arXiv:2606.10046v2 Announce Type: replace-cross Abstract: Flow-matching transformers achieve strong audio separation, yet their attention dynamics are opaque. We adapt established causal-intervention principles into a deterministic, inference-time probing protocol for SAM Audio. Orthogonal probing uncovers a dual-pathway text-conditioning...
Les hele artikkelen hos kilden.
Kommentarer (0)
Ingen kommentarer ennå. Bli den første til å kommentere!