2026ICML 2026
Exploring More to Solve More: Boosting Diversity in Text Diffusion Models via Entropy-Based Guidance
We propose a training-free Semantic-Aware Kernel Entropy (SAKE) guidance method for diffusion LLMs to enhance the reasoning ability.
PHYSICAL AI · WORLD MODELS
Haoyu Lei 雷浩瑀
HUAWEI · Intelligent Automotive Solution (IAS) BU
Autonomous Driving Solution (ADS) Research
I have joined HUAWEI’s Intelligent Automotive Solution (IAS) BU, Autonomous Driving Solution (ADS) Research Department at Oct 2026.
My research focuses on Physical AI Foundation Models for embodied AI and autonomous driving.
I received my Ph.D. in Computer Science and Engineering from The Chinese University of Hong Kong (CUHK) in July 2026, advised by Prof. Farzan Farnia. My research interests include diffusion-based generative models, machine learning theory, and trustworthy AI (Robustness, Fairness, and Interpretability).
I received my B.Sc. in Mathematics and Information Engineering, a double-major program at CUHK, as part of the ELITE Stream. I was fortunate to be advised by Prof. Chandra Nair and Prof. Anthony Man-Cho So.
Feel free to email me about internships or research collaborations!
News
2026.10
I have joined HUAWEI's IAS BU, ADS Research Department!
2026.07
I am honored to have graduated with a Ph.D. from the Department of Computer Science and Engineering at CUHK!
2026.03
Our paper is accepted by ICML 2026!
2026.03
Our paper is accepted by ISIT 2026!
2026.01
Our paper is honored to be selected by AAAI 2026 ML4Wireless Best Paper Award!
Earlier news (11)
2025.11
Two papers are accepted by AAAI 2026 & AAAI 2026 ML4Wireless!
2025.09
Two papers are accepted by NeurIPS 2025!
2025.07
Our paper is accepted by ACMMM 2025!
2025.06
Join Huawei Hong Kong Research Center, Theory Lab as a research intern!
2025.06
Honored to be selected as the Outstanding Intern in Noah's Ark Lab!
2025.01
Our paper is accepted by AAAI 2025 GenPlan Workshop (Spotlight)!
2025.01
Our paper is accepted by ICLR 2025!
2024.07
Join Huawei Noah's Ark Lab as a research intern!
2024.04
Our paper is accepted by UAI 2024!
2022.08
Start the journey as a Ph.D. student at CSE, CUHK!
2021.05
Our paper is accepted by ICASSP 2021!
Selected Publications
* Equal contribution
2026
2026ISIT 2026
On the Fragility of AI-Based Channel Decoders under Small Channel Perturbations
We theoretically and numerically study the lens of robustness to distributional shifts at the channel output.
2026AAAI 2026 ML4Wireless (Best Paper Award)
Syndrome-Flow Consistency Model Achieves One-step Denoising Error Correction Codes
We propose a highly-efficient 1-NFE consistency flow model for decoding tasks in Error Correction Codes with superior performance.
2026AAAI 2026
Boosting Generalization in Diffusion-Based Neural Combinatorial Solver via Inference Time Adaptation
We propose a general energy-guided sampling framework during inference time that enhances both the cross-scale and cross-problem generalization capabilities of diffusion-based NCO solvers without requiring additional training.
2025NeurIPS 2025
SPARKE: Scalable Prompt-Aware Diversity and Novelty Guidance in Diffusion Models via RKE Scores
We propose the Scalable Prompt-Aware Renyi Kernel Entropy Diversity Guidance (SPARKE) method to improve prompt-aware diversity in text-to-image diffusion models, allowing large-scale generation settings with linear inference computational overhead.
2025ICLR 2025
Boosting the visual interpretability of CLIP via adversarial fine-tuning
We propose an unsupervised adversarial fine-tuning (AFT) with norm-regularization to enhance the visual interpretability of CLIP.
2024UAI 2024
On the Inductive Biases of Demographic Parity-based Fair Learning Algorithms
We theoretically show that Inductive Biases widely exist in DP-based fair supervised learning algorithms, and further propose a distributionally robust optimization framework to mitigate the biases.
Education & Experience
Education
2022.08 - 2026.07 Hong Kong SAR
Ph.D. in Computer Science and Engineering Department, CUHK
2017.09 - 2022.07 Hong Kong SAR
Bachelor of Science in Mathematics and Information Engineering (double major), CUHK
Experience
2025.06 - 2026.01 Hong Kong SAR
Research intern, Huawei Hong Kong Research Center, Theory Lab
2024.07 - 2025.01 Shenzhen, China
Research intern, Huawei Noah's Ark Lab, Decision Making & Reasoning Group
2021.08 - 2022.04 Hong Kong SAR
Research Assistant, advised by Prof. Anthony MC So, Department of SEEM, CUHK
2020.08 - 2020.12 Hong Kong SAR
Research Assistant, advised by Prof. Anthony MC So, Department of SEEM, CUHK
Honors & Awards
2025
Huawei Noah's Ark Lab Outstanding Intern
2022
Postgraduate Studentship Scholarship Scheme
2021
Chung Chi College Departmental Prize (Graduation Top 10%)
2019 - 2021
Dean's List (Academic Year Top 10%)
2019 - 2021
Chung Chi College Class Scholarship (College Top 10%)
2019 - 2021
ELITE Stream Scholarship
Teaching
2025-26 Fall
AIST3010/ESTR3114 Numerical Optimization (Undergraduate)
2024-25 Spring
CSCI5130 Game Theory (Postgraduate)
2023-24 Spring
CSCI5030 Machine Learning Theory (Postgraduate)
2023-24 Fall
ENGG2760A Probability for Engineers (Undergraduate)
2022-23 Spring
ENGG1003SG Digital Literacy and Computational Thinking (Undergraduate)
2022-23 Fall
AIST3010 Numerical Optimization (Undergraduate)
Academic Service
ICML Golden Reviewer, ICML, NeurIPS, ICLR, AAAI, UAI, TMLR, ISIT Reviewer
Languages & Skills
Languages: English (Advanced), Cantonese (Intermediate), Putonghua (Native)
Programming Skills: Python (Main), Pytorch (Main), Matlab, R, C, C++, C#, LaTeX
Contact
Feel free to email me about internships or research collaborations!