Identity Increases Stability in Neural Cellular Automata

• URL: http://arxiv.org/abs/2508.06389v2
• Date: Mon, 03 Nov 2025 16:04:41 GMT
• Title: Identity Increases Stability in Neural Cellular Automata
• Abstract summary: We present a method for improving the stability of NCA-grown organisms by introducing an 'identity' layer with simple constraints during training.<n>Results show that NCAs grown in close proximity are more stable compared with the original NCA model.<n>This work lays the foundation for further study of the interaction between NCA-grown organisms, paving the way for studying social interaction at a cellular level in artificial organisms.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Neural Cellular Automata (NCAs) offer a way to study the growth of two-dimensional artificial organisms from a single seed cell. From the outset, NCA-grown organisms have had issues with stability, their natural boundary often breaking down and exhibiting tumour-like growth or failing to maintain the expected shape. In this paper, we present a method for improving the stability of NCA-grown organisms by introducing an 'identity' layer with simple constraints during training. Results show that NCAs grown in close proximity are more stable compared with the original NCA model. Moreover, only a single identity value is required to achieve this increase in stability. We observe emergent movement from the stable organisms, with increasing prevalence for models with multiple identity values. This work lays the foundation for further study of the interaction between NCA-grown organisms, paving the way for studying social interaction at a cellular level in artificial organisms. Code/Videos available at: https://github.com/jstovold/ALIFE2025

Related papers

• Evolving Many Worlds: Towards Open-Ended Discovery in Petri Dish NCA via Population-Based Training [46.01525213637453]
  We introduce PBT-NCA, a meta-evolutionary algorithm that evolves a population of Petri Dish Neural Cellular Automata.<n>By actively penalizing monocultures and dead states, PBT-NCA sustains a state of effective complexity that is neither globally ordered nor globally random.
  arXiv  Detail & Related papers  (2026-04-13T09:56:22Z)
• Conditional Morphogenesis: Emergent Generation of Structural Digits via Neural Cellular Automata [0.0]
  We propose a novel Conditional Neural Cellular Automata architecture capable of growing distinct topological structures from a single generic seed.<n>By injecting a one-hot condition into the cellular perception field, a single set of local rules can learn to break symmetry and self-assemble into ten distinct geometric attractors.
  arXiv  Detail & Related papers  (2025-12-09T08:36:54Z)
• Neural cellular automata: applications to biology and beyond classical AI [1.9116784879310027]
  Neural Cellular Automata (NCA) represent a powerful framework for modeling biological self-organization.<n>NCA can simulate processes across molecular, cellular, tissue, and system-level scales.<n>Their governing self-regulatory behavior is constraint to fully localized interactions, yet their collective behavior scales into coordinated system-level outcomes.
  arXiv  Detail & Related papers  (2025-09-14T06:55:29Z)
• Mixtures of Neural Cellular Automata: A Stochastic Framework for Growth Modelling and Self-Organization [0.0]
  Neural Cellular Automata (NCAs) are a promising new approach to model self-organizing processes.<n>We propose the Mixture of Neural Cellular Automata (MNCA), a novel framework incorporating the idea of mixture models into the NCA paradigm.<n>We evaluate the effectiveness of MNCAs in three key domains: (1) synthetic simulations of tissue growth and differentiation, (2) image morphogenesis robustness, and (3) microscopy image segmentation.
  arXiv  Detail & Related papers  (2025-06-25T14:33:35Z)
• Continual Learning in Vision-Language Models via Aligned Model Merging [84.47520899851557]
  We present a new perspective based on model merging to maintain stability while still retaining plasticity.<n>To maximize the effectiveness of the merging process, we propose a simple mechanism that promotes learning aligned weights with previous ones.
  arXiv  Detail & Related papers  (2025-05-30T20:52:21Z)
• BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning [60.80381372245902]
  We find emergent behaviors in biological vision models via large-scale contrastive vision-language training.<n>We train BioCLIP 2 on TreeOfLife-200M to distinguish different species.<n>We identify emergent properties in the learned embedding space of BioCLIP 2.
  arXiv  Detail & Related papers  (2025-05-29T17:48:20Z)
• Structural Cellular Hash Chemistry [0.24475591916185496]
  Hash Chemistry is a minimalistic artificial chemistry model of open-ended evolution.<n>It has been extended to non-spatial and cellular versions.<n>We propose an improved version called Structural Cellular Hash Chemistry.
  arXiv  Detail & Related papers  (2024-12-17T10:51:01Z)
• Incorporating Neuro-Inspired Adaptability for Continual Learning in Artificial Intelligence [59.11038175596807]
  Continual learning aims to empower artificial intelligence with strong adaptability to the real world. Existing advances mainly focus on preserving memory stability to overcome catastrophic forgetting. We propose a generic approach that appropriately attenuates old memories in parameter distributions to improve learning plasticity.
  arXiv  Detail & Related papers  (2023-08-29T02:43:58Z)
• Growing Steerable Neural Cellular Automata [63.91346650159648]
  In the original implementation of Neural Cellular Automata, cells are incapable of adjusting their own orientation. We make each cell responsible for its own orientation by allowing it to "turn" as determined by an adjustable internal state. We show that we can train Steerable NCA in similar but simpler ways than their Isotropic variant by: (1) breaking symmetries using only two seeds, or (2) introducing a rotation-invariant training objective.
  arXiv  Detail & Related papers  (2023-02-19T09:45:46Z)
• The scaling of goals via homeostasis: an evolutionary simulation, experiment and analysis [0.0]
  We propose that evolution pivoted the collective intelligence of cells during morphogenesis into behavioral intelligence by scaling up the goal states at the center of homeostatic processes. We found that these emergent morphogenetic agents exhibit a number of predicted features, including the use of stress propagation dynamics to achieve its target morphology. We propose that this system is a first step toward a quantitative understanding of how evolution scales minimal goal-directed behavior (homeostatic loops) into higher-level problem-solving agents in morphogenetic and other spaces.
  arXiv  Detail & Related papers  (2022-11-15T21:48:44Z)
• Growing Isotropic Neural Cellular Automata [63.91346650159648]
  We argue that the original Growing NCA model has an important limitation: anisotropy of the learned update rule. We demonstrate that cell systems can be trained to grow accurate asymmetrical patterns through either of two methods.
  arXiv  Detail & Related papers  (2022-05-03T11:34:22Z)
• Variational Neural Cellular Automata [7.863826008567604]
  In nature, the process of cellular growth and differentiation has lead to an amazing diversity of organisms. We propose a generative model, the Variational Cellular Automata (VNCA), which is loosely inspired by the biological processes of cellular growth and differentiation.
  arXiv  Detail & Related papers  (2022-01-28T11:41:53Z)
• Towards self-organized control: Using neural cellular automata to robustly control a cart-pole agent [62.997667081978825]
  We use neural cellular automata to control a cart-pole agent. We trained the model using deep-Q learning, where the states of the output cells were used as the Q-value estimates to be optimized.
  arXiv  Detail & Related papers  (2021-06-29T10:49:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.