Book
Open access
Aug 2026
RePatch: Learning Entropy-Guided Patch Structures with Quantized Representations for Time Series Forecasting
RePatch is proposed, a two-stage framework that learns adaptive and reusable temporal representations for time series forecasting and achieves state-of-the-art performance on most benchmarks and consistently generalizes well across diverse transfer scenarios.
Han-Bin Xiao, Xun Zhou, Ruizhi Huang et al.
· Proceedings of the 32nd ACM... · 0 citations