AI Paper Atlas

Research map / Time series / Causal and generative time series

MambaSL: Exploring Single-Layer Mamba for Time Series Classification

Yoo-Min Jung, Leekyung Kim

ICLR 2026 · Time series › Causal and generative time series · approach: Dynamical system reconstruction · 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 H1 (scaled input projection kernel k=0.02L) (ablation)MambaSL · UEA 30 datasetsavg accuracy: 80.215 -> 79.802 (30 datasets); 77.413 -> 78.779 (10 datasets)Mixed
add H2 (modular time variance/invariance) (ablation)MambaSL · UEA 30 datasetsavg accuracy: 77.075 -> 79.802Improved
add H3 (remove skip connection D) (ablation)MambaSL · UEA 30 datasetsavg accuracy: 79.163 -> 79.802Improved
add H4 adaptive pooling instead of fully connected (ablation)MambaSL · UEA 30 datasetsavg accuracy: 77.722 -> 79.802Improved
add H4 adaptive pooling instead of average pooling (ablation)MambaSL · UEA 30 datasetsavg accuracy: 78.610 -> 79.802Improved
add H4 adaptive pooling instead of max pooling (ablation)MambaSL · UEA 30 datasetsavg accuracy: 78.535 -> 79.802Improved
add H4 adaptive pooling instead of last-step readout (ablation)MambaSL · UEA 30 datasetsavg accuracy: 76.848 -> 79.802Improved
add H1, H3, H4 on top of H2-only variant (ablation)MambaSL · UEA 30 datasetsavg accuracy: 77.935 -> 79.802Improved
add all four hypotheses H1-H4 to vanilla Mamba (ablation)Mamba · UEA 30 datasetsavg accuracy: 74.243 -> 79.802Improved
make Delta, B, C all time-variant (vs all time-invariant) (ablation)MambaSL · UEA 30 datasetsavg accuracy: 77.400 -> 77.055Hurt
stack 2 Mamba blocks instead of 1 (ablation)MambaSL · UEA 30 datasetsavg accuracy: 79.819 -> 79.316Hurt
stack 3 Mamba blocks instead of 1 (ablation)MambaSL · UEA 30 datasetsavg accuracy: 79.819 -> 79.279Hurt

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