@inproceedings{bai2026vlm3d,
    title={Let Language Constrain Geometry: Vision-Language Models as Semantic and Spatial Critics for 3D Generation},
    author={Weimin Bai and Yubo Li and Weijian Luo and Zeqiang Lai and Yequan Wang and Wenzheng Chen and He Sun},
    booktitle={Proceedings of the International Conference on Machine Learning (ICML)},
    year={2026},
    eprint={2511.14271},
    archivePrefix={arXiv},
    primaryClass={cs.CV},
    url={https://arxiv.org/abs/2511.14271},
}