AINeutralarXiv – CS AI · 6h ago6/10
🧠
Inside the Latent Flow: Causal Deciphering of Attention Dynamics in Audio Separation Foundation Models
Researchers have developed a causal analysis framework to understand how attention mechanisms work in SAM Audio, a flow-matching transformer for audio separation. The study reveals a dual-pathway conditioning system and proposes Layer-Selective Attention Caching (LSAC), a training-free optimization technique that reduces computational overhead by ~25% while maintaining audio quality.