Correctable Landmark Discovery via Large Models for Vision-Language Navigation

1 code implementation • 29 May 2024 • Bingqian Lin, Yunshuang Nie, Ziming Wei, Yi Zhu, Hang Xu, Shikui Ma, Jianzhuang Liu, Xiaodan Liang

To mitigate the noise in the priors due to the lack of visual constraints, we introduce a learnable cooccurrence scoring module, which corrects the importance of each cooccurrence according to actual observations for accurate landmark discovery.

NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning

1 code implementation • 12 Mar 2024 • Bingqian Lin, Yunshuang Nie, Ziming Wei, Jiaqi Chen, Shikui Ma, Jianhua Han, Hang Xu, Xiaojun Chang, Xiaodan Liang

Vision-and-Language Navigation (VLN), as a crucial research problem of Embodied AI, requires an embodied agent to navigate through complex 3D environments following natural language instructions.

Navigate Vision and Language Navigation