Author name: Qidong Wang, Junjie Hu, Ming Jiang

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

Qidong Wang, Junjie Hu, Ming Jiang / April 28, 2026

arXiv:2509.14837v2 Announce Type: replace
Abstract: 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 …

cs.CL, cs.CV

From Heads to Neurons: Causal Attribution and Steering in Multi-Task Vision-Language Models

Qidong Wang, Junjie Hu, Ming Jiang / April 21, 2026

arXiv:2604.17941v1 Announce Type: cross
Abstract: Recent work has increasingly explored neuron-level interpretation in vision-language models (VLMs) to identify neurons critical to final predictions. However, existing neuron analyses generally focus o…