@inproceedings{lin2024vila,
  title = {{VILA}: {O}n pretraining for vision language models},
  author = {Ji Lin and Hongxu Yin and Wei Ping and Yao Lu and Pavlo Molchanov and Andrew Tao and Huizi Mao and Jan Kautz and Mohammad Shoeybi and Song Han},
  year = {2024},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2312.07533},
  archiveprefix = {arxiv},
}