@article{xiaoicetrainingfreevideounderstandingvia,
  title = {Xiaoice: Training-Free Video Understanding via Self-Supervised Spatio-Temporal Clustering of Semantic Features},
  author = {Shihao Ji and Zihui Song},
  year = {2025},
  eprint = {2510.16781},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.16781},
}