LeapTS: Rethinking Time Series Forecasting as Adaptive Multi-Horizon Scheduling

ArXi:2605.10292v1 Announce Type: cross Time series forecasting serves as an essential tool for many real-world applications, ing tasks such as resource optimization and decision-making. Despite significant architectural advancements, most modern models still treat forecasting task as a fixed mapping from history to target horizons. This induces temporal decoupling across future time points and limits the model's ability to adapt to the evolving context as forecasting progresses.