Min Zhao (赵敏)

I am a postdoctoral researcher at Tsinghua University, working under the supervision of Prof. Jun Zhu. I have collaborated closely with Prof. Chongxuan Li and Dr. Fan Bao. I received my Ph.D. degree from Chinese Academy of Sciences Institute of Automation, advised by Prof. Jing Sui and Prof. Shan Yu. Before that, I received my B.S. degree from Beijing Institute of Technology in 2019.

My research interests include AIGC, with a particular focus on image, video, and 3D generation using diffusion models. Feel free to connect with me for research collaborations or discussions related to the above topics.

Email / Google Scholar / GitHub / 小红书 / 笔记

News

[2025.09] 🎉 Our paper FlexWorld, which expands 3D Scenes for flexiable-View synthesis, is accepted by NeurIPS 2025.
[2025.05] 🎉 Our paper RIFLEx, which extends video with just one line of code, has been accepted by ICML 2025. It now supports various models including HunyuanVideo, CogVideoX, and Wan2.1, extending video lengths from 5-6 s to 10-12 s.
[2024.09] 🎉 One paper: Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model is accepted by NeurIPS 2024.
[2024.07] 🎉 One paper: PoseCrafter is accepted by ECCV 2024.
[2024.05] 🎉 Our text-to-video model Vidu, which produces 16s clips with 1080p and is similar to Sora, has been published.
[2023.01] 🎉 One paper: EEGSDE is accepted by ICLR 2023.
[2022.09] 🎉 One paper: EGSDE is accepted by NeurIPs 2022.

Selected Publications

	FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesis Luxi Chen, Zihan Zhou, Min Zhao, Yikai Wang, Ge Zhang, Wenhao Huang, Hao Sun, Ji-Rong Wen, Chongxuan Li NeurIPS 2025 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
	PoseCrafter: One-Shot Personalized Video Synthesis Following Flexible Poses Yong Zhong, Min Zhao, Zebin You, Xiaofeng Yu, Changwang Zhang, Chongxuan Li ECCV 2024 Paper / Website
	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 Arixv Paper / Website
	Controlvideo: Adding conditional control for one shot text-to-video editing Min Zhao, Rongzhen Wang, Fan Bao, Chongxuan Li, Jun Zhu Science China Information Sciences 2024 Paper / Code / Website / Zhihu
	Equivariant Energy-Guided SDE for Inverse Molecular Design Fan Bao, Min Zhao, Zhongkai Hao, Peiyao Li, Chongxuan Li, Jun Zhu ICLR 2023 Paper / Code / Poster / Slides
	EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations Min Zhao, Fan Bao, Chongxuan Li, Jun Zhu NeurIPS 2022 Paper / Code / Talk / Poster / Slides
	An attention-based hybrid deep learning framework integrating brain connectivity and activity of resting-state functional MRI data Min Zhao, Weizheng Yan, Na Luo, Dongmei Zhi, Zening Fu, Yuhui Du, Shan Yu, Tianzi Jiang, Vince D. Calhoun, Jing Sui Medical Image Analysis Paper /
	Mapping relationships among schizophrenia, bipolar and schizoaffective disorders: A deep classification and clustering framework using fMRI time series Weizheng Yan, Min Zhao, Godfrey D. Pearlson, Jing Sui, Vince D. Calhoun Schizophrenia Research Paper /
	An attention-based hybrid deep learning framework integrating temporal coherence and dynamics for discriminating schizophrenia Min Zhao, Weizheng Yan, Rongtao Xu, Dongmei Zhi, Rongtao Jiang, Tianzi Jiang, Vince D. Calhoun, Jing Sui IEEE ISBI 2021, Best student paper nomination Paper /