@misc{unitime,
        title={Universal Video Temporal Grounding with Generative Multi-modal Large Language Models},
        author={Zeqian Li and Shangzhe Di and Zhonghua Zhai and Weilin Huang and Yanfeng Wang and Weidi Xie},
        year={2025},
        eprint={2506.18883},
        archivePrefix={arXiv},
        primaryClass={cs.CV}
    }