# Spiking Local Interaction and Adaptive Complementary Fusion for Spiking Transformer

arXiv: https://arxiv.org/abs/2608.19238 · HTML: https://mlsanity.com/paper/2608.19238/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 39 references that are in the map.
- First posted on arXiv 11 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [MetaFormer Is Actually What You Need for Vision](https://mlsanity.com/paper/2111.11418/) (2021)
- [Deep Residual Learning in Spiking Neural Networks](https://mlsanity.com/paper/2102.04159/) (2021)
- [Going Deeper With Directly-Trained Larger Spiking Neural Networks](https://mlsanity.com/paper/2011.05280/) (2020)
- [Spikformer: When Spiking Neural Network Meets Transformer](https://mlsanity.com/paper/2209.15425/) (2022)
- [Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips](https://mlsanity.com/paper/2404.03663/) (2024)
- [Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training](https://mlsanity.com/paper/2411.16061/) (2024)
- [Spiking Vision Transformer with Saccadic Attention](https://mlsanity.com/paper/2502.12677/) (2025)
- [Spiking Transformer with Spatial-Temporal Attention](https://mlsanity.com/paper/2409.19764/) (2024)
- [Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation](https://mlsanity.com/paper/2412.14587/) (2024)
- [Spiking Transformer:Introducing Accurate Addition-Only Spiking Self-Attention for Transformer](https://mlsanity.com/paper/2503.00226/) (2025)
- [TIM: An Efficient Temporal Interaction Module for Spiking Transformer](https://mlsanity.com/paper/2401.11687/) (2024)
- [SpiLiFormer: Enhancing Spiking Transformers with Lateral Inhibition](https://mlsanity.com/paper/2503.15986/) (2025)
- [STEP: A Unified Spiking Transformer Evaluation Platform for Fair and Reproducible Benchmarking](https://mlsanity.com/paper/2505.11151/) (2025)
- [Spiking Neural Networks Need High Frequency Information](https://mlsanity.com/paper/2505.18608/) (2025)
- [SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference](https://mlsanity.com/paper/2604.22575/) (2026)
- [TEFormer: Structured Bidirectional Temporal Enhancement Modeling in Spiking Transformers](https://mlsanity.com/paper/2601.18274/) (2026)

## Abstract (arXiv)

Spiking Transformers model token interactions primarily through spiking self-attention (SSA). However, binary query and key representations map continuous similarities to sparse and discrete relation responses, which may suppress weak relations and limit the propagation of local spatial context. To address this limitation, we introduce Spiking Local Interaction (SLI) and Adaptive Complementary Fusion (ACF). SLI establishes an attention-independent pathway for direct information exchange among neighboring spiking tokens using lightweight depthwise--pointwise transformations. ACF integrates SSA and SLI through layer-specific, channel-wise coefficients that adaptively balance their contributions at different network depths. The proposed design preserves the original attention formulation and can be incorporated into different Spiking Transformer architectures with modest parameter overhead. Experiments on ImageNet-1K, CIFAR-10, CIFAR-100, CIFAR10-DVS, and ADE20K show consistent improvements across image classification, event-based recognition, and semantic segmentation. In particular, QKFormer with SLI and ACF achieves 84.37% Top-1 accuracy on ImageNet-1K and 37.5% mIoU on ADE20K, where the segmentation model is trained without ImageNet pretraining. Ablation studies and qualitative analyses further indicate that SSA and SLI capture complementary interaction patterns and that learnable fusion consistently outperforms fixed weighting.