OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer ModelsQian He, Pengze Zhang, Zhuowei Chen et al.|arXiv (Cornell University)|2025Cited by 0
HuMo: Human-Centric Video Generation via Collaborative Multi-Modal ConditioningLiyang Chen, Zhiyong Wu, Tianxiang Ma et al.|arXiv (Cornell University)|2025Cited by 0