mlsanityData to 7 Oct 2026

Ge2mS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformer

arXiv 2604.08894 ↗First posted 10 Apr 2026cs.NE cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Spiking Neural Networks (SNNs) offer superior energy efficiency over Artificial Neural Networks (ANNs). However, they encounter significant deficiencies in training and inference metrics when applied to Spiking Vision Transformers (S-ViTs). Existing paradigms including ANN-SNN Conversion and Spatial-Temporal Backpropagation (STBP) suffer from inherent limitations, precluding concurrent optimization of memory, accuracy and energy consumption. To address these issues, we propose Ge2mS-T, a novel architecture implementing grouped computation across temporal, spatial and network structure dimensions. Specifically, we introduce the Grouped-Exponential-Coding-based IF (ExpG-IF) model, enabling lossless conversion with constant training overhead and precise regulation for spike patterns. Additionally, we develop Group-wise Spiking Self-Attention (GW-SSA) to reduce computational complexity via multi-scale token grouping and multiplication-free operations within a hybrid attention-convolution framework. Experiments confirm that our method can achieve superior performance with ultra-high energy efficiency on challenging benchmarks. To our best knowledge, this is the first work to systematically establish multi-dimensional grouped computation for resolving the triad of memory overhead, learning capability and energy budget in S-ViTs. Code is available at https://github.com/hzc1208/Ge2mST.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 35 of its 53 references that are in the map. First posted on arXiv 10 Apr 2026.

Builds on

35 of 53 references.

References · 35

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 399
  3. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 340
  4. 2021Deep Residual Learning in Spiking Neural Networkscited by 326
  5. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 268
  6. 2022Spikformer: When Spiking Neural Network Meets Transformercited by 263
  7. 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 192
  8. 2019Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networkscited by 143
  9. 2023Spike-driven Transformercited by 141
  10. 2023Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networkscited by 116
  11. 2021A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibrationcited by 111
  12. 2022Attention Spiking Neural Networkscited by 103
23 more
  1. 2023Agent Attention: On the Integration of Softmax and Linear Attentioncited by 90
  2. 2021Advancing Spiking Neural Networks towards Deep Residual Learningcited by 76
  3. 2024Integer-Valued Training and Spike-Driven Inference Spiking Neural Network for High-performance and Energy-efficient Object Detectioncited by 65
  4. 2022GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networkscited by 63
  5. 2024Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Trainingcited by 57
  6. 2022Online Training Through Time for Spiking Neural Networkscited by 48
  7. 2023Constructing Deep Spiking Neural Networks from Artificial Neural Networks with Knowledge Distillationcited by 41
  8. 2023Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependenciescited by 41
  9. 2022Masked Spiking Transformercited by 38
  10. 2023Bridging the Gap between ANNs and SNNs by Calibrating Offset Spikescited by 38
  11. 2023Ternary Spike: Learning Ternary Spikes for Spiking Neural Networkscited by 36
  12. 2023Gated Attention Coding for Training High-performance and Efficient Spiking Neural Networkscited by 26
  13. 2024CLIF: Complementary Leaky Integrate-and-Fire Neuron for Spiking Neural Networkscited by 21
  14. 2025Spiking Vision Transformer with Saccadic Attentioncited by 21
  15. 2025Spiking Transformer:Introducing Accurate Addition-Only Spiking Self-Attention for Transformercited by 13
  16. 2025Quantized Spike-driven Transformercited by 12
  17. 2025Rethinking Spiking Neural Networks from an Ensemble Learning Perspectivecited by 12
  18. 2024LM-HT SNN: Enhancing the Performance of SNN to ANN Counterpart through Learnable Multi-hierarchical Threshold Modelcited by 10
  19. 2025Towards High-performance Spiking Transformers from ANN to SNN Conversioncited by 10
  20. 2023Spikingformer: A Key Foundation Model for Spiking Neural Networkscited by 9
  21. 2024FTBC: Forward Temporal Bias Correction for Optimizing ANN-SNN Conversioncited by 5
  22. 2024Faster and Stronger: When ANN-SNN Conversion Meets Parallel Spiking Calculationcited by 2
  23. 2025SpikePack: Enhanced Information Flow in Spiking Neural Networks with High Hardware Compatibilitycited by 2

Built on by

Not cited yet.