Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning 事件

Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning arXiv:2605.27318v1 Announce Type: new Abstract: Video spatial reasoning requires accumulating viewpoint-dependent evidence over time while retaining information useful to the question being asked. Existing spatial video-language models improve geometric perception and long-range context modeling, but often treat memory as a generic temporal cache, which can introduce redundant or irrelevant geometry and weaken long-horizon r