AI Paper Atlas

Research map / Time series / Causal and generative time series

DoFlow: Flow-based Generative Models for Interventional and Counterfactual Forecasting on Time Series

Dongze Wu, Feng Qiu, Yao Xie

ICLR 2026 · Time series › Causal and generative time series · approach: Probabilistic and conformal forecasting · 1 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 DoFlow instead of adapted forecasters for interventional queriesDoFlow · Tree (additive)RMSE (interventional): 0.74 -> 0.54Improved
use DoFlow instead of adapted forecasters for interventional queriesDoFlow · FC-Layer (NLNA)RMSE (interventional): 1.02 -> 0.36Improved
use DoFlow for observational forecasting vs strongest baselineDoFlow · Diamond (additive)RMSE (observational): 0.49 -> 0.55Hurt
use DoFlow for observational forecasting vs strongest baselineDoFlow · FC-Layer (additive)RMSE (observational): 0.38 -> 0.39No clear effect
use DoFlow for observational forecasting vs strongest baselineDoFlow · Diamond (NLNA)RMSE (observational): 0.33 -> 0.31Improved
use DoFlow encode-decode counterfactual generation under NLNA SCMs outside the theory assumptionsDoFlow · Tree (NLNA)RMSE (counterfactual): 0.11 -> 0.14No clear effect

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