@article{mtamultimodaltaskalignmentforbev,
  title = {MTA: Multimodal Task Alignment for BEV Perception and Captioning},
  author = {Yunsheng Ma and Burhaneddin Yaman and Xin Ye and Feng Tao and Abhirup Mallik and Ziran Wang and Liu Ren},
  year = {2024},
  eprint = {2411.10639},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.10639v1},
}