AI Paper Atlas

Research map / Time series / Long-term forecasting

L-Drive: Beyond a Single Mapping—Latent Context Drives Time Series Forecasting

Fan Zhang, Shijun Chen, Hua Wang

ICML 2026 · Time series › Long-term forecasting · approach: Attention for time series 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 L-Context generator (ablation)L-Drive · ETTh2MSE: 0.375 -> 0.367Improved
add L-Context generator (ablation)L-Drive · ECLMSE: 0.177 -> 0.169Improved
add gating on increment representations (ablation)L-Drive · ECLMSE: 0.176 -> 0.169Improved
use structured L-Context instead of random learnable context variables (ablation)L-Drive · ETTh2MSE: 0.382 -> 0.367Improved
use intra-patch relative positional bases instead of none (ablation)L-Drive · ETTm2MSE: 0.277 -> 0.273Improved
use patch-shared relative positional bases instead of global positional representation (ablation)L-Drive · ETTh1MSE: 0.434 -> 0.427Improved
use patch-shared relative positional bases instead of global positional representation (ablation)L-Drive · ETTm2MSE: 0.273 -> 0.273No clear effect
inject L-Context into DLinearDLinear · ECLMSE: 0.212 -> 0.198Improved
inject L-Context into PatchTSTPatchTST · ECLMSE: 0.205 -> 0.184Improved
inject L-Context into iTransformeriTransformer · ECLMSE: 0.178 -> 0.176Improved
inject L-Context into DLinearDLinear · WeatherMSE: 0.265 -> 0.265No clear effect
use L-Drive instead of Direct-Mapping baselines around change eventsL-Drive vs TimeBridge and iTransformer · ETTh1 lag errorTailAUC: 119.98 -> 95.94Improved

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