Yihao Zhi
2 papers · Latest:
Computer Vision
ReImagine: Rethinking Controllable High-Quality Human Video Generation via Image-First Synthesis
ReImagine proposes an image-first approach for controllable, high-quality human video generation, decoupling appearance from temporal consistency.
2604.19720
Computer VisionOmni123: Exploring 3D Native Foundation Models with Limited 3D Data by Unifying Text to 2D and 3D Generation
Omni123 is a 3D-native foundation model that unifies text-to-2D and 3D generation, leveraging 2D data to improve 3D representations despite limited 3D data.
2604.02289
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.