# Modality-Dependent Memory Mechanisms in Cross-Modal Neuromorphic Computing

arXiv: https://arxiv.org/abs/2512.18575 · HTML: https://mlsanity.com/paper/2512.18575/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 19 references that are in the map.
- First posted on arXiv 21 Dec 2025.

## Builds on (most cited first, 7 of 7)

- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Hopfield Networks is All You Need](https://mlsanity.com/paper/2008.02217/) (2020)
- [Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades](https://mlsanity.com/paper/1507.07629/) (2015)
- [Long short-term memory and learning-to-learn in networks of spiking neurons](https://mlsanity.com/paper/1803.09574/) (2018)
- [The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks](https://mlsanity.com/paper/1910.07407/) (2019)
- [A survey on learning models of spiking neural membrane systems and spiking neural networks](https://mlsanity.com/paper/2403.18609/) (2024)

## Abstract (arXiv)

Memory-augmented spiking neural networks (SNNs) promise energy-efficient neuromorphic computing, yet their generalization across sensory modalities remains unexplored. We present the first comprehensive cross-modal ablation study of memory mechanisms in SNNs, evaluating Hopfield networks, Hierarchical Gated Recurrent Networks (HGRNs), and supervised contrastive learning (SCL) across visual (N-MNIST) and auditory (SHD) neuromorphic datasets. Our systematic evaluation of five architectures reveals striking modality-dependent performance patterns: Hopfield networks achieve 97.68% accuracy on visual tasks but only 76.15% on auditory tasks (21.53 point gap), revealing severe modality-specific specialization, while SCL demonstrates more balanced cross-modal performance (96.72% visual, 82.16% audio, 14.56 point gap). These findings establish that memory mechanisms exhibit task-specific benefits rather than universal applicability. Joint multi-modal training with HGRN achieves 94.41% visual and 79.37% audio accuracy (88.78% average), matching parallel HGRN performance through unified deployment. Quantitative engram analysis confirms weak cross-modal alignment (0.038 similarity), validating our parallel architecture design. Our work provides the first empirical evidence for modality-specific memory optimization in neuromorphic systems, achieving 603x energy efficiency over traditional neural networks.