AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

HuiduRep: A Robust Self-Supervised Framework for Learning Neural Representations from Extracellular Recordings

Feng Cao, Zishuo Feng, Jicong Zhang, Wei Shi

AAAI 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 2 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
add denoising autoencoder branch with alpha=0.2 to contrastive training (ablation)HuiduRep · IBL test (10 units)ARI: 70.5 -> 71.9Improved
increase denoising loss weight to 0.8 or above (ablation)HuiduRep · IBL test (10 units)ARI: 71.9 -> 65.3Hurt
increase representation dimension from 16 to 48 (ablation)HuiduRep · IBL test (10 units)ARI: 69.7 -> 72.9 (time 5.39 -> 7.47 s)Improved
apply DAE before encoder at inference on Hybrid Janelia (ablation)HuiduRep pipeline · Hybrid Janelia-Staticaccuracy: 0.69 -> 0.70Improved
apply DAE before encoder at inference on Hybrid Janelia (ablation)HuiduRep pipeline · Hybrid Janelia-Driftaccuracy: 0.56 -> 0.60Improved
apply DAE before encoder at inference on Hybrid Janelia (ablation)HuiduRep pipeline · Hybrid Janeliaprecision: 0.87 -> 0.85 (static); 0.83 -> 0.83 (drift)No clear effect
apply DAE at inference on in-distribution data (ablation)HuiduRep · IBL test datasetARI: 0.72 -> 0.44Hurt
use HuiduRep instead of CEED/MoCo-v3 representationsspike clustering with GMM · IBL test (10 units)ARI: 63.5 -> 71.9 (CEED); 66.9 -> 71.9 (MoCo-v3)Improved
HuiduRep pipeline vs KiloSort4 and MountainSort5spike sorting · Hybrid Janelia-Staticaccuracy: 0.40 -> 0.70Improved

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