@article{hyvilmenhancingfinegrainedrecognition,
  title = {HyViLM: Enhancing Fine-Grained Recognition with a Hybrid Encoder for Vision-Language Models},
  author = {Shiding Zhu and Wenhui Dong and Jun Song and Yingbo Wang and Yanan Guo and Bo Zheng},
  year = {2024},
  eprint = {2412.08378},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.08378v2},
}