AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Resolving the Timestep Scaling Paradox in Spiking Neural Networks with a Timestep-Scalable Neuron Model

Binghao Ye, Wenjuan Li, Dengfeng Xue, Bing Li, Weiming Hu, Dong Liang, Kun Shang

ICML 2026 · Architectures and efficiency › Spiking networks · approach: Training deep spiking networks

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 memory reconsolidation (ablation)LIF neuron · CIFAR-100 (ResNet20, T=10)accuracy (%): 72.01 -> 74.33Improved
add memory reconsolidation (ablation)LIF neuron · CIFAR10-DVS (ResNet20, T=10)accuracy (%): 79.60 -> 81.50Improved
add temporal forgetting alone (ablation)LIF neuron · CIFAR-100 (ResNet20, T=10)accuracy (%): 72.01 -> 72.85Improved
add temporal forgetting on top of reconsolidation (ablation)TS-LIF (R only) · CIFAR-100 (ResNet20, T=10)accuracy (%): 74.33 -> 75.54Improved
add temporal forgetting on top of reconsolidation (ablation)TS-LIF (R only) · CIFAR10-DVS (ResNet20, T=10)accuracy (%): 81.50 -> 82.30Improved
add normalization alone (ablation)LIF neuron · CIFAR-100 (ResNet20, T=10)accuracy (%): 72.01 -> 69.95Hurt
add normalization alone (ablation)LIF neuron · CIFAR10-DVS (ResNet20, T=10)accuracy (%): 79.60 -> 78.70Hurt
add normalization on top of forgetting (ablation)TS-LIF (F only) · CIFAR10-DVS (ResNet20, T=10)accuracy (%): 80.30 -> 81.20Improved
add normalization to reconsolidation plus forgetting (ablation)TS-LIF (R+F) · CIFAR-100 (ResNet20, T=10)accuracy (%): 75.54 -> 76.28Improved
replace LIF with TS-LIF at larger timesteps3B-Net · Gait (T=90)accuracy (%): 83.80 -> 89.80Improved
increase timesteps from 4 to 8SpikeYOLO 13.2M · COCOmAP@50 (%): 51.3 -> 50.1Hurt
increase timesteps from 4 to 8TS-LIF 13.2M · COCOmAP@50 (%): 51.8 -> 53.6Improved

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