VLM4D: Towards Spatiotemporal Awareness in Vision Language Models

@misc{chen2025vlm4dtowardsspatiotemporal,
      title={VLM4D: Towards Spatiotemporal Awareness in Vision Language Models},
      author={Dongdong Chen and Xuehai He and Xin Eric Wang and Ziyu Wan and Alexander Vilesov and Achuta Kadambi and Shijie Zhou and Di Chang and Shuwang Zhang and Aditya Nagachandra},
      year={2025},
      eprint={2508.02095},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2508.02095},
}