AI Paper Atlas

Research map / Time series / Causal and generative time series

MoRGen: Mixture-of-Resolutions Generative Forecasting for Irregularly Sampled Medical Time-Series Data

Nassim Oufattole, Matthew B.A. McDermott, Collin Stultz

ICML 2026 · Time series › Causal and generative time series · approach: Irregular series and imputation

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
fuse minute-level and coarse-resolution experts with learned mixture weightsminute-level baseline forecaster · MIMIC-IV death, 30-dayAUROC: 70.27 -> 89.06Improved
fuse minute-level and coarse-resolution expertsminute-level baseline forecaster · EHRSHOT death, 30-dayAUROC: 49.98 -> 81.46Improved
fuse resolutionsminute-level baseline forecaster · MIMIC-IV readmission, 30-dayAUROC: 69.98 -> 70.28No clear effect
fuse resolutionsminute-level baseline forecaster · Hospital A death, 2-yearAUROC: 58.93 -> 77.46Improved
fuse resolutions at extended horizonminute-level baseline forecaster · MIMIC-IV death, 20-yearAUROC: 55.36 -> 77.64Improved
fuse resolutions for joint endpointminute-level baseline forecaster · EHRSHOT creatinine and death, 30d/90dAUROC: 50.00 -> 82.70Improved
learn task- and horizon-specific mixture weights instead of uniform averaging (ablation)MoRGen · 3 datasets, 7 tasks, 2 horizonsAUROC win rate vs baseline: 66.7% -> 100.0%Improved
share one weight set across tasks and horizons instead of per-task weights (ablation)MoRGen · 3 datasets, 7 tasks, 2 horizonsAUROC win rate vs baseline: 100.0% -> 100.0%No clear effect
use all codebook sizes K in the expert pool instead of a single K (ablation)MoRGen · EHRSHOT 30-dayAUROC: Death 79.42 -> 81.46Mixed
restrict pool to a single codebook size (ablation)MoRGen · 3 datasets, 7 tasks, 2 horizonsAUROC win rate vs baseline: 167 / 168No clear effect
add ETHOS as an extra expert in the mixture (ablation)MoRGen · 42 task-horizon settings vs ETHOSAUROC win rate: 27 / 42 (64.3%) -> 40 / 42 (95.2%)Improved
add ETHOS as an extra expert (ablation)MoRGen · EHRSHOT hematocrit, 30-dayAUROC: 86.54 -> 86.36Hurt

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