@article{vlm4dtowardsspatiotemporalawarenessinvis,
  title = {VLM4D: Towards Spatiotemporal Awareness in Vision Language Models},
  author = {Shijie Zhou and Alexander Vilesov and Xuehai He and Ziyu Wan and Shuwang Zhang and Aditya Nagachandra and Di Chang and Dongdong Chen and Xin Eric Wang and Achuta Kadambi},
  year = {2025},
  eprint = {2508.02095},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.02095},
}