In-Context Learning with Unpaired Clips for Instruction-based Video Editing
Published in arXiv preprint, 2025
A cost-effective pretraining method using unpaired video clips for instruction-based video editing, achieving 12% improvement in editing instruction following and 15% in editing quality.
Recommended citation: Xinyao Liao, Xianfang Zeng, Ziye Song, Zhoujie Fu, Gang Yu, Guosheng Lin. (2025). "In-Context Learning with Unpaired Clips for Instruction-based Video Editing." arXiv:2510.14648.
Download Paper