# S2M-Former: Spiking Symmetric Mixing Branchformer for Brain Auditory Attention Detection

arXiv: https://arxiv.org/abs/2508.05164 · HTML: https://mlsanity.com/paper/2508.05164/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 53 references that are in the map.
- First posted on arXiv 7 Aug 2025.

## Builds on (most cited first, 23 of 23)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks](https://mlsanity.com/paper/2007.05785/) (2020)
- [Deep Residual Learning in Spiking Neural Networks](https://mlsanity.com/paper/2102.04159/) (2021)
- [Spikformer: When Spiking Neural Network Meets Transformer](https://mlsanity.com/paper/2209.15425/) (2022)
- [SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence](https://mlsanity.com/paper/2310.16620/) (2023)
- [Spike-driven Transformer](https://mlsanity.com/paper/2307.01694/) (2023)
- [Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion](https://mlsanity.com/paper/2403.07721/) (2024)
- [Advancing Spiking Neural Networks towards Deep Residual Learning](https://mlsanity.com/paper/2112.08954/) (2021)
- [SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion](https://mlsanity.com/paper/2404.14197/) (2024)
- [QKFormer: Hierarchical Spiking Transformer using Q-K Attention](https://mlsanity.com/paper/2403.16552/) (2024)
- [Towards Voice Reconstruction from EEG during Imagined Speech](https://mlsanity.com/paper/2301.07173/) (2023)
- [EEG-based Auditory Attention Decoding: Towards Neuro-Steered Hearing Devices](https://mlsanity.com/paper/2008.04569/) (2020)
- [Relating EEG to continuous speech using deep neural networks: a review](https://mlsanity.com/paper/2302.01736/) (2023)
- [NeuroBOLT: Resting-state EEG-to-fMRI Synthesis with Multi-dimensional Feature Mapping](https://mlsanity.com/paper/2410.05341/) (2024)
- [DARNet: Dual Attention Refinement Network with Spatiotemporal Construction for Auditory Attention Detection](https://mlsanity.com/paper/2410.11181/) (2024)
- [SpGesture: Source-Free Domain-adaptive sEMG-based Gesture Recognition with Jaccard Attentive Spiking Neural Network](https://mlsanity.com/paper/2405.14398/) (2024)
- [EEG-informed attended speaker extraction from recorded speech mixtures with application in neuro-steered hearing prostheses](https://mlsanity.com/paper/1602.05702/) (2016)
- [CSLP-AE: A Contrastive Split-Latent Permutation Autoencoder Framework for Zero-Shot Electroencephalography Signal Conversion](https://mlsanity.com/paper/2311.07788/) (2023)
- [Spiking Neural Networks for Temporal Processing: Status Quo and Future Prospects](https://mlsanity.com/paper/2502.09449/) (2025)
- [Low-latency auditory spatial attention detection based on spectro-spatial features from EEG](https://mlsanity.com/paper/2103.03621/) (2021)
- [Auditory Attention Decoding with Task-Related Multi-View Contrastive Learning](https://mlsanity.com/paper/2308.04244/) (2023)
- [Linear stimulus reconstruction works on the KU Leuven audiovisual, gaze-controlled auditory attention decoding dataset](https://mlsanity.com/paper/2412.01401/) (2024)

## Built on by (most cited first, 1 of 1)

- [UIESNN: A Scale-Aware Spiking Network for Underwater Image Enhancement](https://mlsanity.com/paper/2605.08376/) (2026)

## Abstract (arXiv)

Auditory attention detection (AAD) aims to decode listeners' focus in complex auditory environments from electroencephalography (EEG) recordings, which is crucial for developing neuro-steered hearing devices. Despite recent advancements, EEG-based AAD remains hindered by the absence of synergistic frameworks that can fully leverage complementary EEG features under energy-efficiency constraints. We propose S2M-Former, a novel spiking symmetric mixing framework to address this limitation through two key innovations: i) Presenting a spike-driven symmetric architecture composed of parallel spatial and frequency branches with mirrored modular design, leveraging biologically plausible token-channel mixers to enhance complementary learning across branches; ii) Introducing lightweight 1D token sequences to replace conventional 3D operations, reducing parameters by 14.7×. The brain-inspired spiking architecture further reduces power consumption, achieving a 5.8× energy reduction compared to recent ANN methods, while also surpassing existing SNN baselines in terms of parameter efficiency and performance. Comprehensive experiments on three AAD benchmarks (KUL, DTU and AV-GC-AAD) across three settings (within-trial, cross-trial and cross-subject) demonstrate that S2M-Former achieves comparable state-of-the-art (SOTA) decoding accuracy, making it a promising low-power, high-performance solution for AAD tasks. Code is available at https://github.com/JackieWang9811/S2M-Former.