Multimodal Function Vectors for Visual Relations 事件

Multimodal Function Vectors for Visual Relations arXiv:2510.02528v2 Announce Type: replace Abstract: Large Multimodal Models (LMMs) demonstrate impressive in-context learning abilities from few multimodal demonstrations, yet the internal mechanisms supporting such task learning remain opaque. Building on prior work of Large Language Models, we show that a small subset of attention heads in Large Multimodal Models is responsible for transmitting representations of visual relations. The activatio