@inproceedings{florencevlenhancingvisionlanguagemodels,
  title = {Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion},
  author = {Jiuhai Chen and Jianwei Yang and Haiping Wu and Dianqi Li and Jianfeng Gao and Tianyi Zhou and Bin Xiao},
  year = {2024},
  booktitle = {CVPR 2025 1},
  eprint = {2412.04424},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.04424v1},
}