Awesome-Spiking-Neural-Networks

Collect some spiking neural network papers & codes. (Actively keep updating)

If you own or find some overlooked SNN papers, you can add them to this document by pull request.

News

[2024.05.06] Update SNN-related papers in ICLR 2024 (17 papers), AAAI 2024 (8 papers), CVPR 2024.

[2023.12.31] Update SNN-related papers in TPAMI 2023, Frontiers in Neuroscience 2023.

[2023.11.06] Update SNN-related papers in NeurIPS 2023 (12 papers).

[2023.10.08] Update SNN-related papers in CVPR 2023 (2 papers), ICML 2023 (2), IJCAI 2023 (3), and ICCV 2023 (10).

[2023.06.25] Update SNN-related papers in ICLR 2023 (6 papers), AAAI 2023 (6 papers).

Papers

2024

Review

• Direct Training High-Performance Deep Spiking Neural Networks: A Review of Theories and Methods. [paper]

AAAI, ICLR, Frontiers in Neuroscience, CVPR

• SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networks (CVPR 2024). [paper] [code]
• SGLFormer: Spiking Global-Local-Fusion Transformer with high performance (Frontiers in Neuroscience 2024).[paper] [code]
• Towards Energy Efficient Spiking Neural Networks: An Unstructured Pruning Framework (ICLR 2024). [paper]
• Online Stabilization of Spiking Neural Networks (ICLR 2024). [paper]
• SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition (ICLR 2024). [paper]
• Spatio-Temporal Approximation: A Training-Free SNN Conversion for Transformers (ICLR 2024). [paper]
• Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNN (ICLR 2024). [paper]
• Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings (ICLR 2024). [paper] [code]
• Threaten Spiking Neural Networks through Combining Rate and Temporal Information (ICLR 2024). [paper] [code]
• TAB: Temporal Accumulated Batch Normalization in Spiking Neural Networks (ICLR 2024). [paper]
• Certified Adversarial Robustness for Rate Encoded Spiking Neural Networks (ICLR 2024). [paper]
• Bayesian Bi-clustering of Neural Spiking Activity with Latent Structures (ICLR 2024). [paper]
• Adaptive deep spiking neural network with global-local learning via balanced excitatory and inhibitory mechanism (ICLR 2024). [paper]
• Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks (ICLR 2024). [paper] [code]
• A Progressive Training Framework for Spiking Neural Networks with Learnable Multi-hierarchical Model (ICLR 2024). [paper] [code]
• LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units (ICLR 2024). [paper] [code]
• Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips (ICLR 2024). [paper] [code]
• Can we get the best of both Binary Neural Networks and Spiking Neural Networks for Efficient Computer Vision? (ICLR 2024). [paper] [code]
• A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks (ICLR 2024). [paper] [code]
• Ternary Spike: Learning Ternary Spikes for Spiking Neural Networks (AAAI 2024). [paper] [code]
• Memory-Efficient Reversible Spiking Neural Networks (AAAI 2024). [paper] [code]
• Gated Attention Coding for Training High-performance and Efficient Spiking Neural Networks (AAAI 2024). [paper]
• SpikingBERT: Distilling BERT to Train Spiking Language Models Using Implicit Differentiation (AAAI 2024). [paper] [code]
• TC-LIF: A Two-Compartment Spiking Neuron Model for Long-Term Sequential Modelling (AAAI 2024). [paper] [code]
• Shrinking Your TimeStep: Towards Low-Latency Neuromorphic Object Recognition with Spiking Neural Networks (AAAI 2024). [paper]
• Dynamic Spiking Graph Neural Networks (AAAI 2024). [paper]
• An Efficient Knowledge Transfer Strategy for Spiking Neural Networks from Static to Event Domain (AAAI 2024). [paper] [code]

Arxiv

• QKFormer: Hierarchical Spiking Transformer using Q-K Attention. [paper] [code]
• Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN Ticket. [paper] [code]
• SpikeNAS: A Fast Memory-Aware Neural Architecture Search Framework for Spiking Neural Network Systems. [paper]
• Astrocyte-Enabled Advancements in Spiking Neural Networks for Large Language Modeling. [paper]

2023

Review

• Direct Learning-Based Deep Spiking Neural Networks: A Review (Frontiers in Neuroscience 2023). [paper]

