AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Stable Spike: Dual Consistency Optimization via Bitwise AND Operations for Spiking Neural Networks

Yongqi Ding, Kunshan Yang, Linze Li, Yiyang Zhang, Mengmeng Jing, Lin Zuo

CVPR 2026 · Architectures and efficiency › Spiking networks · approach: Spiking transformers · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add spike map consistency loss L_spike (ablation)VGG-9 SNN · DVS-Gestureaccuracy (%): 87.15 -> 91.32Improved
add perturbation consistency loss L_noise (amplitude-aware spike noise) (ablation)VGG-9 SNN · DVS-Gestureaccuracy (%): 87.15 -> 94.09Improved
add both consistency losses (ablation)ResNet-18 SNN · CIFAR10-DVSaccuracy (%): 66.1 -> 70.3Improved
add both consistency losses (ablation)QKFormer · CIFAR10-DVSaccuracy (%): 81.2 -> 82.9Improved
use AND instead of OR to extract stable spikes (ablation)Stable Spike VGG-9 · CIFAR10-DVSaccuracy (%): 68.9 -> 77.1Improved
use AND instead of XOR to extract stable spikes (ablation)Stable Spike VGG-9 · DVS-Gestureaccuracy (%): 89.58 -> 94.44Improved
use amplitude-aware noise instead of fixed noise probability p=0.5 (ablation)Stable Spike VGG-9 · DVS-Gestureaccuracy (%): 88.89 -> 94.44Improved
use discrete spike noise instead of continuous Gaussian noise (std=0.5) (ablation)Stable Spike VGG-9 · DVS-Gestureaccuracy (%): 91.67 -> 94.44Improved
use amplitude-aware spike noise instead of adaptive Gaussian noise (ablation)Stable Spike VGG-9 · DVS-Gestureaccuracy (%): 88.54 -> 94.44Improved
swap MSE consistency for KL or cosine in L_spike (ablation)Stable Spike VGG-9 · CIFAR10-DVSaccuracy (%): 77.1 -> 76.2 (KL), 75.6 (Cosine)No clear effect
apply Stable Spike at ultra-low latency T=2VGG-9 SNN · DVS-Gestureaccuracy (%): 83.68 -> 92.01Improved
add AND-based consistency to more layers (Stable Spike Dense) (ablation)Stable Spike VGG-9 · CIFAR10-DVSaccuracy (%): 77.1 -> 78.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy