Uni-LaViRA: Language-Vision-Robot Actions Translation for Unified Embodied Navigation
Published in arXiv preprint, 2026
| Project page | Code | arXiv |
Uni-LaViRA extends the LaViRA translation paradigm into a unified agentic framework for embodied navigation. It covers VLN-CE, ObjectNav, EQA, and Aerial-VLN in a zero-shot manner across heterogeneous robots.
Recommended citation: Hongyu Ding, Sizhuo Zhang, Ziming Xu, Jinwen Guo, Hongxiu Liu, Xingzhi Cheng, Zixuan Chen, Haifei Qi, Duo Wang, Hao Xu, Jieqi Shi, Yifan Zhang, Jing Huo, Jian Cheng, Yang Gao, and Jiebo Luo. "Uni-LaViRA: Language-Vision-Robot Actions Translation for Unified Embodied Navigation." arXiv preprint arXiv:2605.27582, 2026.
Download Paper