@article{concertojoint2d3dselfsupervisedlearninge,
  title = {Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations},
  author = {Yujia Zhang and Xiaoyang Wu and Yixing Lao and Chengyao Wang and Zhuotao Tian and Naiyan Wang and Hengshuang Zhao},
  year = {2025},
  eprint = {2510.23607},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.23607},
}