SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.02543 · ICLR · 2025

Diffusion Models are Evolutionary Algorithms

Yanbo Zhang, Benedikt Hartl, Hananel Hazan, Michael Levin

arXiv · PDF · Open in the Atlas

Code that ran

10 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 1 violated it and 4 have no contract verdict; 3 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2410.02543.json · badge: /api/ran/2410.02543.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
Zhangyanbo/diffusion-evolution canonical (classifier label)
classifier basis: classifier_2025
9 ran · 1 no recorded run
zhangyanbo/diffusion-evolution canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
BayesianEstimator Ran
ran on a synthesized input · constructed an object; no result was computed
Zhangyanbo/diffusion-evolution/diffevo/optimizer.py
pointer only (licence: NOASSERTION) · get_code("8ba778ff16d2c4f7")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Zhangyanbo/diffusion-evolution (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

BayesianGenerator Ran
ran on a synthesized input · constructed an object; no result was computed
Zhangyanbo/diffusion-evolution/diffevo/optimizer.py
pointer only (licence: NOASSERTION) · get_code("8b585a04523c0a9d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Zhangyanbo/diffusion-evolution (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

DDIMScheduler Ran
ran on a synthesized input · constructed an object; no result was computed
Zhangyanbo/diffusion-evolution/diffevo/optimizer.py
pointer only (licence: NOASSERTION) · get_code("a61f6693c4182262")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Zhangyanbo/diffusion-evolution (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Identity Ran
ran on a synthesized input · constructed an object; no result was computed
Zhangyanbo/diffusion-evolution/diffevo/optimizer.py
pointer only (licence: NOASSERTION) · get_code("5e3a40fa59c113e0")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Zhangyanbo/diffusion-evolution (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

KDE Ran
ran; our contract draft was wrong, not the code
Zhangyanbo/diffusion-evolution/diffevo/optimizer.py
pointer only (licence: NOASSERTION) · get_code("0e279a90e8f567ef")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Zhangyanbo/diffusion-evolution (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

calculate_dim Ran
ran, violated the contract we drafted
zhangyanbo/diffusion-evolution/experiments/RL/diffRL/experiments.py
pointer only (licence: NOASSERTION) · get_code("0e088813836b4325")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, zhangyanbo/diffusion-evolution (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ddim_step Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Zhangyanbo/diffusion-evolution/diffevo/optimizer.py
pointer only (licence: NOASSERTION) · get_code("fe659543339f194c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Zhangyanbo/diffusion-evolution (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ddpm_sigma Ran
ran, honoured the contract we drafted
Zhangyanbo/diffusion-evolution/diffevo/optimizer.py
pointer only (licence: NOASSERTION) · get_code("0fa9c93146146013")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Zhangyanbo/diffusion-evolution (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

distance_matrix Ran
ran, honoured the contract we drafted
Zhangyanbo/diffusion-evolution/diffevo/optimizer.py
pointer only (licence: NOASSERTION) · get_code("809084a9f4de7e1f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Zhangyanbo/diffusion-evolution (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

project_to_1d Ran
ran; our contract draft was wrong, not the code
Zhangyanbo/diffusion-evolution/experiments/2d_models/experiment.py
pointer only (licence: NOASSERTION) · get_code("cedb8b3d8057d15d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Zhangyanbo/diffusion-evolution (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

DiffEvo Not yet run
unverified (harvested, no recorded run)
Zhangyanbo/diffusion-evolution/diffevo/optimizer.py
pointer only (licence: NOASSERTION) · get_code("007d6f984a8b1791")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Zhangyanbo/diffusion-evolution (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 11 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In a convergence of machine learning and biology, we reveal that diffusion models are evolutionary algorithms. By considering evolution as a denoising process and reversed evolution as diffusion, we mathematically demonstrate that diffusion models inherently perform evolutionary algorithms, naturally encompassing selection, mutation, and reproductive isolation. Building on this equivalence, we propose the Diffusion Evolution method: an evolutionary algorithm utilizing iterative denoising -as originally introduced in the context of diffusion models -to heuristically refine solutions in parameter spaces. Unlike traditional approaches, Diffusion Evolution efficiently identifies multiple optimal solutions and outperforms prominent mainstream evolutionary algorithms. Furthermore, leveraging advanced concepts from diffusion models, namely latent space diffusion and accelerated sampling, we introduce Latent Space Diffusion Evolution, which finds solutions for evolutionary tasks in high-dimensional complex parameter space while significantly reducing computational steps. This parallel between diffusion and evolution not only bridges two different fields but also opens new avenues for mutual enhancement, raising questions about open-ended evolution and potentially utilizing non-Gaussian or discrete diffusion models in the context of Diffusion Evolution.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.02543")
get_code_for_paper("2410.02543")
have("2410.02543")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2410.02543.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2410.02543.svg)](https://syntology.ai/paper/2410.02543)

Connect an agent — have() is free.