Perceive, Route and Modulate: Dynamic Pattern Recalibration for Time Series Forecasting

ArXi:2605.06310v1 Announce Type: new Local temporal patterns in real-world time series continuously shift, rendering globally shared transformations suboptimal. Current deep forecasting models, despite their scale and complexity, rely on fixed weight matrices applied uniformly to all temporal tokens. This creates a static pattern response: models settle into a compromised average, unable to adapt to changing local dynamics. We