@article{locanymedvisionlanguagegroundingformulti,
  title = {LocAnyMed: Vision-Language Grounding for Multimodal Medical Images},
  author = {Zihan Wang and Tong Liu and Zhiwei Wang and Tao Huang and Wentao Jiang and Sihan Ma and Shanshan Ye and Xiaohui Yang and Jing Zhang},
  year = {2026},
  eprint = {2608.03322},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.03322},
}