AI Paper Atlas

Research map / Time series / Foundation models for time series

FlowState: Sampling-Rate‑Equivariant Time‑Series Forecasting

Lars Graf, Thomas Ortner, Stanisław Woźniak, Angeliki Pantazi

ICML 2026 · Time series › Foundation models for time series · approach: Time series foundation models

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 functional basis decoder instead of fixed linear decoder (ablation)FlowState-3M (2k) · GIFT-Eval (FlowState-3M, 2k context)MASE: 0.754 -> 0.725Improved
add time noise to decoder sampling locations during training (ablation)FlowState-3M (2k) · GIFT-Eval (FlowState-3M, 2k context)MASE: 0.740 -> 0.725Improved
use causal RevIN instead of standard RevIN (ablation)FlowState-3M (2k) · GIFT-Eval (FlowState-3M, 2k context)MASE: 0.738 -> 0.725Improved
use all basis functions instead of first 128 at inference (ablation)FlowState-3M (2k) · GIFT-Eval (FlowState-3M, 2k context)MASE: 0.726 -> 0.725No clear effect
use all basis functions instead of first 64 at inference (ablation)FlowState-3M (2k) · GIFT-Eval (FlowState-3M, 2k context)MASE: 0.735 -> 0.725Improved
add sampling-rate adjustment mechanism (scale factor) (ablation)FlowState-3M (2k) · GIFT-Eval (FlowState-3M, 2k context)MASE, CRPSImproved
add parallel predictions during training (ablation)FlowState-3M (2k) · GIFT-Eval (FlowState-3M, 2k context)MASE, CRPSImproved
add output gate to SSM block (ablation)FlowState-3M (2k) · GIFT-Eval (FlowState-3M, 2k context)MASE, CRPSImproved
use complex SSM instead of real SSM (S4D-real init) (ablation)FlowState-3M (2k) · GIFT-Eval (FlowState-3M, 2k context)MASE, CRPSImproved
make Delta_E input-selective like S6 (ablation)FlowState-3M (2k) · GIFT-Eval (FlowState-3M, 2k context)MASE, CRPSHurt
use Legendre basis instead of Fourier basis (ablation)FlowState-3M (2k) · GIFT-Eval (FlowState-3M, 2k context)MASE, CRPSImproved
forecast a quarter season (Legendre) instead of full season (Full-Legendre) (ablation)FlowState-3M (2k) · GIFT-Eval (FlowState-3M, 2k context)MASE, CRPSImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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