AI Paper Atlas

Research map / Time series / Causal and generative time series

Diff-MN: Diffusion Parameterized MoE-NCDE for Continuous Time Series Generation with Irregular Observations

Xu Zhang, Junwei Deng, Chang Xu, Hao Li, Jiang Bian

ICML 2026 · Time series › Causal and generative time series · approach: Diffusion models for time series · 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 mixture-of-experts dynamics function (ablation)Diff-MN · ECG5K (30% dropped)MDD: 0.152 -> 0.062Improved
add decoupled design with pretrained channel-wise autoencoder (ablation)Diff-MN · ECG5K (30% dropped)MDD: 0.191 -> 0.062Improved
combine MoE and decoupled design (ablation)Diff-MN · ECGFD (30% dropped)MDD: 0.965 -> 0.424Improved
use four experts rather than one expert with same layers (ablation)MoE-NCDE · ECG200 (30% dropped)KL divergence: 0.136 -> 0.052Improved
use four experts rather than one expert with same layers (ablation)MoE-NCDE · ECG5K (30% dropped)Discriminative score: 0.364 -> 0.205Improved
use diffusion-generated MoE weights for continuous generationDiff-MN · Sines continuous forecasting (30% dropped)MSE: 0.049 -> 0.026Improved
apply standard NCDE for continuous generationKoVAE · Stocks continuous forecasting (30% dropped)MSE: 0.025 -> 0.041Hurt
use dense MoE instead of sparse MoE (ablation)MoE-NCDE · ECG datasetsDiscriminative score: 7 vs 5 winsMixed
increase number of experts beyond one (ablation)MoE-NCDE · ECG datasetsMDD: one expert 0.176 -> four experts 0.079Mixed
use MoE dynamics over standard NCDE in time costMoE-NCDE · Stocks length 12generation time: 0.81s -> 1.2sHurt

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