@article{sceneversescaling3dvisionlanguage,
  title = {SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding},
  author = {Baoxiong Jia and Yixin Chen and Huangyue Yu and Yan Wang and Xuesong Niu and Tengyu Liu and Qing Li and Siyuan Huang},
  year = {2024},
  eprint = {2401.09340},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2401.09340v3},
}