AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

UniSparse: Combining Weight Pruning and Spike Sparsification in Spiking Neural Networks

Xinyu Shi, Tong Bu, Zhaofei Yu

ICML 2026 · Architectures and efficiency › Spiking networks · approach: Spiking transformers

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 UniSparse instead of UPFUPF · CIFAR-10 CifarNet lowest-SOPs pointaccuracy: 90.65 -> 90.76Improved
use UniSparse ResNet-18 instead of UPFUPF · CIFAR-10 lowest-SOPs pointaccuracy: 90.65 -> 92.38Improved
use UniSparse ResNet-19 instead of UPFUPF · CIFAR-10 lowest-SOPs pointaccuracy: 90.65 -> 91.56Improved
use UniSparse instead of UPFUPF · DVS-CIFAR10accuracy: 78.3 -> 79.12Improved
use UniSparse instead of UPFUPF · ImageNet ResNet-18accuracy: 58.99 -> 59.66Improved
add weight pruning to spike sparsification only (ablation)UniSparse (spike sparsification only) · DVS-CIFAR10average SOPsImproved
add spike sparsification to weight pruning only (ablation)UniSparse (weight pruning only) · DVS-CIFAR10accuracy at matched SOPsImproved
apply UniSparse to Spikformer-8-384 spiking transformerSpikformer-8-384 · ImageNetaccuracy: 72.21 -> 70.68 -> 68.29No clear effect

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