AI RESEARCH
Do MLLMs Understand Pointing? Benchmarking and Enhancing Referential Reasoning in Egocentric Vision
arXiv CS.CV
•
ArXi:2604.21461v1 Announce Type: new Egocentric AI agents, such as smart glasses, rely on pointing gestures to resolve referential ambiguities in natural language commands. However, despite advancements in Multimodal Large Language Models (MLLMs), current systems often fail to precisely ground the spatial semantics of pointing. Instead, they rely on spurious correlations with visual proximity or object saliency, a phenomenon we term "Referential Hallucination." To address this gap, we