Xiyu Meng

Dual-MoE: Learning Time and Channel Dependencies via Dual Mixture-of-Experts for Time Series Forecasting

Flames: Multi-Scale Mamba with Adaptive Fourier Filters and Laplace Transform for Time Series Forecasting

CrossSparse-MoE: Adaptive Sparsity and Cross-Channel Expert Routing for Time Series Forecasting

AdaKAN: Kolmogorov-Arnold Networks with Adaptive Spectral Decomposition for Time Series Forecasting