AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Pretraining with Re-parametrized Self-Attention: Unlocking Generalizationin SNN-Based Neural Decoding Across Time, Brains, and Tasks

Yuqi Yang, Tengjun Liu, Haiyan Zhang, Wang Ruixue, Xuchao Chen, Mingkang Li, Yansong Chua, Nenggan Zheng, Shaomin Zhang

ICLR 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 CST re-parameterized attention block instead of spike-driven transformer block (ablation)RAT SNN-SS · Monkey C05 2025R2 x 100: 65.21 -> 66.71Improved
add CST re-parameterized attention block instead of spike-driven transformer block (ablation)RAT SNN-SS · Monkey C05 2022R2 x 100: 80.09 -> 81.58Improved
use CST attention block rather than 3-hidden-layer fully connected recurrent SNN (ablation)RAT SNN-SS · Monkey C05 2022R2 x 100: 79.47 -> 81.58Improved
enlarge MLP output dimension from 192 to 512 via surrogate shortcut (ablation)RAT SNN-SS · Monkey C05 2025R2 x 100: 66.61 -> 66.71Improved
add structural re-parameterization (ablation)RAT SNN-SS · Monkey C05R2 x 100: 67.58 -> 81.58Improved
add structural re-parameterization (ablation)RAT SNN-SS · Monkey C05training epochs to converge: 545 -> 179Improved
add cross-session pretraining (ablation)RAT SNN · NHP Monkey IR2 x 100: 72.22 -> 74.26Improved
add cross-condition pretraining over single-session (ablation)RAT SNN · NHP Monkey LR2 x 100: 66.30 -> 70.40Improved
add cross-session pretraining (ablation)RAT SNN · NLB RTT (Monkey I)R2 x 100: 76.34 -> 78.55Improved
prune RAT SNN-CC (ablation)RAT SNN-CC · NHP averageR2 x 100: 72.23 -> 71.96No clear effect
prune RAT SNN-CC (ablation)RAT SNN-CC · NHP effective ACseffective ACs: 65307 -> 21020Improved
add cross-condition pretraining to unseen subject and task (ablation)RAT SNN · RTT-joystick unseentraining epochsImproved

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