ActiveVLN is a Vision-and-Language Navigation (VLN) framework designed to enable active exploration through multi-turn reinforcement learning. Unlike traditional VLN methods, which rely on imitation ...
Official code for the CVPR 2026 paper: Bridging the 2D-3D Gap: A Hierarchical Semantic-Geometric Map for Vision Language Navigation Kailing Li, Tianwen Qian, Lijin Yang, Yuqian Fu, Jingyu Gong, ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results