@article{convllavahierarchicalbackbonesasvisual,
  title = {ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models},
  author = {Chunjiang Ge and Sijie Cheng and ZiMing Wang and Jiale Yuan and Yuan Gao and Jun Song and Shiji Song and Gao Huang and Bo Zheng},
  year = {2024},
  eprint = {2405.15738},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.15738v1},
}