@article{mavenaneffectivemultigranularityhybrid,
  title = {MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model},
  author = {Chaoya Jiang and Jia Hongrui and Haiyang Xu and Wei Ye and Mengfan Dong and Ming Yan and Ji Zhang and Fei Huang and Shikun Zhang},
  year = {2024},
  eprint = {2408.12321},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2408.12321v2},
}