AAAI, ICLR, CVPR, ICML, IJCAI, ICCV, NeurIPS, TPAMI, Science Advances

• SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence (Science Advances 2023). [paper] [code]
• Spike-driven Transformer [paper] [code]
• Parallel Spiking Neurons with High Efficiency and Long-term Dependencies Learning Ability (NeurIPS 2023). [paper] [code]
• Temporal Conditioning Spiking Latent Variable Models of the Neural Response to Natural Visual Scenes (NeurIPS 2023). [paper]
• SEENN: Towards Temporal Spiking Early Exit Neural Networks (NeurIPS 2023). [paper]
• EICIL: Joint Excitatory Inhibitory Cycle Iteration Learning for Deep Spiking Neural Networks (NeurIPS 2023). [paper]
• Addressing the speed-accuracy simulation trade-off for adaptive spiking neurons (NeurIPS 2023). [paper]
• Enhancing Adaptive History Reserving by Spiking Convolutional Block Attention Module in Recurrent Neural Networks (NeurIPS 2023). [paper]
• Trial matching: capturing variability with data-constrained spiking neural networks (NeurIPS 2023). [paper]
• Evolving Connectivity for Recurrent Spiking Neural Networks (NeurIPS 2023). [paper]
• SparseProp: Efficient Event-Based Simulation and Training of Sparse Recurrent Spiking Neural Networks (NeurIPS 2023). [paper]
• Spiking PointNet: Spiking Neural Networks for Point Clouds (NeurIPS 2023). [paper] [code]
• Exploring Loss Functions for Time-based Training Strategy in Spiking Neural Networks (NeurIPS 2023). [paper]
• Membrane Potential Batch Normalization for Spiking Neural Networks (ICCV 2023). [paper]
• Unleashing the Potential of Spiking Neural Networks with Dynamic Confidence (ICCV 2023). [paper]
• RMP-Loss: Regularizing Membrane Potential Distribution for Spiking Neural Networks (ICCV 2023). [paper]
• Inherent Redundancy in Spiking Neural Networks (ICCV 2023). [paper]
• Temporal-Coded Spiking Neural Networks with Dynamic Firing Threshold: Learning with Event-Driven Backpropagation (ICCV 2023). [paper]
• Efficient Converted Spiking Neural Network for 3D and 2D Classification (ICCV 2023). [paper]
• Deep Directly-Trained Spiking Neural Networks for Object Detection (ICCV 2023). [paper]
• Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks (ICCV 2023). [paper]
• SSF: Accelerating Training of Spiking Neural Networks with Stabilized Spiking Flow (ICCV 2023). [paper]
• Masked Spiking Transformer (ICCV 2023). [paper]
• Spatial-Temporal Self-Attention for Asynchronous Spiking Neural Networks (IJCAI 2023). [paper]
• Learnable Surrogate Gradient for Direct Training Spiking Neural Networks (IJCAI 2023). [paper]
• Enhancing Efficient Continual Learning with Dynamic Structure Development of Spiking Neural Networks (IJCAI 2023). [paper]
• Adaptive Smoothing Gradient Learning for Spiking Neural Networks (ICML 2023). [paper]
• Surrogate Module Learning: Reduce the Gradient Error Accumulation in Training Spiking Neural Networks (ICML 2023). [paper] [code]
• Rate Gradient Approximation Attack Threats Deep Spiking Neural Networks (CVPR 2023). [paper]
• Constructing Deep Spiking Neural Networks from Artificial Neural Networks with Knowledge Distillation (CVPR 2023). [paper]
• Attention Spiking Neural Networks (TPAMI 2023) .[paper] [code]
• Heterogeneous neuronal and synaptic dynamics for spike-efficient unsupervised learning: Theory and design principles (ICLR 2023).[paper]
• Spiking Convolutional Neural Networks for Text Classification (ICLR 2023) .[paper]
• Bridging the Gap between ANNs and SNNs by Calibrating Offset Spikes (ICLR 2023).[paper] [code]
• Spikformer: When Spiking Neural Network Meets Transformer (ICLR 2023) .[paper] [code]
• A Unified Framework of Soft Threshold Pruning (ICLR 2023). [paper] [code]
• Bridging the Gap between ANNs and SNNs by Calibrating Offset Spikes (ICLR 2023). [paper] [code]
• Reducing ANN-SNN Conversion Error through Residual Membrane Potential (AAAI 2023). [paper] [code]
• Deep Spiking Neural Networks with High Representation Similarity Model Visual Pathways of Macaque and Mouse (AAAI 2023). [paper]
• ESL-SNNs: An Evolutionary Structure Learning Strategy for Spiking Neural Networks (AAAI 2023). [paper]
• Exploring Temporal Information Dynamics in Spiking Neural Networks (AAAI 2023). [paper] [code]
• Scaling Up Dynamic Graph Representation Learning via Spiking Neural Networks(AAAI 2023). [paper] [code]
• Complex Dynamic Neurons Improved Spiking Transformer Network for Efficient Automatic Speech Recognition(AAAI 2023). [paper]

