AIBearisharXiv – CS AI · Apr 66/10
🧠
Do Audio-Visual Large Language Models Really See and Hear?
A new research study reveals that Audio-Visual Large Language Models (AVLLMs) exhibit a fundamental bias toward visual information over audio when the modalities conflict. The research shows that while these models encode rich audio semantics in intermediate layers, visual representations dominate during the final text generation phase, indicating limited effectiveness of current multimodal AI training approaches.