# Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips

arXiv: https://arxiv.org/abs/2404.03663 · HTML: https://mlsanity.com/paper/2404.03663/

## Key facts

- Cited by 103 papers in the map (data through 14 Oct 2026).
- Builds on 64 of its 91 references that are in the map.
- First posted on arXiv 15 Feb 2024.

## Builds on (most cited first, 30 of 64)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Twins: Revisiting the Design of Spatial Attention in Vision Transformers](https://mlsanity.com/paper/2104.13840/) (2021)
- [MetaFormer Is Actually What You Need for Vision](https://mlsanity.com/paper/2111.11418/) (2021)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [ResNeSt: Split-Attention Networks](https://mlsanity.com/paper/2004.08955/) (2020)
- [Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks](https://mlsanity.com/paper/1706.02609/) (2017)

## Built on by (most cited first, 30 of 103)

- [Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training](https://mlsanity.com/paper/2411.16061/) (2024)
- [SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanisms](https://mlsanity.com/paper/2406.03287/) (2024)
- [Scalable MatMul-free Language Modeling](https://mlsanity.com/paper/2406.02528/) (2024)
- [MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map](https://mlsanity.com/paper/2411.10741/) (2024)
- [Spiking Vision Transformer with Saccadic Attention](https://mlsanity.com/paper/2502.12677/) (2025)
- [SpikingSSMs: Learning Long Sequences with Sparse and Parallel Spiking State Space Models](https://mlsanity.com/paper/2408.14909/) (2024)
- [Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation](https://mlsanity.com/paper/2412.14587/) (2024)
- [Autonomous Driving with Spiking Neural Networks](https://mlsanity.com/paper/2405.19687/) (2024)
- [Quantized Spike-driven Transformer](https://mlsanity.com/paper/2501.13492/) (2025)
- [Rethinking Spiking Neural Networks from an Ensemble Learning Perspective](https://mlsanity.com/paper/2502.14218/) (2025)
- [SDTrack: A Baseline for Event-based Tracking via Spiking Neural Networks](https://mlsanity.com/paper/2503.08703/) (2025)
- [BKDSNN: Enhancing the Performance of Learning-based Spiking Neural Networks Training with Blurred Knowledge Distillation](https://mlsanity.com/paper/2407.09083/) (2024)
- [Efficient 3D Recognition with Event-driven Spike Sparse Convolution](https://mlsanity.com/paper/2412.07360/) (2024)
- [Libra: Building Decoupled Vision System on Large Language Models](https://mlsanity.com/paper/2405.10140/) (2024)
- [SPikE-SSM: A Sparse, Precise, and Efficient Spiking State Space Model for Long Sequences Learning](https://mlsanity.com/paper/2410.17268/) (2024)
- [Towards Effective and Sparse Adversarial Attack on Spiking Neural Networks via Breaking Invisible Surrogate Gradients](https://mlsanity.com/paper/2503.03272/) (2025)
- [Ternary Spike-based Neuromorphic Signal Processing System](https://mlsanity.com/paper/2407.05310/) (2024)
- [Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications](https://mlsanity.com/paper/2410.09218/) (2024)
- [QSViT: A Methodology for Quantizing Spiking Vision Transformers](https://mlsanity.com/paper/2504.00948/) (2025)
- [Adaptive Event Stream Slicing for Open-Vocabulary Event-Based Object Detection via Vision-Language Knowledge Distillation](https://mlsanity.com/paper/2510.00681/) (2025)
- [Advancing Spiking Neural Networks towards Multiscale Spatiotemporal Interaction Learning](https://mlsanity.com/paper/2405.13672/) (2024)
- [Toward Large-scale Spiking Neural Networks: A Comprehensive Survey and Future Directions](https://mlsanity.com/paper/2409.02111/) (2024)
- [Spiking Meets Attention: Efficient Remote Sensing Image Super-Resolution with Attention Spiking Neural Networks](https://mlsanity.com/paper/2503.04223/) (2025)
- [Fully Spiking Neural Networks for Unified Frame-Event Object Tracking](https://mlsanity.com/paper/2505.20834/) (2025)
- [MK-SGN: A Spiking Graph Convolutional Network with Multimodal Fusion and Knowledge Distillation for Skeleton-based Action Recognition](https://mlsanity.com/paper/2404.10210/) (2024)
- [SpikingBrain: Spiking Brain-inspired Large Models](https://mlsanity.com/paper/2509.05276/) (2025)
- [SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and O(T) Complexity](https://mlsanity.com/paper/2505.10352/) (2025)
- [TP-Spikformer: Token Pruned Spiking Transformer](https://mlsanity.com/paper/2603.00527/) (2026)
- [SVFormer: A Direct Training Spiking Transformer for Efficient Video Action Recognition](https://mlsanity.com/paper/2406.15034/) (2024)
- [SpikeVoice: High-Quality Text-to-Speech Via Efficient Spiking Neural Network](https://mlsanity.com/paper/2408.00788/) (2024)

## Abstract (arXiv)

Neuromorphic computing, which exploits Spiking Neural Networks (SNNs) on neuromorphic chips, is a promising energy-efficient alternative to traditional AI. CNN-based SNNs are the current mainstream of neuromorphic computing. By contrast, no neuromorphic chips are designed especially for Transformer-based SNNs, which have just emerged, and their performance is only on par with CNN-based SNNs, offering no distinct advantage. In this work, we propose a general Transformer-based SNN architecture, termed as ``Meta-SpikeFormer", whose goals are: 1) Lower-power, supports the spike-driven paradigm that there is only sparse addition in the network; 2) Versatility, handles various vision tasks; 3) High-performance, shows overwhelming performance advantages over CNN-based SNNs; 4) Meta-architecture, provides inspiration for future next-generation Transformer-based neuromorphic chip designs. Specifically, we extend the Spike-driven Transformer in citetyao2023spike into a meta architecture, and explore the impact of structure, spike-driven self-attention, and skip connection on its performance. On ImageNet-1K, Meta-SpikeFormer achieves 80.0% top-1 accuracy (55M), surpassing the current state-of-the-art (SOTA) SNN baselines (66M) by 3.7%. This is the first direct training SNN backbone that can simultaneously supports classification, detection, and segmentation, obtaining SOTA results in SNNs. Finally, we discuss the inspiration of the meta SNN architecture for neuromorphic chip design. Source code and models are available at urlhttps://github.com/BICLab/Spike-Driven-Transformer-V2.