@article{gemvgtowardsgeneralizedmultiimagevisualg,
  title = {GeM-VG: Towards Generalized Multi-image Visual Grounding with Multimodal Large Language Models},
  author = {Shurong Zheng and Yousong Zhu and Hongyin Zhao and Fan Yang and Yufei Zhan and Ming Tang and Jinqiao Wang},
  year = {2026},
  eprint = {2601.04777},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.04777},
}