2001.04643/) (2020)
- [Rewriting a Deep Generative Model](https://mlsanity.com/paper/2007.15646/) (2020)
- [Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions](https://mlsanity.com/paper/2003.08536/) (2020)
- [CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms](https://mlsanity.com/paper/1706.07068/) (2017)
- [Resolution Dependent GAN Interpolation for Controllable Image Synthesis Between Domains](https://mlsanity.com/paper/2010.05334/) (2020)
- [Toward Quantifying Ambiguities in Artistic Images](https://mlsanity.com/paper/2008.09688/) (2020)
- [Amplifying The Uncanny](https://mlsanity.com/paper/2002.06890/) (2020)
- [Combinets: Creativity via Recombination of Neural Networks](https://mlsanity.com/paper/1802.03605/) (2018)
- [Spurious samples in deep generative models: bug or feature?](https://mlsanity.com/paper/1810.01876/) (2018)
- [Transforming the output of GANs by fine-tuning them with features from different datasets](https://mlsanity.com/paper/1910.02411/) (2019)
- [Generating Novel Glyph without Human Data by Learning to Communicate](https://mlsanity.com/paper/2010.04402/) (2020)
- [Automating Generative Deep Learning for Artistic Purposes: Challenges and Opportunities](https://mlsanity.com/paper/2107.01858/) (2021)
- [Digits that are not: Generating new types through deep neural nets](https://mlsanity.com/paper/1606.04345/) (2016)
- [Real-time interactive sequence generation and control with Recurrent Neural Network ensembles](https://mlsanity.com/paper/1612.04687/) (2016)
- [Searching for an (un)stable equilibrium: experiments in training generative models without data](https://mlsanity.com/paper/1910.02409/) (2019)

## Built on by (most cited first, 12 of 12)

- [Art and the science of generative AI: A deeper dive](https://mlsanity.com/paper/2306.04141/) (2023)
- [Evaluating Creative Short Story Generation in Humans and Large Language Models](https://mlsanity.com/paper/2411.02316/) (2024)
- [Creativity in AI: Progresses and Challenges](https://mlsanity.com/paper/2410.17218/) (2024)
- [Towards Mode Balancing of Generative Models via Diversity Weights](https://mlsanity.com/paper/2304.11961/) (2023)
- [Challenges in creative generative models for music: a divergence maximization perspective](https://mlsanity.com/paper/2211.08856/) (2022)
- [Seizing the Means of Production: Exploring the Landscape of Crafting, Adapting and Navigating Generative AI Models in the Visual Arts](https://mlsanity.com/paper/2404.17688/) (2024)
- [The Homogenization Problem in LLMs: Towards Meaningful Diversity in AI Safety](https://mlsanity.com/paper/2601.06116/) (2026)
- [Explainability-in-Action: Enabling Expressive Manipulation and Tacit Understanding by Bending Diffusion Models in ComfyUI](https://mlsanity.com/paper/2508.07183/) (2025)
- [Creative divergent synthesis with generative models](https://mlsanity.com/paper/2211.08861/) (2022)
- [Why Open Small AI Models Matter for Interactive Art](https://mlsanity.com/paper/2511.09788/) (2025)
- [Unboxing Diffusion Models for the Arts: Interactive Model Bending and Practice-Based Explainability](https://mlsanity.com/paper/2607.22428/) (2026)
- [Architecture and Affordances of PLAUD: Performative Latents and Unsupervised DDSP](https://mlsanity.com/paper/2608.13724/) (2026)

## Abstract (arXiv)

Generative deep learning systems offer powerful tools for artefact generation, given their ability to model distributions of data and generate high-fidelity results. In the context of computational creativity, however, a major shortcoming is that they are unable to explicitly diverge from the training data in creative ways and are limited to fitting the target data distribution. To address these limitations, there have been a growing number of approaches for optimising, hacking and rewriting these models in order to actively diverge from the training data. We present a taxonomy and comprehensive survey of the state of the art of active divergence techniques, highlighting the potential for computational creativity researchers to advance these methods and use deep generative models in truly creative systems.