@inproceedings{ijcai2024p0093,
  title     = {Why Only Text: Empowering Vision-and-Language Navigation with Multi-modal Prompts},
  author    = {Hong, Haodong and Wang, Sen and Huang, Zi and Wu, Qi and Liu, Jiajun},
  booktitle = {Proceedings of the Thirty-Third International Joint Conference on
               Artificial Intelligence, {IJCAI-24}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Kate Larson},
  pages     = {839--847},
  year      = {2024},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2024/93},
  url       = {https://doi.org/10.24963/ijcai.2024/93},
}