@article{imagerefvlenablingcontextualimage,
  title = {ImageRef-VL: Enabling Contextual Image Referencing in Vision-Language Models},
  author = {Jingwei Yi and Junhao Yin and Ju Xu and Peng Bao and Yongliang Wang and Wei Fan and Hao Wang},
  year = {2025},
  eprint = {2501.12418},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2501.12418v1},
}