@article{worldbageluncoveringthepowerofunifiedmul,
  title = {WorldBagel: Uncovering the Power of Unified Multimodal Models for Vision-Language-Action-World Modeling},
  author = {Zelin Zhao and Min Shi and Bo Yuan and Haotian Xue and Jialuo Li and Lama Moukheiber and Humphrey Shi and Yongxin Chen},
  year = {2026},
  eprint = {2607.03461},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.03461},
}