AI RESEARCH
Mechanisms of Object Localization in Vision-Language Models
arXiv CS.CV
•
ArXi:2605.19792v1 Announce Type: new Visually-grounded language models (VLMs) are highly effective in linking visual and textual information, yet they often struggle with basic classification and localization tasks. While classification mechanisms have been studied extensively, the processes that object localization remain poorly understood. In this work, we investigate two representative families, LLaVA-1.5 and InternVL-3.5, using a suite of mechanistic interpretability tools, including token ablations, attention knockout, and causal mediation analysis.