@article{tdbenchbenchmarkingvisionlanguagemodels,
  title = {TDBench: Benchmarking Vision-Language Models in Understanding Top-Down Images},
  author = {Kaiyuan Hou and Minghui Zhao and Lilin Xu and Yuang Fan and Xiaofan Jiang},
  year = {2025},
  eprint = {2504.03748},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.03748v1},
}