Qingyan Bai

Hi! I am a third-year PhD student in Computer Science and Engineering at The Hong Kong University of Science and Technology (HKUST), supervised by Prof. Qifeng Chen. I received my master's degree at Tsinghua University in IIGroup, supervised by Prof. Yujiu Yang. My research interests include generative models and agents.

Email / Github / Google Scholar

Research (* indicates equal contribution. Please click the images/videos to zoom in.)
	LingBot-World: Advancing Open-source World Models Technical Report 2026 Paper / Project Page
	Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset , , , , , , , , , , , , Preprint 2025 Paper / Project Page
	The World is Your Canvas: Painting Promptable Events with Reference Images, Trajectories, and Text , , , , , , , , , , , , , , Preprint 2025 Paper / Project Page
	Edicho: Consistent Image Editing in the Wild , , , , , , , ICCV 2025 Paper / Project Page
	Real-time 3D-aware Portrait Editing from a Single Image , , , , , , , , , ECCV 2024 Paper / Project Page
	CoDeF: Content Deformation Fields for Temporally Consistent Video Processing , , , , , , , , CVPR 2024 (Highlight Paper) Paper / Project Page
	GLeaD: Improving GANs with A Generator-Leading Task , , , , , CVPR 2023 Paper / Project Page
	Revisiting the Evaluation of Image Synthesis with GANs , , , , , NeurIPS 2023 (D&B) Paper
	High-fidelity GAN Inversion with Padding Space , , , , , ECCV 2022 Paper / Project Page
	One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN , , , , , , , , , ECCV 2022 Paper / Project Page
	Region-adaptive Deformable Network for Image Quality Assessment , , , , , , CVPR 2021 NTIRE Workshop Paper