AI Paper Atlas

Research map / Time series / Long-term forecasting

Generalizing Multi-Scale Time-Series Modeling with a Single Operator

Cheonwoo Lee, Dooho Lee, Doyun Choi, Jaemin Yoo

ICML 2026 · Time series › Long-term forecasting · approach: Lightweight long-term forecasters · 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 the plain MLP predictor instead of TimeMixer trend-seasonal mixing (ablation)Sigma · ETTh1 predict-720MSE: 0.486 -> 0.480No clear effect
use per-element learnable scale parameters instead of one shared scale (ablation)Sigma · ETTh1 predict-720MSE: 0.489 -> 0.480Improved
use dataset-level scale parameters instead of sample-wise MLP-predicted scales (ablation)Sigma · ETTh1 predict-720MSE: 0.490 -> 0.480Improved
add the scaling mechanism rather than raw input only (ablation)Sigma · ETTh1 predict-720MSE: 0.492 -> 0.480Improved
use learnable distance-aware LDG scaling instead of moving average (ablation)Sigma · ETTh1 predict-720MSE: 0.493 -> 0.480Improved
use a normalized scaling-operator kernel instead of unnormalized convolution (ablation)Sigma · ETTh1 predict-720MSE: 0.524 -> 0.480Improved
Sigma versus second-best modelElectricity long-term · ElectricityMSE: 0.185 -> 0.175Improved
Sigma versus second-best modelTraffic long-term · TrafficMSE: 0.497 -> 0.458Improved
Sigma versus best baseline on low-dimensional dataWeather long-term · WeatherMSE: 0.245 -> 0.247No clear effect
Sigma on the small Others categoryM4 Others · M4 OthersOWA: 1.014 -> 1.037Hurt
increase input length LSigma · ETTh1 predict-720MSEImproved

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