@article{enhancingperceptioncapabilitiesof,
  title = {Enhancing Perception Capabilities of Multimodal LLMs with Training-Free Fusion},
  author = {Zhuokun Chen and Jinwu Hu and Zeshuai Deng and Yufeng Wang and Bohan Zhuang and Mingkui Tan},
  year = {2024},
  eprint = {2412.01289},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.01289v2},
}