Research map / Architectures and efficiency / Spiking networks
GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| replace LIF neurons with GLIF in STBP-tdBN ResNet-19 | STBP-tdBN · CIFAR-100 T=6 | top-1 accuracy: 71.12 -> 77.35 | Helped |
| GLIF vs TET | ResNet-19 · CIFAR-10 T=6 | top-1 accuracy: 94.50 -> 95.03 | Helped |
| GLIF vs STBP-tdBN on ImageNet | ResNet-34 · ImageNet | top-1 accuracy: 63.72 -> 69.09 | Helped |
| GLIF on MS-ResNet-18 | MS-ResNet-18 · ImageNet | top-1 accuracy: 63.10 -> 68.11 | Helped |
| fuse dual bio-features with gating instead of single simplex LIF (best simplex 100) (ablation) | GLIF · CIFAR-100 ResNet-19 T=4 | top-1 accuracy: 77.15 -> 77.22 | Helped |
| fuse dual bio-features with gating instead of simplex LIF 000 (ablation) | GLIF · CIFAR-100 ResNet-18 T=4 | top-1 accuracy: 75.77 -> 76.39 | Helped |
| make gating factors learnable instead of static (ablation) | GLIF · CIFAR-100 ResNet-19 T=4 | top-1 accuracy: 76.89 -> 77.22 | Helped |
| use gating instead of simple addition fusion (ablation) | GLIF · CIFAR-100 ResNet-19 T=4 | top-1 accuracy: 71.26 -> 77.22 | Helped |
| channel-wise instead of layer-wise parameter sharing (ablation) | GLIF · CIFAR-100 ResNet-19 T=4 | top-1 accuracy: 75.71 -> 77.22 | Helped |
| channel-wise instead of layer-wise parameter sharing (ablation) | GLIF · CIFAR-100 ResNet-18 T=2 | top-1 accuracy: 73.40 -> 74.85 | Helped |
Closest papers by meaning
- CLIF: Complementary Leaky Integrate-and-Fire Neuron for Spiking Neural Networks (ICML 2024 · similarity 0.89)
- Neuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks (NeurIPS 2026 · similarity 0.88)
- TC-LIF: A Two-Compartment Spiking Neuron Model for Long-Term Sequential Modelling (AAAI 2024 · similarity 0.88)
- HetSyn: Versatile Timescale Integration in Spiking Neural Networks via Heterogeneous Synapses (NeurIPS 2025 · similarity 0.87)
- The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks. (ICLR 2024 · similarity 0.86)
- Balanced Resonate-and-Fire Neurons (ICML 2024 · similarity 0.86)
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.