Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads

arXiv:2606.05843v1 Announce Type: cross 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...

Læs hele artiklen hos kilden.