@article{fromseeingtopredictingavisionlanguagefra,
  title = {From Seeing to Predicting: A Vision-Language Framework for Trajectory Forecasting and Controlled Video Generation},
  author = {Fan Yang and Zhiyang Chen and Yousong Zhu and Xin Li and Jinqiao Wang},
  year = {2025},
  eprint = {2510.00806},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.00806},
}