Preprint
Aug 2026
What Makes a Good Layer? Assessing the Layer-Wise Intrinsic Properties of Music Foundation Models
Music foundation models are commonly used as frozen audio feature extractors, yet selecting which layer to extract from remains largely heuristic. Current practice defaults to fixed depths or multi-layer fusion, with limited understanding of why certain layers transfer better across downstream tasks or how representati...
Angelos-Nikolaos Kanatas, Yuexuan Kong, Pablo Alonso-Jiménez et al.
· 0 citations