@article{efficientvisionlanguagemodelsby,
  title = {Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers},
  author = {Yuxin Wen and Qingqing Cao and Qichen Fu and Sachin Mehta and Mahyar Najibi},
  year = {2024},
  eprint = {2410.14072},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.14072v1},
}