AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

High-Fidelity ANN-to-SNN Conversion via Closed-Loop CKA Distillation

Bozhou Li, Chubo Liu, Yan Ding, Yufeng Zhang, Zhuo Tang, Kenli Li

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
add global distillation loss (ablation)ResNet-18 task-loss baseline · CIFAR-10 (T=2)accuracy: 85.08 -> 87.68Improved
add global distillation loss (ablation)ResNet-18 task-loss baseline · CIFAR-10 (T=8)accuracy: 95.10 -> 94.92Hurt
add global distillation loss (ablation)ResNet-18 task-loss baseline · CIFAR-10 (T=64)accuracy: 96.14 -> 96.41Improved
add CKA local loss (ablation)ResNet-18 task-loss baseline · CIFAR-10 (T=2)accuracy: 85.08 -> 88.86Improved
add CKA local loss (ablation)ResNet-18 task-loss baseline · CIFAR-10 (T=64)accuracy: 96.14 -> 96.18No clear effect
local-only instead of global-only loss (ablation)ResNet-18 task-loss baseline · CIFAR-10 (T=4)accuracy: 93.32 -> 93.50Improved
use beta=0.2 instead of 0.5 (ablation)dual alignment · CIFAR-10 (T=2)accuracy: 85.09 -> 90.05Improved
combine global and local alignment vs baseline (ablation)ResNet-18 · CIFAR-10 (T=2)accuracy: 85.08 -> 90.05Improved
apply closed-loop fine-tuning after SpikingJelly conversionSpikingJelly · CIFAR-10 ResNet-18 (T=8)accuracy: 49.05 -> 95.33Improved
apply closed-loop fine-tuning after SpikingJelly conversionSpikingJelly · CIFAR-10 ResNet-18 (T=32)accuracy: 93.90 -> 96.38Improved
apply closed-loop fine-tuningConvert-SNN · CIFAR-10 Gaussian noise 0.1accuracy: ≈20% -> ≈40%Improved
add refinement stage after conversionSpikingJelly ann2snn · CIFAR-10 ResNet-18 (T=2)wall-clock time (s): 245 -> 1003Hurt

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