About Me

Hi! I am a second-year M.Phil. student in Computer Science at the School of Data Science, The Chinese University of Hong Kong, Shenzhen, advised by Prof. Benyou Wang and Prof. Tom Ko. Prior to this, I received my bachelor's degree in Data Science and Big Data Technology from the Department of Mathematics, Harbin Institute of Technology, Shenzhen, in 2025, advised by Prof. Ho-Kin Tang and Prof. Jing Li. I also worked as a research assistant at Southern University of Science and Technology, advised by Prof. Hongxin Wei and Prof. Bingyi Jing. My research interests focus on multimodal understanding, generation, and interaction. I welcome collaboration, so please feel free to reach out.

I am currently seeking Ph.D. opportunities for Fall 2027 and research internship positions.

News

I attended CVPR 2026 in Denver and had a wonderful experience!

One first-author paper was accepted to CVPR 2026.

One paper was accepted to ICLR 2026.

One paper was accepted for publication in JMLR.

I started my M.Phil. studies at CUHK(SZ).

Experience

Papers

* Equal contribution † Corresponding author

Self-listening for full-duplex speech models overview Preprint

What Did I Just Say? Self-Listening for Full-Duplex Speech Models

Xuanning Zhou*, Junyi Ao*, Xiaotong Liu, Tom Ko†, Benyou Wang, and Haizhou Li

arXiv Code

We plan to release all training data and code upon acceptance of the paper.

SemiCP project poster CVPR 2026

Semi-Supervised Conformal Prediction With Unlabeled Nonconformity Score

Xuanning Zhou*, Zihao Shi*, Hao Zeng, Xiaobo Xia, Bingyi Jing, and Hongxin Wei†

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

arXiv Code

GraftLLM evaluation overview ICLR 2026

Knowledge Fusion of Large Language Models via Modular SkillPacks

Guodong Du, Zhuo Li, Xuanning Zhou, Junlin Li, Zesheng Shi, Wanyu Lin, Ho-Kin Tang, Xiucheng Li, Fangming Liu, Wenya Wang, Min Zhang, and Jing Li†

International Conference on Learning Representations (ICLR), 2026

arXiv Code

TorchCP component architecture JMLR

TorchCP: A Python Library for Conformal Prediction

Jianguo Huang, Jianqing Song, Xuanning Zhou, Bingyi Jing, and Hongxin Wei†

Journal of Machine Learning Research (JMLR), 2025

Page arXiv Code TorchCP GitHub star count

Awards & Honors

Service

Reviewer

  • I serve as a reviewer for AI research venues, including ACL Rolling Review (ARR) and CVPR.

Teaching Assistant

  • CSC4120: Design and Analysis of Algorithms, by Prof. Costas Courcoubetis, CUHK(SZ) (2026 Fall)
  • ORCA2500: Foundations of Data Science, by Prof. Eric Stratman, CUHK(SZ) & Columbia University (2026 Summer)
  • STA3020: Statistical Inference, by Prof. Jiasheng Shi, CUHK(SZ) (2026 Spring)
  • CSC4120: Design and Analysis of Algorithms, by Prof. Costas Courcoubetis, CUHK(SZ) (2025 Fall)
WeChat QR code for Xuanning Zhou