Hongzhou Zhu (朱泓舟)

My research interest includes generative models such as diffusion models, and their applications in (video) world models.

News

[2024.09] 🎉 One paper: UltraViCo: Breaking Extrapolation Limits in Video Diffusion Transformers is accepted by ICLR 2026 as a poster.
[2024.09] 🎉 One paper: RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers is accepted by ICML 2025 as a poster.
[2024.09] 🎉 One paper: Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model is accepted by NeurIPS 2024 as a poster.
[2024.05] 🎉 Our text-to-video model Vidu, which produces 16s clips with 1080p and is similar to Sora, has been published.

Publications (* indicates equal contribution and † indicates correspondence.)

	Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation Hongzhou Zhu, Min Zhao, Guande He, Chongxuan Li, Jun Zhu † Arxiv Paper / Website / Code
	UltraViCo: Breaking Extrapolation Limits in Video Diffusion Transformers Min Zhao , Hongzhou Zhu , Yingze Wang, Bokai Yan, Jintao Zhang, Guande He, Ling Yang, Chongxuan Li Jun Zhu † ICLR 2026 Paper / Website / Code
	RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers Min Zhao, Guande He, Yixiao Chen, Hongzhou Zhu, Chongxuan Li †, Jun Zhu † ICML 2025 Paper / Website / Code
	Identifying and Solving Conditional Image Leakage in Image to-Video Generation Min Zhao, Hongzhou Zhu, Chendong Xiang, Kaiwen Zheng, Chongxuan Li †, Jun Zhu † NeurIPS 2024 Paper / Website / Code /
	Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models Fan Bao, Chendong Xiang, Gang Yue, Guande He, Hongzhou Zhu, Kaiwen Zheng, Min Zhao, Shilong Liu, Yaole Wang, Jun Zhu † Arxiv Paper / Website