@article{mvtmaskgroundedvisionlanguagemodelsforta,
  title = {MVT: Mask-Grounded Vision-Language Models for Taxonomy-Aligned Land-Cover Tagging},
  author = {Siyi Chen and Kai Wang and Weicong Pang and Ruiming Yang and Ziru Chen and Renjun Gao and Alexis Kai Hon Lau and Dasa Gu and Chenchen Zhang and Cheng Li},
  year = {2025},
  eprint = {2509.18693},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.18693},
}