Yanxiao Liu(刘延骁)
 |
Yanxiao Liu |
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.
Research
My research lies at the intersection of network information theory and trustworthy machine learning. I develop new information-theoretic techniques and apply them to problems in modern AI, including distributed learning, generative-model samplinge, LLM watermarking, and algorithmic properties. I am always happy to explore new ideas and collaborations, so please feel free to reach out.
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)
Invited Talks
27 Oct 2026, Invited Talk at Eindhoven University of Technology
28 Aug 2026, Invited Talk at Global Young Scholars’ Forum, The Chinese University of Hong Kong (Shenzhen)
13 May 2026, Invited Talk at University of Cambridge: Change of Measure Inequalities
1 April 2026, Imprial College London IPC Lab: Information-Theoretic Generalization Error Bounds
14 June 2025, Invited Talk at The Chinese University of Hong Kong (Shenzhen) NCLab: [Info Bottleneck Channels and Lossy Compression]
29 November 2024, CUHK CSE&IE: Universal Exact Compression of Differentially Private Mechanisms
12 November 2024, CUHK CSE&IE: One-Shot Information Hiding
27 June 2024, CUHK CSE&IE: One-Shot Coding over General Noisy Networks
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)
News
Aug 2026: I'm invited to give a talk at the Global Young Scholars’ Forum, The Chinese University of Hong Kong (Shenzhen).
Aug 2026: We prove the Marton's Inner Bound is NOT optimal for broadcast channels, see our paper.
July 2026: I present our work on Generalization Error of DP Algorithms at ISIT 2026.
May 2026: I present our work on Private Data Compression via Diffusion in CITC 2026 at University of Cambridge.
May 2026: I am invited to give a talk about Change of Measure Inequalities at Information Theory Seminar, University of Cambridge.
Apr 2026: One paper on Nonasymptotic IB Channel has been accepted to IEEE Transactions on Information Theory.
Mar 2026: One paper on Generalization Error of DP Algorithms has been accepted to ISIT 2026, see you in Guangzhou.
Feb 2026: Presented our work on Joint Scheduling and Multiflow Maximization in Wireless Networks at IZS 2026.
Aug 2025: One paper on One-Shot Coding has been accepted by IEEE Transactions on Information Theory.
Jun 2025: I passed my Ph.D. oral defense, see my [Thesis Page].