cs.AIOct 30, 2026

Neurons Are All You Need

Authors: Joseph B. Alzagatiti, Alain C. Glanzman, Perry A. Demsko, Pablo I. Salanova, David L. Glanzman

Organizations: Department of Integrative Biology and Physiology, UCLA College, University of California, Los Angeles, Los Angeles, CA, USA. · Department of Neurobiology, David Geffen School of Medicine at UCLA, Los Angeles, CA, USA. · Brain Research Institute, David Geffen School of Medicine at UCLA, Los Angeles, CA, USA.

Abstract

For decades, artificial neural networks have operated under the assumption that durable, learned capability resides exclusively in adaptive synaptic parameters, primarily due to the established neurobiology of synaptic connectivity. This design forces models to remain stateless during deployment, incurring well-known limitations such as catastrophic forgetting and expensive retraining. However, recent neurobiological research by Glanzman and colleagues, and others, shows that memories can be transferred between individual organisms in a synaptically independent manner. Inspired by this research, we sought to demonstrate memory transfer of persistent memory between AI model instances, leveraging a neurocentric version of memory. In this paper, we propose NURESA (Neural Unit with Retentive Self-Adaptive Architecture), a novel neural layer that eschews sole reliance on synaptic weight updating by introducing persistent intra-unit memory as a first-class, computational primitive. By structurally separating computation from persistent memory, NURESA enables autonomous memory accumulation and consolidation into transferable stores of memory registers. Experiments across MLP, GPT-2, and modern frontier models like Qwen2.5 demonstrate qualitatively new capability: zero-shot transfer of learned capability into a naive model instance without retraining or access to the original training data; this transfer is enabled by a sparse set of parameters in NURESA's memory register that the model selects on its own based on which neurons were most active. The memory transfer capability of NURESA also protects against domain loss when transformer models undergo learning via fine-tuning. Finally, the memory transfer process completes in approximately one minute even for transformer models with millions to billions of parameters, producing a transfer file orders of magnitude smaller than the original model.

Explore similar work

CardsList
  1. Not Just After One: Sleep-Inspired Replay Prevents Catastrophic Forgetting After Sequential Tasks

    Jun 7, 2026Anthony Bazhenov, Jean Erik Delanois, Giri P. KrishnanReplay-Based Continual LearningMemory Consolidation

  2. Mixture of Chapters: Scaling Learnt Memory in Transformers

    Mar 22, 2026Tasmay Pankaj Tibrewal, Pritish Saha, Ankit Meda +2Memory-Augmented Language ModelsPersistent Memory for Language Models