@article{datacompvlmimprovedopendatasetsforvision,
  title = {DataComp-VLM: Improved Open Datasets for Vision-Language Models},
  author = {Matteo Farina and Vishaal Udandarao and Thao Nguyen and Selim Kuzucu and Maximilian Böther and Andreas Hochlehnert and Adhiraj Ghosh and Marianna Nezhurina and Karsten Roth and Joschka Struber and Yuhui Zhang and Sebastian Dziadzio and Elaine Sui and Soumya Jahagirdar and Dhruba Ghosh and Hasan Hammoud and Thomas De Min and Simone Caldarella and Jehanzeb Mirza and Sedrick Keh and Mehdi Cherti and Hilde Kuehne and Bernt Schiele and Serena Yeung-Levy and Muhammad Ferjad Naeem and Federico Tombari and Ana Klimovic and Elisa Ricci and Matthias Bethge and Sewoong Oh and Ameya Prabhu and Alessio Tonioni and Jenia Jitsev and Massimiliano Mancini and Ludwig Schmidt and Nikhil Parthasarathy},
  year = {2026},
  eprint = {2606.28551},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.28551},
}