AI Paper Atlas

Research map / Time series / Long-term forecasting

QuITE: Query-Based Irregular Time Series Embedding

Junghoon Lim

ICML 2026 · Time series › Long-term forecasting · approach: Graph-based multivariate forecasting · 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 QuITE query-based embeddingiTransformer · IMTS forecasting (average)MSE: 8.37 -> 3.79Improved
add QuITE query-based embeddingPatchTST · IMTS forecasting (average)MSE: 7.59 -> 6.36Improved
add QuITE query-based embeddingPatchMixer · IMTS forecasting (average)MSE: 6.84 -> 6.49Improved
add QuITE query-based embeddingPatchMixer · IMTS classification (average)average score: 65.2 -> 75.5Improved
add QuITE query-based embeddingTMix · IMTS classification P19 AUPRCAUPRC: 10.1 -> 38.0Improved
add QuITE to variate-token models rather than patch-token modelsbackbones · IMTS forecastingMSEMixed
use query-token aggregation instead of mean pooling after self-attention (ablation)iTransformer · PhysioNet horizon-averageMSE: 12.15 -> 5.21Improved
use query-token aggregation instead of mTAND grid embedding (ablation)iTransformer · PhysioNet horizon-averageMSE: 13.11 -> 5.21Improved
add time embedding to values (Add) or concatenate timestamps (Concat) instead of QuITE (ablation)iTransformer · PhysioNet horizon-averageMSE: 18.26 / 18.27 vs 5.21Hurt
vary query token initialization (Xavier, uniform, zero, random) (ablation)QuITE++ · Human Activity / USHCNMSE: 2.45-2.46 MSE on Human ActivityNo clear effect
remove 75% additional observations at test timeQuITE++ · Human Activity, USHCN, PhysioNetMSEHurt
remove up to 50% additional observationsQuITE++ · Human Activity, USHCN, PhysioNetMSENo 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