# Heuristically Adaptive Diffusion-Model Evolutionary Strategy

arXiv: https://arxiv.org/abs/2411.13420 · HTML: https://mlsanity.com/paper/2411.13420/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 26 of its 114 references that are in the map.
- First posted on arXiv 20 Nov 2024.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 26 of 26)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [Diffusion for World Modeling: Visual Details Matter in Atari](https://mlsanity.com/paper/2405.12399/) (2024)
- [Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions](https://mlsanity.com/paper/1912.02875/) (2019)
- [Training Agents using Upside-Down Reinforcement Learning](https://mlsanity.com/paper/1912.02877/) (2019)
- [Learning to Learn with Generative Models of Neural Network Checkpoints](https://mlsanity.com/paper/2209.12892/) (2022)
- [The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning](https://mlsanity.com/paper/2109.02869/) (2021)
- [Neuroevolution of Self-Interpretable Agents](https://mlsanity.com/paper/2003.08165/) (2020)
- [In search of dispersed memories: Generative diffusion models are associative memory networks](https://mlsanity.com/paper/2309.17290/) (2023)
- [Technological Approach to Mind Everywhere (TAME): an experimentally-grounded framework for understanding diverse bodies and minds](https://mlsanity.com/paper/2201.10346/) (2021)
- [Growing Isotropic Neural Cellular Automata](https://mlsanity.com/paper/2205.01681/) (2022)
- [Towards a Theory of Evolution as Multilevel Learning](https://mlsanity.com/paper/2110.14602/) (2021)
- [HyperNCA: Growing Developmental Networks with Neural Cellular Automata](https://mlsanity.com/paper/2204.11674/) (2022)
- [Towards Self-Assembling Artificial Neural Networks through Neural Developmental Programs](https://mlsanity.com/paper/2307.08197/) (2023)
- [Diffusion Models are Evolutionary Algorithms](https://mlsanity.com/paper/2410.02543/) (2024)
- [EmoDM: A Diffusion Model for Evolutionary Multi-objective Optimization](https://mlsanity.com/paper/2401.15931/) (2024)
- [Neural Network Quine](https://mlsanity.com/paper/1803.05859/) (2018)
- [Diffusion Models for Generative Artificial Intelligence: An Introduction for Applied Mathematicians](https://mlsanity.com/paper/2312.14977/) (2023)
- [Unexpected Benefits of Self-Modeling in Neural Systems](https://mlsanity.com/paper/2407.10188/) (2024)

## Built on by (most cited first, 6 of 6)

- [Evolutionary Optimization of Physics-Informed Neural Networks: Evo-PINN Frontiers and Opportunities](https://mlsanity.com/paper/2501.06572/) (2025)
- [Neural cellular automata: applications to biology and beyond classical AI](https://mlsanity.com/paper/2509.11131/) (2025)
- [Evolution Meets Diffusion: Efficient Neural Architecture Generation](https://mlsanity.com/paper/2504.17827/) (2025)
- [Remapping and navigation of an embedding space via error minimization: a fundamental organizational principle of cognition in natural and artificial systems](https://mlsanity.com/paper/2601.14096/) (2026)
- [Evolutionary Computation as Natural Generative AI](https://mlsanity.com/paper/2510.08590/) (2025)
- [On Growth and Form, and Function: Reusable Regulatory Handles Control Phenotypic Variation](https://mlsanity.com/paper/2609.29755/) (2026)

## Abstract (arXiv)

Diffusion Models represent a significant advancement in generative modeling, employing a dual-phase process that first degrades domain-specific information via Gaussian noise and restores it through a trainable model. This framework enables pure noise-to-data generation and modular reconstruction of, images or videos. Concurrently, evolutionary algorithms employ optimization methods inspired by biological principles to refine sets of numerical parameters encoding potential solutions to rugged objective functions. Our research reveals a fundamental connection between diffusion models and evolutionary algorithms through their shared underlying generative mechanisms: both methods generate high-quality samples via iterative refinement on random initial distributions. By employing deep learning-based diffusion models as generative models across diverse evolutionary tasks and iteratively refining diffusion models with heuristically acquired databases, we can iteratively sample potentially better-adapted offspring parameters, integrating them into successive generations of the diffusion model. This approach achieves efficient convergence toward high-fitness parameters while maintaining explorative diversity. Diffusion models introduce enhanced memory capabilities into evolutionary algorithms, retaining historical information across generations and leveraging subtle data correlations to generate refined samples. We elevate evolutionary algorithms from procedures with shallow heuristics to frameworks with deep memory. By deploying classifier-free guidance for conditional sampling at the parameter level, we achieve precise control over evolutionary search dynamics to further specific genotypical, phenotypical, or population-wide traits. Our framework marks a major heuristic and algorithmic transition, offering increased flexibility, precision, and control in evolutionary optimization processes.