Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN Ticket
Zhaokun Zhou, Yijie Lu, Kaiwei Che, Wei Fang, Keyu Tian, Qihao Peng, Yuesheng Zhu, Shuicheng Yan, Yonghong Tian, Li Yuan
cs.NE, cs.CV, cs.LG
Submitted: 2026-08-18
Updated: 2026-08-19
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- LLaMA: Open and Efficient Foundation Language Models
- Segment Anything
- RT-1: Robotics Transformer for Real-World Control at Scale
- Advancing Spiking Neural Networks towards Deep Residual Learning
- VOLO: Vision Outlooker for Visual Recognition
- Symbolic Discovery of Optimization Algorithms
- Enhancing the Performance of Transformer-based Spiking Neural Networks by SNN-optimized Downsampling with Precise Gradient Backpropagation
- cosFormer: Rethinking Softmax in Attention
- Rethinking Attention with Performers
- Deformable DETR: Deformable Transformers for End-to-End Object Detection
- Escaping the Big Data Paradigm with Compact Transformers
- UFO-ViT: High Performance Linear Vision Transformer without Softmax
- Spiking Deep Networks with LIF Neurons
- Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation
- SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks
- Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation
- Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANN
- Spike-driven Transformer
- Spikingformer: A Key Foundation Model for Spiking Neural Networks
Related papers
- Evolutionary Ensemble of Agents
- Encoding and Decoding Temporal Signals with Spiking Bandpass Wavelets
- Large Language Models and Evolutionary Computation: A Critical Review of Bidirectional Interaction, Automated Algorithm Design, and Co-Adaptive Systems
- Learning Alzheimer's Disease Signatures by bridging EEG with Spiking Neural Networks and Biophysical Simulations
- Investigating Hyperparameter Optimization and Transferability for ES-HyperNEAT: A TPE Approach
- S-AI-Recursive: A Bio-Inspired and Temporal Sparse AI Architecture for Iterative, Introspective, and Energy-Frugal Reasoning