SPaRSe-TIME: Saliency-Projected Low-Rank Temporal Modeling for Efficient and Interpretable Time Series Prediction

ArXi:2604.17350v1 Announce Type: cross Time series forecasting is traditionally dominated by sequence-based architectures such as recurrent neural networks and attention mechanisms, which process all time steps uniformly and often incur substantial computational cost. However, real-world temporal signals typically exhibit heterogeneous structure, where informative patterns are sparsely distributed and interspersed with redundant observations. This work