AI Paper Atlas

Research map / Time series / Long-term forecasting

See More, Forecast Better and Faster: Enhancing Time Series Foundation Models via Inference-Time Plug-and-Play Downsampling

Longlong Xu, Zeyan Li, Xiao He, Zhaoyang Yu, Dazhong Wen, Mingze Sun, Changhua Pei, Dan Pei

ICML 2026 · Time series › Long-term forecasting · approach: Lightweight long-term forecasters

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 SPRINT downsampling wrapperChronos · ETTm1MSE: 0.615 -> 0.414Improved
add SPRINT downsampling wrapperVisionTS · ETTm1MSE: 0.709 -> 0.452Improved
add SPRINT downsampling wrapperMoirai · ETTm1MSE: 0.369 -> 0.356Improved
add SPRINT downsampling wrapperTimer · ServiceMSE: 0.745 -> 0.494Improved
add SPRINT downsampling wrapperToTo · ServiceMSE: 0.166 -> 0.171Hurt
add SPRINT downsampling wrapperVisionTS · ServiceMSE: 0.426 -> 0.491Hurt
add SPRINT downsampling wrapperTSFMs (ultra-long L=1440) · Ultra-long-term forecastingaverage MSE reduction: 18.45% to 32.39%Improved
add SPRINT so the model forecasts beyond its native lengthTimer · ETTm1 L>720validity of forecast: NaN -> valid up to L=5760Improved
add SPRINT downsampling wrapperChronos · ETTm1 efficiencyinference time (ms): 1707.72 -> 28.45Improved
add SPRINT downsampling wrapperVisionTS · ETTm1 efficiencyinference time (ms): 6.43 -> 7.33Hurt
add seasonal-trend decomposition before downsampling (ablation)SPRINT · ETTh2, ETTm2, Weather, ServiceMSEImproved
use moving-average instead of STL decomposition (ablation)SPRINT · ETTh2, ETTm2, Weather, ServiceMSEImproved

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