Abstract: Deep learning models employing the Transformer architecture have demonstrated exceptional performance in the field of multivariate time series forecasting research. However, these models ...

This code is the official PyTorch implementation of our NIPS'25 paper: Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective. If you find this project helpful, ...

Forecasting, a fundamental task in machine learning, involves predicting future values of a time series based on its historical behavior. This paper introduces a novel Hierarchical Patch Based ...

Abstract: Transformer-based models have traditionally been the primary focus of research for addressing time series forecasting challenges. However, the emergence of recently introduced ...