Arxiv

• Spikingformer: Spike-driven Residual Learning for Transformer-based Spiking Neural Network [paper] [code]
• Enhancing the Performance of Transformer-based Spiking Neural Networks by Improved Downsampling with Precise Gradient Backpropagation [paper] [code]
• Training Full Spike Neural Networks via Auxiliary Accumulation Pathway [paper]
• MSS-DepthNet: Depth Prediction with Multi-Step Spiking Neural Network [paper]
• SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks [paper] [code]
• Auto-Spikformer: Spikformer Architecture Search [paper]
• Advancing Spiking Neural Networks Towards Deep Residual Learning [paper]

2022

NeurIPS, CVPR, ICLR, AAAI, ICML, Nature Communications

• Event-based Video Reconstruction via Potential-assisted Spiking Neural Network [paper] [code]
• Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks [paper] [code]
• Optimized Potential Initialization for Low-latency Spiking Neural Networks (AAAI 2022). [paper]
• AutoSNN: Towards Energy-Efficient Spiking Neural Networks [paper]
• Neural Architecture Search for Spiking Neural Networks [paper] [code]
• Neuromorphic Data Augmentation for Training Spiking Neural Networks [paper] [code]
• State Transition of Dendritic Spines Improves Learning of Sparse Spiking Neural Networks [paper] [code]
• Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation [paper] [code]
• Exploring Lottery Ticket Hypothesis in Spiking Neural Networks [paper] [code]
• Spiking Graph Convolutional Networks [paper] [code]
• A calibratable sensory neuron based on epitaxial VO2 for spike-based neuromorphic multisensory system [paper] [code]
• Online Training Through Time for Spiking Neural Networks (NeurIPS 2022). [paper] [code]
• Training Spiking Neural Networks with Event-driven Backpropagation [paper] [code]
• GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networks [paper] [code]
• Temporal Effective Batch Normalization in Spiking Neural Networks [paper]
• Training Spiking Neural Networks with Local Tandem Learning (NeurIPS 2022). [paper]
• IM-Loss: Information Maximization Loss for Spiking Neural Networks (NeurIPS 2022). [paper]
• Temporal Effective Batch Normalization in Spiking Neural Networks (NeurIPS 2022). [paper]
• Biologically Inspired Dynamic Thresholds for Spiking Neural Networks (NeurIPS 2022). [paper]
• Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks (ICLR 2022). [paper] [code]
• Multi-Level Firing with Spiking DS-ResNet: Enabling Better and Deeper Directly-Trained Spiking Neural Networks (IJCAI 2022). [paper]

2021

NeurIPS, ICCV, IJCAI, ICML, AAAI

• Deep Residual Learning in Spiking Neural Networks (NeurIPS 2021). [paper] [code]
• Spiking Deep Residual Network[paper]
• Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks (ECCV 2021). [paper] [code]
• Pruning of Deep Spiking Neural Networks through Gradient Rewiring [paper] [code]
• A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibration (ICML 2021). [paper] [code]
• Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networks [paper] [code]
• Sparse Spiking Gradient Descent (NeurIPS 2021). [paper]
• Training Spiking Neural Networks with Accumulated Spiking Flow (AAAI 2021). [paper]
• Temporal-wise Attention Spiking Neural Networks for Event Streams Classification. (ECCV 2021). [paper]