@article{li2025universal,
  title={Universal Video Temporal Grounding with Generative Multi-modal Large Language Models},
  author={Li, Zeqian and Di, Shangzhe and Zhai, Zhonghua and Huang, Weilin and Wang, Yanfeng and Xie, Weidi},
  journal={arXiv preprint arXiv:2506.18883},
  year={2025}
}