V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models

ArXi:2509.14837v2 Announce Type: replace Recent advances in causal interpretability have extended from language models to vision-language models (VLMs), seeking to reveal their internal mechanisms through input interventions. While textual interventions often target semantics, visual interventions typically rely on coarse pixel-level perturbations, limiting semantic insights on multimodal integration. In this study, we