Yue Gao

yuegao@cs.stanford.edu

My name is pronounced as yoo-eh.

I am an incoming PhD student in the Stanford Vision and Learning Lab, Department of Computer Science, at Stanford University. I've had a wonderful experience being advised by Prof. Jiajun Wu and Prof. Bo Zhu, and collaborating with Koven Yu.

Before Stanford, I worked as a researcher at Microsoft Research, where I focused on video generation and editing. I earned my M.S. with distinction in research, from Peking University, specializing in image generation under the supervision of Prof. Zhouhui Lian.

Dynamic Physical World Understanding and Prediction

My primary research interests lie in computer vision and computer graphics. Specifically, I aim to enable computers to understand and predict the physical world by integrating advanced algorithms, such as perception and generative models, with foundational knowledge from physics.

Publications

FluidNexus: 3D Fluid Reconstruction and Prediction from a Single Video
Yue Gao*, Hong-Xing Yu*, Bo Zhu, Jiajun Wu
Computer Vision and Pattern Recognition (CVPR), 2025
Oral Presentation

pdf / website / code

Implicit Motion Function
Yue Gao, Jiahao Li, Lei Chu, Yan Lu
Computer Vision and Pattern Recognition (CVPR), 2024

pdf / supp / website

High-Fidelity and Freely Controllable Talking Head Video Generation
Yue Gao, Yuan Zhou, Jinglu Wang, Xiao Li, Xiang Ming, Yan Lu
Computer Vision and Pattern Recognition (CVPR), 2023

arXiv / pdf / supp / website

Learning to Prompt for Open-Vocabulary Object Detection With Vision-Language Model
Yu Du, Fangyun Wei, Zihe Zhang, Miaojing Shi, Yue Gao, Guoqi Li.
Computer Vision and Pattern Recognition (CVPR), 2022

arXiv / code

Aligning Pretraining for Detection via Object-Level Contrastive Learning
Fangyun Wei*, Yue Gao*, Zhirong Wu, Han Hu, Stephen Lin
Advances in Neural Information Processing Systems (NeurIPS), 2021
Spotlight

arXiv / code

High-Fidelity and Arbitrary Face Editing
Yue Gao, Fangyun Wei, Jianmin Bao, Shuyang Gu, Dong Chen, Fang Wen, Prof. Zhouhui Lian†
Computer Vision and Pattern Recognition (CVPR), 2021

arXiv / website

Attribute2Font: Creating Fonts You Want From Attributes
Yizhi Wang*, Yue Gao*, Prof. Zhouhui Lian†
SIGGRAPH, ACM Transactions on Graphics (TOG), 2020

arXiv / code

Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning
Yue Gao*, Yuan Guo*, Prof. Zhouhui Lian†, Yingmin Tang, Jianguo Xiao
SIGGRAPH Asia, ACM Transactions on Graphics (TOG), 2019

arXiv / code

* Equal contribution; † Corresponding author

Dynamic Physical World Understanding and Prediction

Publications

Education

Stanford University

Peking University

Work

Microsoft Research

Microsoft Research

Apple AI/ML

Academic Service