@article{structxlipenhancingvisionlanguagemodelsw,
  title = {StructXLIP: Enhancing Vision-language Models with Multimodal Structural Cues},
  author = {Zanxi Ruan and Songqun Gao and Qiuyu Kong and Yiming Wang and Marco Cristani},
  year = {2026},
  eprint = {2602.20089},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.20089},
}