AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Positional Encoding for Spiking Transformers

Zijian Zhou, Yu Liang, Honglin Cao, Ammar Belatreche, Jieyuan Zhang, Wenjie Wei, Shuai Wang, Malu Zhang, Yang Yang, Haizhou 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 PE-LIF position-dependent thresholds (positional encoding) (ablation)4-layer Spikingformer · 8 downstream NLP benchmarks avgscore: 66.72 -> 70.31Improved
add PE-LIF on STS-B (ablation)4-layer Spikingformer · STS-Bscore: 27.03 -> 55.23Improved
add MPR-SG surrogate gradient (ablation)SPE · 8 downstream NLP benchmarks avgscore: 70.31 -> 71.43Improved
add MPR-SG on QNLI (ablation)SPE · QNLIaccuracy: 71.06 -> 74.01Improved
add MPR-SG on STS-B (ablation)SPE · STS-Bscore: 55.23 -> 61.78Improved
add MPR-SG on SST-5 (ablation)SPE · SST-5accuracy: 43.79/43.48 -> 44.16No clear effect
replace CPG/Gray/Log-PE with SPESpikingformer · Long text (AGNEWS, IMDB)accuracy avg: 83.62 (Log-PE) -> 91.05Improved
replace Log-PE with SPESpikingformer · Short text avgaccuracy avg: 76.46 -> 78.68Improved
add SPE to SpikingformerSpikingformer · GLUE dev avgscore: 66.8 -> 72.6Improved
add SPE to Spikingformer (energy)Spikingformer · GLUEenergy (mJ): 6.76 -> 4.92Improved
add SPE (higher Q/K thresholds)Spikingformer · attention energymJ/sample: 0.0894 -> 0.0666Improved
add SPE on MNLI-mSpikingformer · GLUE MNLI-m/mmaccuracy: 71.9/72.5 -> 70.7/72.0No clear effect

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