2026-07-10 04:00 UTCOriginal source2 min readUpdated: 2026-07-10 08:18 UTC

Architecture Generalization with MetaNCA

MetaNCA learns local update rules to self-organize neural network weights, enabling weight generation for diverse architectures without backpropagation and generalizing to unseen architectures.

SourcearXiv Machine LearningAuthor: Meet Barot, Daniel Berenberg, Sina Khajehabdollahi

-->

[Submitted on 8 Jul 2026]

Title:Architecture Generalization with MetaNCA

View a PDF of the paper titled Architecture Generalization with MetaNCA, by Meet Barot and 2 other authors

View PDF HTML (experimental)

Abstract:Self-organization is an emergent property of life, driven by the collective behavior of individual components acting on local information. Biological neurons, through local interactions transmitted through synapses, are able to learn efficiently and can adapt their connections over an organism's lifespan. Motivated by these desirable properties of adaptability and local interaction, neural cellular automata (NCA) models have been successful at learning morphogenesis solely through local update rules, demonstrating stability over many updates and robustness to perturbations. In this work, we introduce Meta Neural Cellular Automata (MetaNCA), a framework that learns local rules which self-organize the weights of artificial neural networks. A learned rule network iteratively updates the weights of a task network using only local interactions on the computation graph. We propose a novel Weight Transformer architecture for the local rule network, which uses linear attention to aggregate signals from neighboring weights and hidden states. Once trained, the rule network generates task networks of diverse architectures without backpropagation. We show that MetaNCA generates weights for feedforward MLPs, CNNs, and ResNets on MNIST and CIFAR-100, scaling to networks of 2 million parameters. We further show that MetaNCA generalizes to architectures not seen during meta-training, and that architectural diversity in the training phase strengthens this generalization.

Comments: 9 pages, 6 figures. To appear in the proceedings of the Artificial Life Conference (ALIFE 2026)

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

Cite as: arXiv:2607.07743 [cs.LG]

(or arXiv:2607.07743v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2607.07743

arXiv-issued DOI via DataCite

Submission history

From: Meet Barot PhD [view email] [v1] Wed, 8 Jul 2026 08:31:57 UTC (1,043 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Architecture Generalization with MetaNCA, by Meet Barot and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-07

Change to browse by:

cs cs.AI

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)