JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation
Official implementation for "JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation" is coming in october.
If you find JanusVLN is useful in your research or applications, please consider giving us a star 🌟 and citing it by the following BibTeX entry.
@article{zeng2025janusvln,
title={JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation},
author={Zeng, Shuang and Qi, Dekang and Chang, Xinyuan and Xiong, Feng and Xie, Shichao and Wu, Xiaolong and Liang, Shiyi and Xu, Mu and Wei, Xing},
journal={arXiv preprint arXiv:2509.22548},
year={2025}
}
This project is licensed under the MIT License.