AI RESEARCH
Probing Cross-modal Information Hubs in Audio-Visual LLMs
arXiv CS.AI
•
ArXi:2605.10815v1 Announce Type: new Audio-visual large language models (AVLLMs) have recently emerged as a powerful architecture capable of jointly reasoning over audio, visual, and textual modalities. In AVLLMs, the bidirectional interaction between audio and video modalities