AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Spike-HTR: Spiking Neural Transformer for Handwritten Text Recognition

Xiubo Liang, Jinxing Han, Yuke Li, Haoqi Zhu, Yu Zhao, Hongzhi Wang

ICML 2026 · Architectures and efficiency › Spiking networks · approach: Spiking transformers · 0 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 InkCoder instead of repeat injection (ablation)Spike-HTR · IAM valvalidation CER (%): 4.3 -> 3.5Improved
use InkCoder instead of Poisson coding (ablation)Spike-HTR · IAM valvalidation CER (%): 4.7 -> 3.5Improved
use InkCoder instead of TTFS-style coding (ablation)Spike-HTR · IAM valvalidation CER (%): 4.1 -> 3.5Improved
fuse edge stream with intensity stream (ablation)Spike-HTR · IAM valvalidation CER (%): 3.6 -> 3.5 (intensity-only), 3.8 -> 3.5 (edge-only)Improved
use gradual gate contraction over timesteps (ablation)Spike-HTR · IAM valvalidation CER (%): 3.7 -> 3.5Improved
use spiking neurons instead of GELU (ablation)Spike-HTR · IAM val (T=1)validation CER (%): 3.558 -> 3.489Improved
add InkCoder and membrane residual (ablation)Spike-HTR · IAM val (T=1)validation CER (%): 3.646 -> 3.489Improved
add keep-and-merge length reduction (ablation)Spike-HTR · IAM valvalidation CER (%): 3.52 -> 3.49 (r 1.00 -> 0.68)No clear effect
keep-and-merge instead of merge-only (ablation)Spike-HTR · IAM valvalidation CER (%): 3.60 -> 3.49Improved
stop gradient through the preview (ablation)Spike-HTR · IAM valvalidation CER (%): 3.65 -> 3.49Improved
increase timesteps from T=2 to T=4Spike-HTR · IAM testtest CER (%): 5.4 -> 5.4 (IAM test CER)No clear effect
increase timestepsSpike-HTR · IAM, LAM, READ2016WERImproved

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