Zuhao Liu

PhD Student, Imperial College London

Email / Google Scholar / CV / Github

554 Huxley Building, 180 Queen's Gate, South Kensington, London SW7 2AZ

About me

I'm a PhD student at Imperial College London, supervised by Tolga Birdal, and working together with Riza Alp Guler. I am passionate about AI research that benefits humanity. My current research focuses on 3D vision and robotics, with broader interests in generative models, video understanding, and world models. I am a big fan of Yoshua Bengio.

Previously, I worked as a Machine Learning Engineer at ByteDance, where I optimized user experience and developed models that significantly reduced customer complaint rates, impacting hundreds of millions of users.

Before that, I was a research intern at INSAIT, working on video generation with Luc Van Gool and Danda Paudel. I received my Master's degree from Sun Yat-sen University, where I was fortunate to be advised by Wei-Shi Zheng on video understanding research. I also interned at Intelligent Driving Group (IDG) of Baidu, and NetEase Games AI Lab.

Outside of work, I love hiking and mountaineering. I enjoy bouldering and the gym. I am also an activist committed to protecting our planet from global warming.

Selected Publications

InTraGen: Trajectory-controlled Video Generation for Object Interactions
Zuhao Liu*, Aleksandar Yanev*, Ahmad Mahmood, Ivan Nikolov, Saman Motamed, Wei-Shi Zheng, Xi Wang, Luc Van Gool, Danda Pani Paudel
arXiv

PDF / arXiv / Code

General image-to-image translation with one-shot image guidance
Zuhao Liu*, Bin Cheng*, Yunbo Peng, Yue Lin
ICCV 2023

PDF / arXiv / Code

Generating anomalies for video anomaly detection with prompt-based feature mapping
Zuhao Liu, Xiao-Ming Wu, Dian Zheng, Kun-Yu Lin, Wei-Shi Zheng
CVPR 2023

PDF

Tree Image

Estimator meets equilibrium perspective: A rectified straight through estimator for binary neural networks training
Xiao-Ming Wu, Dian Zheng, Zuhao Liu, Wei-Shi Zheng
ICCV 2023



PDF / arXiv / Code

Tree Image

Diffuvolume: Diffusion model for volume based stereo matching
Dian Zheng, Xiao-Ming Wu, Zuhao Liu, Jingke Meng, Wei-shi Zheng
IJCV

PDF / arXiv / Code

NAS-SCAM: Neural architecture search-based spatial and channel joint attention module for nuclei semantic segmentation and classification
Zuhao Liu*,Huan Wang*, Shaoting Zhang, Guotai Wang, Jin Qi
MICCAI 2020

PDF / Code

Tree Image