AI Paper Atlas

Research map / Time series / Causal and generative time series

Dynamic TMoE: A Drift-Aware Dynamic Mixture of Experts Framework for Non-Stationary Time Series Forecasting

Jiawen Zhu, Shuhan Liu, Di Weng, Yingcai Wu

ICML 2026 · Time series › Causal and generative time series · approach: Probabilistic and conformal 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 drift-aware adaptation (ablation)Dynamic TMoE · ETTh1MSE: 0.436 -> 0.429Improved
add drift-aware adaptation (ablation)Dynamic TMoE · WeatherMSE: 0.246 -> 0.240Improved
use GRU temporal router instead of non-temporal routers (ablation)Dynamic TMoE · six benchmarksMSE: MSE +4.2% and MAE +1.8% when replacedImproved
add anomaly memory repository (ablation)Dynamic TMoE · ETTh1MSE: 0.438 -> 0.429Improved
use heterogeneous experts instead of homogeneous (ablation)Dynamic TMoE · six benchmarksMSE: MSE +4.5% and MAE +2.1% when homogeneousImproved
add cyclic relation layer (ablation)Dynamic TMoE · six benchmarksMSE: MSE +4.5% and MAE +1.8% when removedImproved
use MMD drift detection instead of mean-variance (ablation)Dynamic TMoE · ExchangeMSE: 0.382 -> 0.351Improved
use post-addition alignment instead of fine-tuning base experts (ablation)Dynamic TMoE · ILIMSE: 2.238 -> 1.981Improved
use Drift Pattern Profiler instead of random expert type (ablation)Dynamic TMoE · ILIMSE: 2.260 -> 1.981Improved
add expert pruning (ablation)Dynamic TMoE · ExchangeMSE: 0.355 -> 0.351Improved
increase top-k from 3 to 4 (ablation)Dynamic TMoE · four datasetsMSEHurt
use top-k=1 instead of 3 (ablation)Dynamic TMoE · four datasetsMSEHurt

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