Hi, I am Hongyang Du ( 杜泓阳 )
I am an assistant professor at the Department of Electrical and Electronic Engineering, the University of Hong Kong (HKU). I received my Ph.D. degree from Nanyang Technological University, Singapore, and my B.Eng. degree from Beijing Jiaotong University, China. I am the Principal Investigator (PI) of the Network Intelligence and Computing Ecosystem (NICE) Lab @ HKU.
In response to the evolving era of artificial intelligence and next-generation networks, we identify the following research projects in NICE:
TOWARD UBIQUITOUS INTELLIGENCE
NETWORK FOR AI × AI FOR NETWORK
Users
Wireless Links
Radio Access
Core
Applications
Ubiquitous Intelligent Systems
Embedded intelligence in large-scale environments
Smart Cities
& Environments
& Environments
Autonomous
Industrial Systems
Industrial Systems
Self-Organizing
Integration
Integration
Real-world
Service Intelligence
Service Intelligence
Networked AI Infrastructure
Collaboration across agents, humans, and networks
Multi-Agent
Cooperation
Cooperation
LLM Agents
& Operations
& Operations
Human–Computer
Interaction
Interaction
Distributed
Decision Making
Decision Making
Algorithmic Intelligence Foundation
Fundamental AI modeling, training, and inference
Optimization
Algorithms
Algorithms
Generative &
Representation Learning
Representation Learning
Efficient
Inference
Inference
Model
Robustness
Robustness
These projects cover two complementary directions:
- Network for AI - Unfold Intelligence by Horizontally Scaling It Across the Network
- AI for Network - Specialize Intelligence by Vertically Optimizing It for Network Systems
They converge toward a unified goal: "Ubiquitous Intelligence, where intelligence is woven into every interaction, every environment, and every moment."
Given the shift in our research style starting in 2025, our methodology and focus have changed. To align with our current vision, you may check our work established from 2025 onwards. Please refer to NICE for openings, research opportunities, and application details.
Research Projects
Networked AI Infrastructure: Co-Design of Networks and Large-Scale AI Systems
We treat the network as the execution and scaling infrastructure for AI services, e.g., LLMs, and co-design communication & computing under real network constraints.
 |
 | 2. NetMCP: Network-Aware Model Context Protocol Platform for LLM Capability Extension Enhan Li, Hongyang Du*, Kaibin Huang 2025 🔗 Testing intelligence under real networks. A platform for testing and developing MCP tool routing algorithms with real-time awareness of network and server conditions.  PDF |
 | 3. JAUNT: Joint Alignment of User Intent and Network State for QoE-centric LLM Tool Routing Enhan Li, Hongyang Du* 2025 🚶 Intent travels through the network. We propose the JAUNT framework, which achieves dual-view alignment between semantic intent and network performance for LLM tool routing. PDF |
 | 4. Ubiquitous Intelligence Via Wireless Network-Driven LLMs Evolution Xingkun Yin, Feiran You, Hongyang Du*, Kaibin Huang Nature npj Wireless Technology, 2025 🧬 When networks breathe, intelligence grows. We introduce ubiquitous intelligence as a paradigm where LLMs evolve within wireless network-driven ecosystems. PDF |
 | 5. JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services Feiran You, Hongyang Du*, Kaibin Huang, Abbas Jamalipour submitted to IEEE Transactions on Mobile Computing, major revision, 2025 ⚙️ Less to send, more to think. JPPO++ is a framework that jointly optimizes prompt compression and wireless transmission power for mobile LLM services. A denoising-inspired compression scheme performs iterative prompt refinement by progressively removing less informative tokens. PDF |
Net-Spatial Intelligence: Learning and Reasoning in Urban Ecosystems
We model and exploit spatial structure from heterogeneous sensing and mobility signals to support prediction, planning, and control in city-scale wireless ecosystems.
