AI Paper Atlas

Research map / Time series / Causal and generative time series

Flow-based Conformal Prediction for Multi-dimensional Time Series

Junghwan Lee, Chen Xu, Yao Xie

ICLR 2026 · Time series › Causal and generative time series · approach: Probabilistic and conformal forecasting · 3 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
use FCP instead of MultiDimSPCILOO bootstrap · Wind, d_y=8prediction set size: 205.5 -> 19.4Improved
use FCP instead of MultiDimSPCILOO bootstrap · Traffic, d_y=8prediction set size: 10.7 -> 1.53Improved
use FCP instead of local ellipsoidsLOO bootstrap · Solar, d_y=2prediction set size: 1.44 vs 1.48 (ellipsoid coverage 0.947 below target)No clear effect
use FCP instead of MultiDimSPCILSTM · Traffic, d_y=2prediction set size: 0.870 -> 0.859Improved
remove Transformer encoder for guidance (ablation)FCP, LOO bootstrap · Wind, d_y=8prediction set size: 19.4 -> 35.3Hurt
remove Transformer encoder for guidance (ablation)FCP, LSTM · Wind, d_y=2prediction set size: 1.18 -> 1.92Hurt
model the guided vector field with iResNet (bi-Lipschitz) instead of MLP (ablation)FCP · Wind, Traffic, Solarcoverage and set sizeNo clear effect
increase classifier-free guidance scale w (ablation)FCP · three datasetsprediction set size and coverageMixed

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