Spiking Neural Networks (SNNs) enable event-driven computation with sparse activations, but building multimodal Transformers on SNNs is hindered by unstable training in deep spiking stacks and the mismatch between dense softmax attention and spike-based communication. We propose SMM Transformer, an SNN-based multimodal Transformer framework that combines (i)PLMP, a Parallel LIF with Multistage Learnable Parameters neuron and a tailored P-STBP algorithm for stable deep SNN training, (ii) SMSA, an attention-inspired spike-driven token-mixing module that replaces dense pairwise softmax attention with channel-wise spike co-activation and self-compensation, and (iii)SMoE, a spiking mixture-of-experts module for modality-aware fusion. Across visual and multimodal benchmarks, SMM Transformer achieves competitive accuracy compared to ANN baselines. Under a standard MAC/AC arithmetic model, SMSA reduces the estimated operator-level compute energy of the attention module by up to 97%, while whole-model profiling shows more moderate but consistent efficiency gains.
This work introduces a Temporal Feedback Coding (TFC) scheme that leverages feedback at the encoding stage to diversify spike patterns and designs a Global-Local Dynamic LIF (GLD-LIF) neuron that enhances cross-step dependency modeling by integrating local aggregation and global initialization.
A Rate-Coded Cross-Attention (RCCA) module is proposed, which converts population-coded spike-trains into attention queries, allowing long-range dependency modeling within sub-milliwatt (sub-mW) power budgets.
M. Alsuwaiket· Computers, Materials & C...· 0 citations
A Spiking Neural Network (SNN) is a kind of brain-inspired and event-driven network, which is becoming a promising energy-efficient alternative to Artificial Neural Networks (ANNs). In recent years, SNN methods have been successfully applied in the fields of electromagnetic signal processing and image signal processing, particularly in application scenarios that require low energy consumption. However, the performance of SNNs by direct training is far from satisfactory. In this paper, we study a novel learning method named SAD-SNN (Spatial-Activation Distillation for Spiking Neural Networks), which utilizes the ANN model to guide the SNN model learning. Unlike prior works that rely on element-wise feature alignment approaches, SAD-SNN aligns spatial-activation maps at different resolutions of the teacher and student networks. Specifically, we introduce a direct alignment approach, which defines a spatial-activation loss and normalizes the representation vectors of ANN and SNN, to alleviate the unexpected precision loss. This enables the knowledge of teacher ANNs to be effectively transferred to train student SNNs. On three image classification datasets, our proposed SAD-SNN outperforms other SNN training methods no matter whether homogeneous or heterogeneous teacher ANNs are used. Furthermore, we apply SAD-SNN to the electromagnetic signal detection task, demonstrating strong generalization ability and superior performance. In conclusion, the experimental results on various tasks and SNN architectures demonstrate that our method is a general and effective solution that significantly improves the learning of student SNNs with only two time steps.
Chongxiao Qu, Qian Zhang, Chenxiao Dou et al.· Italian National Conference...· 0 citations
Keyword spotting (KWS) systems based on Spike Neural Networks (SNNs) offer a promising solution for always-on voice interfaces. However, achieving a favorable trade-off between computational footprint and recognition accuracy remains challenging for resource-constrained edge devices. This paper proposes a lightweight convolutional spiking neural network (CSNN) for KWS that combines a streamable Mel-to-Spike encoder, a convolutional spiking feature extractor, and a delay-aware classification module that uses learnable synaptic delays. The proposed encoder adopts streaming frame-by-frame encoding to convert speech features into sparse spike trains, while the delay-aware classifier jointly optimizes synaptic weights and temporal delays for enhanced spatiotemporal evidence aggregation. Experiments on the Google Speech Commands V1 and V2 (GSC-V1 and GSC-V2), Heidelberg Digits (HD), and Chinese Mandarin Keyword (CMK) datasets show mean test accuracies of 94.37%, 92.87%, 99.10%, and 95.60%, respectively. The proposed method uses only 64.05 K and 68.14 K learnable parameters for the 12-class and 20-class classification, while maintaining strong robustness to additive noise. These results indicate that the proposed CSNN achieves a favorable algorithm-level balance among accuracy, compactness, and noise robustness for KWS.
Xiaohuan Li, Yi Liu, Libo Zheng· Italian National Conference...· 0 citations
The Intrinsically Stable SNN (IS-SNN) architecture is proposed, which removes activation-normalization layers by enforcing signal homeostasis through topology-aware weight standardization and modified residual connections and removes the runtime statistics tracking and multiplications introduced by activation normalization, restoring an accumulation-oriented inference datapath.
R. Ma, Xiaoyang Zhang, J. Bai et al.· arXiv.org· 0 citations
Spiking neural networks (SNNs) offer an energy-efficient alternative to conventional deep neural networks by exploiting sparse event-driven computation, but their training remains challenging because the non-differentiable spike function requires surrogate gradients whose fixed shape may be suboptimal across layers and training stages. In this work, we introduce SAGE, an uncertainty-modulated surrogate-gradient mechanism for Transformer-based SNNs. SAGE estimates block-level uncertainty from normalized self-attention entropy and uses this signal to adapt the surrogate-gradient slope during training while leaving the inference model unchanged. By modulating only the training-time surrogate parameter, the proposed method preserves the original architecture and deployment cost while improving optimization flexibility. Experiments on CIFAR-10/100 demonstrate that SAGE achieves improved accuracy over fixed-surrogate baselines, with results up to 1-2\% consistent gains across multiple simulation time steps. These results highlight the potential of attention-derived uncertainty as a lightweight training signal for adaptive surrogate-gradient learning in transformer-based SNNs.