{"ID":2863283,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.24266","arxiv_id":"2509.24266","title":"S$^2$NN: Sub-bit Spiking Neural Networks","abstract":"Spiking Neural Networks (SNNs) offer an energy-efficient paradigm for machine intelligence, but their continued scaling poses challenges for resource-limited deployment. Despite recent advances in binary SNNs, the storage and computational demands remain substantial for large-scale networks. To further explore the compression and acceleration potential of SNNs, we propose Sub-bit Spiking Neural Networks (S$^2$NNs) that represent weights with less than one bit. Specifically, we first establish an S$^2$NN baseline by leveraging the clustering patterns of kernels in well-trained binary SNNs. This baseline is highly efficient but suffers from \\textit{outlier-induced codeword selection bias} during training. To mitigate this issue, we propose an \\textit{outlier-aware sub-bit weight quantization} (OS-Quant) method, which optimizes codeword selection by identifying and adaptively scaling outliers. Furthermore, we propose a \\textit{membrane potential-based feature distillation} (MPFD) method, improving the performance of highly compressed S$^2$NN via more precise guidance from a teacher model. Extensive results on vision tasks reveal that S$^2$NN outperforms existing quantized SNNs in both performance and efficiency, making it promising for edge computing applications.","short_abstract":"Spiking Neural Networks (SNNs) offer an energy-efficient paradigm for machine intelligence, but their continued scaling poses challenges for resource-limited deployment. Despite recent advances in binary SNNs, the storage and computational demands remain substantial for large-scale networks. To further explore the comp...","url_abs":"https://arxiv.org/abs/2509.24266","url_pdf":"https://arxiv.org/pdf/2509.24266v2","authors":"[\"Wenjie Wei\",\"Malu Zhang\",\"Jieyuan Zhang\",\"Ammar Belatreche\",\"Shuai Wang\",\"Yimeng Shan\",\"Hanwen Liu\",\"Honglin Cao\",\"Guoqing Wang\",\"Yang Yang\",\"Haizhou Li\"]","published":"2025-09-29T04:17:44Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}