Rosetta: Composable Native Multimodal Pretraining

@misc{liu2026rosetta,
  title = {Rosetta: Composable Native Multimodal Pretraining},
  author = {Xiangyue Liu and Zijian Zhang and Miles Yang and Zhao Zhong and Liefeng Bo and Ping Tan},
  year = {2026},
  eprint = {2607.00293},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.00293},
}