AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Spiking-Aided Neural Architecture for Efficient and Robust WiFi Sensing

Yisha Lu, Liwen Jing, Jiangmao Zheng, Bowen Zhang

AAAI 2026 · Architectures and efficiency › Spiking networks · approach: Spiking transformers · 1 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
use spiking IF neurons instead of ReLU in the CNN-GRU pipeline (ablation)SWS-Net · Widar3.0 (22 gestures)accuracy (%): about 80% -> 83.83Improved
use hybrid spiking architecture instead of CNN-GRU (ablation)SWS-Net · Widar3.0 (22 gestures)accuracy (%): 80.87 -> 83.83Improved
use SWS-Net instead of CNNSWS-Net · Widar3.0 (22 gestures)training time (s): 5810.18 -> 448.29Improved
use SWS-Net instead of CNNSWS-Net · NTU-Fi-HumanIDFLOPs (G): 42.09 -> 4.62Improved
use SWS-Net instead of ProbSparse AttentionSWS-Net · NTU-Fi-HumanIDaccuracy (%): 99.93 -> 98.11Hurt
use SWS-Net instead of TransformerSWS-Net · NTU-Fi-HumanIDaccuracy (%): 98.78 -> 98.11Hurt
use SWS-Net instead of CNNSWS-Net · NTU-Fi-HARaccuracy (%): 100 -> 100No clear effect
use SWS-Net instead of SenseMambaSWS-Net · Widar3.0 (22 gestures)accuracy (%): 66.15 -> 83.83Improved

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