@inproceedings{seo2026visual,
  title={Visual Grounding First, Multimodal In-context Learning Follows},
  author={Seo, Minhyuk and Lee, Minjae and Lee, Chaeeun and Lin, Wei and Mirza, Muhammad Jehanzeb and Tuytelaars, Tinne and Choi, Jonghyun},
  booktitle={Advances in Neural Information Processing Systems},
  year={2026}
}
