@article{fromdensepredictiontovisualeditingstruct,
  title = {From Dense Prediction to Visual Editing: Structured Supervision for Unified Image and Video Creation},
  author = {Zhefan Rao and Bin Zou and Xuanhua He and Chong Hou Choi and Yanheng Li and Rui Liu and Haoxuan Che and Qifeng Chen},
  year = {2026},
  eprint = {2608.14740},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.14740},
}