Tianyang Wang

MoRAM for Multi-Step and Multivariate Short-Term Wind-Power Forecasting: A Reproducibility Audit and Corrected Attention Ablation

This study presents a reproducibility and implementation audit of MoRAM, an integrated architecture that combines feature-token attention, a residual Mamba layer, dense two-expert blending, and a one-dimensional convolution–linear residual output path to forecast 12 h of normalized turbine power from 48 h multivariate...