AI Paper Atlas

Research map / Time series / Causal and generative time series

PULSE: Generative Phase Evolution for Non-Stationary Time Series Forecasting

Yangyou Liu, Zezhi Shao, Xinyu Chen, Hu Chen, Fei Wang, Yuankai Wu

ICML 2026 · Time series › Causal and generative time series · approach: Dynamical system reconstruction · 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
Add Phase Anchor disentanglement (ablation)PULSE (MLP) · Average over 8 datasetsMSE: 0.326 -> 0.306Improved
Add Phase Router (ablation)PULSE (MLP) · Average over 8 datasetsMSE: 0.315 -> 0.306Improved
Add Statistic-Aware Mixup (SAM) (ablation)PULSE (MLP) · Average over 8 datasetsMSE: 0.314 -> 0.306Improved
Add Statistic-Aware mechanism (ablation)PULSE (MLP) · Average over 8 datasetsMSE: 0.313 -> 0.306Improved
Add SAM (ablation)PULSE (MLP) · ElectricityMSE: 0.160 -> 0.160No clear effect
Plug PULSE into DLinearDLinear · ETTh2MSE: 0.559 -> 0.373Improved
Plug PULSE into DLinearDLinear · SolarMSE: 0.330 -> 0.216Improved
Plug PULSE into TimesNetTimesNet · SolarMSE: 0.301 -> 0.203Improved
Plug PULSE into iTransformeriTransformer · SolarMSE: 0.233 -> 0.193Improved
Plug PULSE into PatchTSTPatchTST · TrafficMSE: 0.481 -> 0.565Hurt
Plug PULSE into PatchTSTPatchTST · SolarMSE: 0.270 -> 0.216Improved
Plug PULSE into iTransformeriTransformer · TrafficMSE: 0.428 -> 0.424No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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