作者位次 #6/8ACL 2026Findings· Findings of ACL
C o V : Chain-of-View Prompting for Spatial Reasoning
Haoyu Zhao · Akide Liu · Zeyu Zhang · Weijie Wang · Feng Chen · Ruihan Zhu · Gholamreza Haffari · Bohan Zhuang
摘要
Embodied question answering (EQA) in 3D environments often requires collecting context that is distributed across multiple viewpoints and partially occluded. However, most recent vision–language models (VLMs) are constrained to a fixed and finite set of input views, which limits their ability to...