AG-REPA: Causal Layer Selection for Representation Alignment in Audio Flow Matching 事件

AG-REPA: Causal Layer Selection for Representation Alignment in Audio Flow Matching arXiv:2603.01006v2 Announce Type: replace-cross Abstract: REPresentation Alignment (REPA) improves the training of generative flow models by aligning intermediate hidden states with pretrained teacher features, but its effectiveness in token-conditioned audio Flow Matching critically depends on the choice of supervised layers, which is typically made heuristically based on the depth. In this work, we introduce A