Research map / Architectures and efficiency / Spiking networks
Spik4lite: Refactoring Neuromorphic Sparsity for Efficient Spiking Neural Networks on Commodity Edge Devices
Yongzhi She, Qihua Zhou, Yuhao Wang, Yaodong Huang, Laizhong Cui, Jingcai Guo
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Spik4lite compression | Spikingformer-4-384 · CIFAR10 | parameters (M): 9.32 -> 2.86 | Improved |
| add Spik4lite compression | Spikingformer-4-384 · CIFAR10 | Top-1 accuracy (%): 95.07 -> 94.43 | Hurt |
| add Spik4lite compression | Spikingformer-4-384 · CIFAR10 | energy per batch (J): 5.42 -> 3.42 | Improved |
| add Spik4lite compression | Spikformer-4-384 · CIFAR10 | peak memory (MiB): 2614 -> 1613 | Improved |
| add Spik4lite compression | SD-Transformer-2-256 · DVS-128 Gesture | energy per batch (J): 9.24 -> 2.85 | Improved |
| add Spik4lite compression | SD-Transformer-2-256 · DVS-128 Gesture | latency (s): 1.65 -> 0.46 | Improved |
| add Spik4lite compression | Spikformer-4-384 · CIFAR100 | Top-1 accuracy (%): 78.0 -> 74.19 | Hurt |
| add Spik4lite compression | Spikformer-2-256 · DVS-CIFAR10 | Top-1 accuracy (%): 79.9 -> 76.4 | Hurt |
| add Spik4lite compression | Spikingformer · CIFAR100 (Jetson Orin Nano) | inference duration: approximately 130 s -> roughly 57 s | Improved |
| increase penalty to prune 32% of channels (ablation) | Spikingformer + Spik4lite · CIFAR10 | Top-1 accuracy (%): 95.07 -> 95.07 | No clear effect |
| increase penalty to prune 55% of channels (ablation) | Spikingformer + Spik4lite · CIFAR10 | Top-1 accuracy (%): 95.07 -> 94.4 | Hurt |
| increase penalty to prune 90% of channels (ablation) | Spikingformer + Spik4lite · CIFAR10 | Top-1 accuracy (%): 95.07 -> 83.98 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 2 on most shared results.
- Spikingformer-4-384 — Spikingformer: A Key Foundation Model for Spiking Neural Networks (AAAI 2026) · better on 2 of 6 shared results
- Spikformer-4-384 — Spikformer: When Spiking Neural Network Meets Transformer (ICLR 2023) · better on 2 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips (ICLR 2024 · similarity 0.92)
- Sorbet: A Neuromorphic Hardware-Compatible Transformer-Based Spiking Language Model (ICML 2025 · similarity 0.89)
- Towards Efficient Spiking Transformer: a Token Sparsification Framework for Training and Inference Acceleration (ICML 2024 · similarity 0.88)
- Multiplication-Free Parallelizable Spiking Neurons with Efficient Spatio-Temporal Dynamics (NeurIPS 2025 · similarity 0.88)
- S$^2$NN: Sub-bit Spiking Neural Networks (NeurIPS 2025 · similarity 0.88)
- Spiking Token Mixer: An event-driven friendly Former structure for spiking neural networks (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
