Preprint
Sep 2026
Beyond Textual Chain-of-Thought: JEPA-Conditioned Latent Reasoning for Large Audio Language Models
Explicit textual Chain-of-Thought (CoT) has improved the reasoning ability of large audio language models (LALMs). However, textual CoTs are often constructed from text captions of audio and provide limited access to the acoustic evidence, which can introduce problems like hallucination. To address this modality-gap is...
Dong-Hang Wu, Hao-Yang Zhang, Yizhou Peng et al.
· 0 citations