cs.AINov 17, 2026

DAQ: Decision-Aligned Post-Training Quantization for Spiking Transformers

Authors: Jialin Chen, Xiaochen Zhao, Aili Wang

Organizations: ZJU-UIUC Institute, Zhejiang University · College of Information Science and Electronic Engineering, Zhejiang University

Abstract

Spiking transformers combine attention-based representation learning with sparse spike communication, yet their weights and membrane variables still incur substantial storage and computation overhead. Post-training quantization (PTQ) offers a practical way to reduce these overheads, but preserving neuronal firing under weight and membrane quantization remains challenging. In this paper, we propose Decision-Aligned Post-Training Quantization (DAQ), a method that calibrates the quantizers to align neuronal firing decisions with those of a floating-point reference. We analyze how errors from these quantizers affect firing at decision boundaries and how they propagate over time steps in recurrent neurons. Based on this analysis, we formulate an objective that encourages quantized membrane variables to remain within the reference firing regions along the quantized model's own state trajectory. Experiments across multiple spiking transformer architectures on image classification, semantic segmentation, and event-based tracking demonstrate the effectiveness of DAQ with 4-bit weights and membrane variables. On FE108, DAQ achieves 58.8% AUC and 90.9% PR with SDTrack, while reducing energy by 66.2%.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. PTQ4SNN: Membrane-Aware Post-Training Quantization for Spiking Neural Networks

    Aug 7, 2026Hui Xie, Tong Shi, Haotong Qin +3Mixed-Precision Quantization4-Bit Quantization

  2. SpikeQ: Spike-Guided Post-Training Quantization for Spiking Neural Networks

    Oct 16, 2026Kai Sun, Peibo Duan, Zhanglu Yan +3Spiking Neural NetworksPost-Training Quantization

  3. DAQ: Delta-Aware Quantization for Post-Training LLM Weight Compression

    Mar 20, 2026Xiaoming Yu, Shize Tang, Guanghua Yu +4QuantizationLLM Quantization