LongSpace: Exploring Long-Horizon Spatial Memory from Perception to Recall in Video 事件

LongSpace: Exploring Long-Horizon Spatial Memory from Perception to Recall in Video arXiv:2606.05677v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have advanced image and video understanding and can increasingly handle longer visual inputs. Long-horizon tasks such as autonomous driving and robotic navigation require more than recognizing the current view, as models must remember and retrieve previously observed spatial layouts, routes, viewpoint changes, and object sta