@article{instructionguidedfusionofmultilayer,
  title = {Instruction-Guided Fusion of Multi-Layer Visual Features in Large Vision-Language Models},
  author = {Xu Li and Yi Zheng and Haotian Chen and Xiaolei Chen and Yuxuan Liang and Chenghang Lai and Bin Li and xiangyang xue},
  year = {2024},
  eprint = {2501.08443},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2501.08443v3},
}