Youxuan Fang

Unveiling Multimodal Processing: Exploring Activation Patterns in Multimodal LLMs for Interpretability and Efficiency

Recent Multimodal Large Language Models (MLLMs) have achieved remarkable advancements, yet their internal mechanisms for concurrently processing diverse modalities like text, image, and audio remain largely opaque. In this paper, we propose a methodology to convert dense MLLMs into fine-grained Mixt