@article{tipstextimagepretrainingwithspatial,
  title = {TIPS: Text-Image Pretraining with Spatial Awareness},
  author = {Kevis-Kokitsi Maninis and KaiFeng Chen and Soham Ghosh and Arjun Karpur and Koert Chen and Ye Xia and Bingyi Cao and Daniel Salz and Guangxing Han and Jan Dlabal and Dan Gnanapragasam and Mojtaba Seyedhosseini and Howard Zhou and Andre Araujo},
  year = {2024},
  eprint = {2410.16512},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.16512v1},
}