@article{griffonv2advancingmultimodalperception, title = {Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring}, author = {Yufei Zhan and Yousong Zhu and Hongyin Zhao and Fan Yang and Ming Tang and Jinqiao Wang}, year = {2024}, eprint = {2403.09333}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2403.09333v1}, }