@article{whennumbersspeakaligningtextualnumeralsa,
  title = {When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models},
  author = {Zhengyang Sun and Yu Chen and Xin Zhou and Xiaofan Li and Xiwu Chen and Dingkang Liang and Xiang Bai},
  year = {2026},
  eprint = {2604.08546},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.08546},
}