AdaLoop: Adaptive-Depth Latent Reasoning for Audio Language Models

Excerpt

arXiv:2610.06949v1 Announce Type: cross Abstract: Large audio language models answer questions about speech, sound, and music, yet their accuracy drops sharply on tasks that need fine-grained acoustic analysis. Judging which of two speakers has the higher pitch demands iterative signal-level reasoning that a content question does not. Current models spend the same computational depth on both. We introduce AdaLoop, a lightweight recurrent module that learns how many latent refinement steps a give