一作ACL 2026Findings· Findings of ACL
Do MLLM s Understand Pointing? Benchmarking and Enhancing Referential Reasoning in Egocentric Vision
Chentao Li · Zirui Gao · Mingze Gao · Yinglian Ren · Jianjiang Feng · Jie Zhou
摘要
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. Inst...