I'm currently a fourth-year Ph.D. student at the University of Hong Kong, advised by Prof. Xiaojuan Qi. Before that, I obtained my B.Eng. degree (Ranked 3/153, GPA 3.95/4.0 or 91.25/100) in Automation at Zhejiang University (2021) supervised by Prof. Yong Liu, and I was also at Chu Kochen Honors College's mixed class.

My research interest lies in the wild areas of artificial intelligence and computer vision, with a focus on data-centric/efficient learning (e.g. synthetic/generative data, mixing multi-modal data, and semi-supervised learning) for computer vision tasks. During my Ph.D. study, I have been fortunate to intern at ByteDance AI Lab, advised by Song Bai.

I'm currently seeking full-time opportunities starting in Summer 2025, please feel free to reach out if you have any openings!

• Learn More

Selected Publication

Is synthetic data from generative models ready for image recognition?

Ruifei He, Shuyang Sun, Xin Yu, Chuhui Xue, Wenqing Zhang, Philip Torr, Song Bai, Xiaojuan Qi.

International Conference on Learning Representations (ICLR), 2023.

Spotlight

[paper] [code]

Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability.

Ruifei He, Shuyang Sun, Jihan Yang, Song Bai, Xiaojuan Qi.

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.

[paper] [code]

Re-distributing Biased Pseudo Labels in Self-training for Semi-supervised Semantic Segmentation.

Ruifei He, Jihan Yang, Xiaojuan Qi.

IEEE International Conference on Computer Vision (ICCV), 2021.

Oral (3.4% acceptance rate)

[paper] [code]

Multi-Modal Controllable Video-to-Audio Generation.

Ruifei He, Chuhui Xue, Wenqing Zhang, Yingchen Yu, Zhengzhe Liu, Song Bai, Xiaojuan Qi.

Under review, 2024.

MC-MoE: Mixture Compressor for Mixture-of-Experts LLMs Gains More.

Wei Huang, Yue Liao, Jianhui Liu, Ruifei He, Haoru Tan, Shiming Zhang, Hongsheng Li, Si Liu, Xiaojuan Qi.

Under review, 2024.

[paper]

Debiasing Text-to-Image Diffusion Models.

Ruifei He, Chuhui Xue, Haoru Tan, Wenqing Zhang, Yingchen Yu, Song Bai, Xiaojuan Qi.

Proceedings of the 1st ACM Multimedia Workshop on Multi-modal Misinformation Governance in the Era of Foundation Models
(ACM MM Workshop), 2024.

[paper]

Vertical Layering of Quantized Neural Networks for Heterogeneous Inference.

Hai Wu, Ruifei He, Haoru Tan, Xiaojuan Qi, Kaibin Huang.

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023.

[paper]

LUMix: Improving Mixup by Better Modelling Label Uncertainty.

Shuyang Sun, Jie-Neng Chen, Ruifei He, Alan Yuille, Philip Torr, Song Bai.

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022.

[paper] [code]

Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation.

Liang Liu, Jiangning Zhang, Ruifei He, Yong Liu, Yabiao Wang, Ying Tai, Donghao Luo, Chengjie Wang, Jilin Li, Feiyue Huang.

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

[paper] [code]

Research on artificial intelligence algorithm of edge computing.

Co-work with Zizhang Li and Jintao Lu

[report] [slides]

Teaching Assistant

Undergraduate Course Projects

These projects mainly represent my undergraduate work.

VROOM: Interactive rendering virtual environment with binocular vision.

Course Project, CS 21120970 Mixed Reality, 2019 Winter. Instructor: Prof. Hujun Bao

[demo] [code]

Eigenface: face recognition and rebuild using Eigenvalue decomposition.

Course Project, CS 21191070 Computer Vision, 2019 Winter. Instructor: Prof. Mingli Song

[code]

Research on where to build charging stations and the quantity of charging piles.

Co-work with Jintao Lu and Yuheng Zha

Course Project, EE 68190140 Mathematical Modeling & Simulating, 2019 Spring. Instructor: Prof. Jian Chen

[report] [slides]

Robot Navigation: Augmented A* with feedback control.

Co-work with Anqiao Li

Course Project, EE 86120080 Robotics, 2019 Fall. Instructor: Prof. Rong Xiong

[demo] [code]

News!