Home
About me
Research
Publications
Teaching
Thesis

Yanxiao Liu(刘延骁)

alt text 

Yanxiao Liu
Postdoctoral Research Associate
Department of Electrical and Electronic Engineering
Imperial College London
Email 1: y.liu2 [at] imperial.ac.uk
Email 2: yanxiaoliu [at] link.cuhk.edu.hk
[CV]

About me

I am currently a postdoctoral research associate at Imperial College London, working with Professor Deniz Gündüz in Information Processing and Communications Lab.

I received my Ph.D. degree from The Chinese University of Hong Kong in 2025, advised by Professor Cheuk Ting Li and Professor Raymond W. Yeung.

I was a visiting scholar in Stanford University, ISL Lab, from January 2024 to June 2024, hosted by Professor Ayfer Özgür and supported by CUHK PhD IMPAC Award 2023–24.

I received my B.Eng. degree in Electronic Information Engineering and minor degree in Philosophy from The Chinese University of Hong Kong (Shenzhen) in 2021, advised by Professor Shenghao Yang.

Research

My research interests lie at the intersection of information theory, machine learning, and privacy. I develop novel techniques for non-asymptotic information theory, and I apply these techniques in various fields of artificial intelligence, including distributed machine learning, sampling problems, LLM inference, LLM watermarking, and generalization performance characterization of learning algorithms. I am always passionate about any form of collaboration and am happy to help or learn new things, so please feel free to contact me.

Awards

  • CIEIT Best Paper Award (2025) (中国电子学会信息论年会学术论文奖) [paper]

  • CUHK PhD International Mobility for Partnerships and Collaborations Award (2024) (CUHK PhD IMPAC Award 2024).

  • NeurIPS Scholar Award (2024)

  • ISIT Travel Award (2024)

Service

Award:

  • Top Reviewer for NeurIPS 2025 (≈8%)

TPC member:

  • IEEE GLOBECOM 2026

Session chair:

  • Information Theory Workshop (ITW) 2024

Reviewer:

  • Annual Conference on Neural Information Processing Systems (NeurIPS 2025, 2026)

  • Association for the Advancement of Artificial Intelligence (AAAI 2027)

  • IEEE Transactions on Information Theory (TIT)

  • IEEE Transactions on Automatic Control (TAC)

  • IEEE Transactions on Mobine Computing (TMC)

  • IEEE Transactions on Knowledge and Data Engineering (TKDE)

  • IEEE Journal on Selected Areas in Communications (JSAC)

  • IEEE International Symposium on Information Theory (ISIT)

  • IEEE International Conference on Communications (ICC)

  • IEEE Global Communications Conference (GLOBECOM)

  • IEEE Information Theory Workshop (ITW)

  • Data Compression Conference (DCC)

  • IMA International Conference on Cryptography and Coding

  • Northern Lights Deep Learning Conference (NLDL)

Invited Talks

  • 28 Aug 2026, Invited Talk: Global Young Scholars’ Forum, The Chinese University of Hong Kong (Shenzhen)

  • 13 May 2026, Invited Talk: Information Theory Seminar, University of Cambridge: A Unified Framework for Change of Measure Inequalities

  • 1 April 2026, Imprial College London IPC Lab: Information-Theoretic Generalization Error Bounds via Data Processing Inequality and Typicality

  • 14 June 2025, Invited Talk: Chinese University of Hong Kong (Shenzhen) NCLab: Nonasymptotic Oblivious Relaying and Variable-Length Noisy Lossy Source Coding

  • 2024 Information Theory Workshop (ITW), Shenzhen, China

  • 2024 IEEE International Symposium on Information Theory (ISIT), Athens, Greece

  • 29 November 2024, CUHK CSE&IE Theory Talk: Universal Exact Compression of Differentially Private Mechanisms

  • 12 November 2024, CUHK CSE&IE Theory Talk: One-Shot Information Hiding

  • 27 June 2024, CUHK CSE&IE Theory Talk: One-Shot Coding over General Noisy Networks

  • 17 March 2023, CUHK CSE&IE Theory Talk: Maximal Clique Enumeration in Periodic Graphs

  • 11 November 2022, CUHK CSE&IE Theory Talk: Coding Over Sets for DNA Storage

  • 12 October 2021, CUHK CSE&IE Theory Talk: Wireless Link Scheduling with Propagation Delays

News