I am currently a PhD student of the Hong Kong Polytechnic University (PolyU), supervised by Prof. Kit Lun Yick in AiDLAB and Prof. Bo Yang. Before that, I was a machine learning engineer at XiaoMi Inc. I received my Master’s degree from the Department of Computer Science, Beijing Jiaotong University, under the supervision of Prof. Jing Wang.

I closely collaborate with Guofeng Mei (FBK), Chenhan Jiang (HKUST) and Qi Zhang (UvA).

My research interests include:

3D Shape Matching 3D Vision-Language Models 3D Segmentation 3D Generation

News

• [02/2026]: One paper on universal 3D shape matching is accepted to CVPR 2026!

Work Experience

Research Assistant, The Hong Kong Polytechnic University

Hong Kong

Apr. 2023 – Sep. 2023

Machine Learning Engineer, XiaoMi Inc.

Beijing, China

2021 – 2023

Publications

^* denotes equal contribution; co-first author names swap order automatically.

arXiv 2026

Articulating then Matching: Zero-Shot Shape Matching for Uncurated Data

Qilong Liu^*Qinfeng Xiao^*Chenyuan YiLiying ZhangKit-lun Yick

arXiv, 2026.

Paper

CVPR 2026

Universal 3D Shape Matching via Coarse-to-Fine Language Guidance

Qinfeng Xiao^*Guofeng Mei^*Bo YangLiying ZhangJian ZhangKit-lun Yick

The IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026.

Paper

arXiv 2025

Parameter-Efficient CLIP Adaptation for 3D Understanding via Unified Tokenization

Guofeng Mei^*Qinfeng Xiao^*Bin RenLuigi RizJuan LiuXiaoshui HuangXu ZhengNicu SebeMing-Hsuan YangFabio Poiesi

arXiv, 2025.

Paper

IEEE SPL 2021

CoSleep: A Multi-view Representation Learning Framework for Self-Supervised Learning of Sleep Stage Classification

Jianan Ye^*Qinfeng Xiao^*

IEEE Signal Processing Letters, 2021.

Paper Code

ICASSP 2021

Self-Supervised Learning for Sleep Stage Classification with Predictive and Discriminative Contrastive Coding

Qinfeng Xiao

The International Conference on Acoustics, Speech, & Signal Processing, 2021.

Paper Code