Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads 事件

Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads arXiv:2606.05843v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) demonstrate remarkable proficiency on complex vision-language tasks, the mechanisms by which they extract query-relevant visual features from complex, noisy contexts remain opaque. In this paper, we present an in-depth interpretability study that uncovers a profound structural property within MLLMs: functional sparsity in