# NeuMoSync: End-to-End Neuromodulatory Control for Plasticity and Adaptability in Continual Learning

arXiv: https://arxiv.org/abs/2608.04358 · HTML: https://mlsanity.com/paper/2608.04358/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 92 references that are in the map.
- First posted on arXiv 5 Aug 2026.

## Builds on (most cited first, 20 of 20)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System](https://mlsanity.com/paper/2201.12604/) (2022)
- [Disentangling the Causes of Plasticity Loss in Neural Networks](https://mlsanity.com/paper/2402.18762/) (2024)
- [Learning to Continually Learn](https://mlsanity.com/paper/2002.09571/) (2020)
- [Bayesian Hypernetworks](https://mlsanity.com/paper/1710.04759/) (2017)
- [Maintaining Plasticity in Continual Learning via Regenerative Regularization](https://mlsanity.com/paper/2308.11958/) (2023)
- [Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks](https://mlsanity.com/paper/2406.02596/) (2024)
- [Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity](https://mlsanity.com/paper/2002.10585/) (2020)
- [Embedded Encoder-Decoder in Convolutional Networks Towards Explainable AI](https://mlsanity.com/paper/2007.06712/) (2020)
- [Neuroplastic Expansion in Deep Reinforcement Learning](https://mlsanity.com/paper/2410.07994/) (2024)
- [HyperNetworks with statistical filtering for defending adversarial examples](https://mlsanity.com/paper/1711.01791/) (2017)
- [Brain-inspired Artificial Intelligence: A Comprehensive Review](https://mlsanity.com/paper/2408.14811/) (2024)
- [ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains](https://mlsanity.com/paper/2505.14511/) (2025)
- [Preserving Plasticity in Continual Learning with Adaptive Linearity Injection](https://mlsanity.com/paper/2505.09486/) (2025)
- [Contrastive Consolidation of Top-Down Modulations Achieves Sparsely Supervised Continual Learning](https://mlsanity.com/paper/2505.14125/) (2025)

## Abstract (arXiv)

Continual learning (CL) requires models to learn tasks sequentially, yet deep neural networks often suffer from plasticity loss and poor knowledge transfer, which can impede their long-term adaptability. Drawing high-level inspiration from global neuromodulatory mechanisms in the brain, we introduce Neuromodulation and Synchronization (NeuMoSync), a novel architecture that integrates dynamic, neuron-specific modulation into deep neural networks to enhance their adaptability and plasticity. NeuMoSync extends standard neural network architectures with learnable feature vectors for each neuron that track network-wide historical context and with a module operating at a higher level of abstraction. This module synthesizes neuron-specific signals, conditioned on both current inputs and the network's evolving state, to adaptively regulate activation dynamics and synaptic plasticity. Evaluated on diverse CL benchmarks, including memorization (Random Label CIFAR-10 and Random Label MNIST), concept drift (Shuffle CIFAR-10 and Shuffle Mini-ImageNet), class-incremental learning (Class Split ImageNet and Class Split CIFAR-100), and domain-incremental learning (Permuted MNIST), NeuMoSync demonstrates strong performance in retaining plasticity and achieves improvements in both forward and backward adaptation compared with existing methods. Ablation studies validate the necessity of each component, while analysis of the learned modulatory signals reveals interpretable coordination patterns across tasks. Our work underscores the potential of integrating global coordination mechanisms into deep learning systems to advance robust, adaptive continual learning. The code is publicly available at https://github.com/RoozbehRazavi/NeuMoSync.