Multiscale POD of Transformer Attention Fields: Scale-Selective Analysis via Morlet Scalogram 事件

Multiscale POD of Transformer Attention Fields: Scale-Selective Analysis via Morlet Scalogram arXiv:2606.06573v1 Announce Type: cross Abstract: We introduce scale-selective Proper Orthogonal Decomposition (POD) for transformer attention fields, inspired by the use of POD for extracting energetically dominant modes from turbulent flow ensembles. The Morlet continuous wavelet transform identifies dominant temporal scales in the attention lag structure across a document ensemble; POD then extracts