@article{mmfusermultimodalmultilayerfeaturefuser,
  title = {MMFuser: Multimodal Multi-Layer Feature Fuser for Fine-Grained Vision-Language Understanding},
  author = {Yue Cao and Yangzhou Liu and Zhe Chen and Guangchen Shi and Wenhai Wang and Danhuai Zhao and Tong Lu},
  year = {2024},
  eprint = {2410.11829},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.11829v1},
}