@misc{chen2025jepa,
  title={VL-JEPA: Joint Embedding Predictive Architecture for Vision-language},
  author={Delong Chen and Mustafa Shukor and Theo Moutakanni and Willy Chung and Jade Yu and Tejaswi Kasarla and Allen Bolourchi and Yann LeCun and Pascale Fung},
  year={2025},
  eprint={2512.10942},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2512.10942}
}