Yanhong Zeng is currently a researcher at Shanghai AI Laboratory . Before that, she obtained her computer science Ph.D. degree in the joint doctoral program between Sun Yat-sen University and Microsoft Research Asia (MSRA) in 2022, supervised by Prof. Hongyang Chao and Dr. Baining Guo . Her research interests is generative AI (AIGC), specifically in controllable multimodal (e.g., text, pixels, audio) generation and image/video editing. I am super into the real-word applications and studies of generative AI. I'm open to all kinds of chats, communication, and collaboration.
wechat/discord/gmail/x: zengyh1900 CV / Email / Google Scholar / Twitter / Github / Linkedin 🎉 HumanVid is accepted by NeurIPS 2024 (D&B Track).

[2024.09] 🎉 MotionBooth is accepted by NeurIPS 2024 (Spotlight).

[2024.07] 🎉 PowerPaint is accepted by ECCV 2024.

[2024.03] 🎉 PIA and Make-it-Vivid are accepted by CVPR 2024.

[2024.02] 🔥 Our technology has been shipped in the animation series "Poems of Timeless Acclaim" , which is broadcasted in over 10 languages and on more than 70 mainstream media platforms overseas. It has reached an audience of nearly 100 million worldwide viewers within two weeks.

[2024.01] 🔥 We release MagicMaker , an AI platform that supports image generation, editing and animation! Live2Diff: Live Stream Translation via Uni-directional Attention in Video Diffusion Models Zhening Xing , Gereon Fox , Yanhong Zeng , Xingang Pan , Mohamed Elgharib , KChristian Theobalt , Kai Chen Arxiv , 2024 project page / video / arXiv / demo / Live2Diff is the first attempt that enables uni-directional attention modeling to video diffusion models for live video steam processing, and achieves 16FPS on RTX 4090 GPU. A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting Junhao Zhuang , Yanhong Zeng , Wenran Liu , Chun Yuan , Kai Chen ECCV , 2024 project page / video / arXiv / demo / PowerPaint is the first versatile inpainting model that achieves SOTA in text-guided and shape-guided object inpainting, object removal, outpainting, etc. Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions Yanhong Zeng* , Hongwei Xue* , Tiankai Hang* , Yuchong Sun* , Bei Liu , Huan Yang , Jianlong Fu , Baining Guo CVPR , 2022 arXiv / video /

We collect a large dataset which is the first high-resolution dataset including 371.5k hours of 720p videos and the most diversified dataset covering 15 popular YouTube categories.

Tutorial Talk (ICCV 2023): MMagic: Multimodal Advanced, Generative and Intelligent Creation

Tutorial Talk (CVPR 2023): Learning to Generate, Edit, and Enhance Images and Videos with MMagic

Invited Talk: Towards High-Quality Image Inpainting ( Microsoft China Video Center on Bilibili Live 2019 )

Award: ICML 2022 Outstanding Reviewer.

Award: National Scholarship in 2021 (Top 1% in SYSU).

Award: Outstanding Undergraduate Thesis in 2017.

Award: Outstanding Undergraduate in 2017.

Award: National Scholarship in 2016 (Top 1% in SYSU).

Award: First Prize Excellence Scholarship in 2013, 2014, 2015.