@inproceedings{vilaonpretrainingforvisuallanguage,
  title = {VILA: On Pre-training for Visual 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 = {2023},
  booktitle = {CVPR 2024 1},
  eprint = {2312.07533},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2312.07533v4},
}