AI Paper Atlas

Research map / Time series / Long-term forecasting

XLinear: A Lightweight and Accurate MLP-Based Model for Long-Term Time Series Forecasting with Exogenous Inputs

Xinyang Chen, Huidong Jin, Yu Huang, Zaiwen Feng

AAAI 2026 · Time series › Long-term forecasting · approach: Lightweight long-term forecasters · 10 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 global tokens carrying exogenous information to the endogenous sequence (ablation)XLinear · Weather multivariate h96MSE: 0.175 -> 0.149Improved
add global tokens carrying exogenous information (ablation)XLinear · ETTh1 multivariate h96MSE: 0.370 -> 0.369No clear effect
add endogenous temporal sequence to global tokens (ablation)XLinear · Weather multivariate h96MSE: 0.153 -> 0.149Improved
add endogenous temporal sequence to global tokens (ablation)XLinear · GTDS h96MSE: 0.012 -> 0.012No clear effect
use global tokens alone instead of endogenous sequence alone (ablation)XLinear · ETTm1 / Weather / GTDSMSE: ETTm1 0.328 -> 0.326; Weather 0.175 -> 0.153Improved
use XLinear instead of TimeXerXLinear · Electricity multivariate h96MSE: 0.140 -> 0.138Improved
use XLinear instead of iTransformer on high-dimensional TrafficXLinear · Traffic multivariate h96MSE: 0.395 -> 0.432Hurt
use XLinear instead of patch-based TimeXer and PatchTST on volatile PEMS dataXLinear · PEMS03 h12MSE: 0.033 -> 0.030Improved
use XLinear on PEMS03 at longest horizonXLinear · PEMS03 h96MSE: 0.129 -> 0.133Hurt
use lookback 512 with XLinear instead of PatchTST at horizon 720XLinear · ETTh1 lookback 512 h720MSE: 0.447 -> 0.451No clear effect
use XLinear instead of TimeXer for training speedXLinear · Electricity univariatetraining time ms/iter: 37 -> 17Improved

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