Scholar
Min Zhao
Google Scholar ID: ExIZrLAAAAAJ
Tsinghua University
Citations & Impact
Citations
735
H-index
10
i10-index
10
Publications
13
Co-authors
8
list available
Publications
Resume (English only)
Academic Achievements
- Paper 'FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesis' accepted by NeurIPS 2025
- Paper 'RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers' accepted by ICML 2025; supports models like HunyuanVideo, CogVideoX, and Wan2.1, extending video length from 5–6s to 10–12s
- Paper 'Identifying and Solving Conditional Image Leakage in Image-to-Video Generation' accepted by NeurIPS 2024
- Paper 'PoseCrafter: One-Shot Personalized Video Synthesis Following Flexible Poses' accepted by ECCV 2024
- Co-developed text-to-video model Vidu, which generates 16-second 1080p clips with Sora-like performance (released May 2024)
- Paper 'Controlvideo: Adding conditional control for one shot text-to-video editing' published in Science China Information Sciences 2024
- Paper 'Equivariant Energy-Guided SDE for Inverse Molecular Design' accepted by ICLR 2023
- Paper 'EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations' accepted by NeurIPS 2022
- Authored a paper on an attention-based hybrid deep learning framework integrating brain connectivity and activity of resting-state fMRI data
