Scholar
Qingyan Bai
Google Scholar ID: xUMjxi4AAAAJ
The Hong Kong University of Science and Technology
Citations & Impact
Citations
465
H-index
7
i10-index
5
Publications
10
Co-authors
11
list available
Publications
Resume (English only)
Academic Achievements
- - Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset (Preprint, 2025)
- - Edicho: Consistent Image Editing in the Wild (ICCV 2025)
- - Real-time 3D-aware Portrait Editing from a Single Image (ECCV 2024)
- - CoDeF: Content Deformation Fields for Temporally Consistent Video Processing (CVPR 2024, Highlight Paper)
- - GLeaD: Improving GANs with A Generator-Leading Task (CVPR 2023)
- - Revisiting the Evaluation of Image Synthesis with GANs (NeurIPS 2023)
- - High-fidelity GAN Inversion with Padding Space (ECCV 2022)
- - One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN (ECCV 2022)
- - Region-adaptive Deformable Network for Image Quality Assessment (CVPR 2021 NTIRE Workshop)
- - Academic Excellence Award, HKUST
- - Outstanding Graduate of Beijing
- - First-Class Scholarship for Outstanding Students, Tsinghua University
- - National Scholarship, Twice (2017 & 2018)
Research Experience
- - Research Intern, AntGroup, working on Generative Models (Jul. 2022 - now)
- - Research Intern, Bytedance, working on Generative Models (Sep. 2021 - Apr. 2022)
Education
- - PhD student in Computer Science and Engineering at The Hong Kong University of Science and Technology (HKUST), supervised by Prof. Qifeng Chen
- - Master's degree at Tsinghua University, supervised by Prof. Yujiu Yang
Background
- Research interests include generative models and agents.
Miscellany
- Reviewer for CVPR, ECCV, ICCV, ICLR, NeurIPS