 | 1. U-MASK: User-adaptive Spatio-Temporal Masking for Personalized Mobile AI Applications NEWShiyuan Zhang, Yilai Liu, Yuwei Du, Ruoxuan Yang, Dong In Kim, Hongyang Du* Submitted A user-adaptive spatiotemporal masking method that allocates evidence budgets based on user reliability and task sensitivity. PDF |
 | 2. LSDM: LLM-Enhanced Spatio-temporal Diffusion Model for Service-Level Mobile Traffic Prediction Shiyuan Zhang, Tong Li*, Zhu Xiao, Hongyang Du*, Kaibin Huang submitted to IEEE/ACM Transactions on Networking, major revision, 2025 🗺️ Your traffic tells a story. An LLM-Enhanced Spatio-temporal Diffusion Model (LSDM) to achieve SOTA service-level mobile traffic prediction for individual users. PDF |  Code |
Agentic Intelligence: Reliable Task-Oriented AI Systems
We design mechanisms that make agentic systems reliably executable, using verification, memory realignment, and experience reuse to stabilize long-horizon task completion.
 |
 | 2. Experience Scaling: Post-Deployment Evolution For Large Language Models Xingkun Yin, Kaibin Huang, Dong In Kim, Hongyang Du* 2025 📑 The learning never stops. We propose experience scaling, a framework for continuous post-deployment evolution for LLMs through autonomous interaction with the environment and collaborative sharing of accumulated experience. PDF |
 | 3. MAD-SPEAR: A Conformity-Driven Prompt Injection Attack on Multi-Agent Debate Systems Yu Cui, Hongyang Du* 2025 🎭 Corrupt few, conform all. We introduce MAD-SPEAR, a targeted prompt injection attack that compromises a small subset of agents but significantly disrupts the overall multi-agent debate (MAD) process. PDF |
 | 4. Reinforcement Learning With LLMs Interaction For Distributed Diffusion Model Services Hongyang Du, et al IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025 A novel user-centric Interactive AI approach for service management, with a distributed GDM-based AIGC framework that emphasizes efficient and cooperative deployment. PDF | Code |
Resilient Intelligence: Intelligent Networks across Complex Scenarios
We develop learning and reasoning mechanisms that remain stable and effective under sparse feedback, high-dimensional decision spaces, and harsh or non-stationary conditions.
 | 1. ReaCritic: Large Reasoning Transformer-based DRL Critic-model Scaling For Heterogeneous Networks Feiran You, Hongyang Du* submitted to IEEE Transactions on Mobile Computing, major revision, 2025 🤔 Learning without thought is labor lost. 学而不思则罔。 ReaCritic is a large reasoning transformer-based DRL critic-model scaling scheme that brings LLMs' reasoning ability into DRL, performing horizontal reasoning over parallel state-action inputs and vertical reasoning through deep transformer stacks. PDF |
 | 2. DRESS: Diffusion Reasoning-based Reward Shaping Scheme For Intelligent Networks Feiran You, Hongyang Du*, Xiangwang Hou, Yong Ren, Kaibin Huang IEEE Transactions on Signal Processing, 2025 🥼 If your DRL is a mess, DRESS it! DRESS is designed for seamless integration with any DRL framework, allowing DRESS-aided DRL (DRESSed-DRL) to enable stable and efficient DRL training even under extreme network environments. PDF | Code |
 | 3. Diffusion-based Reinforcement Learning for Edge-enabled AI-Generated Content Services Hongyang Du, et al IEEE Transactions on Mobile Computing, 2024 We propose a diffusion model-based AI-generated optimal decision (AGOD) algorithm, which can generate the optimal ASP selection decisions. Highlight: ESI highly cited paper · ESI hot cited paper PDF | Code |
 | 4. Attention-aware Resource Allocation and QoE Analysis for Metaverse xURLLC Services Hongyang Du, et al IEEE Journal on Selected Areas in Communications, 2023 An attention-aware rendering capacity allocation scheme to improve QoE in xURLLC. Highlight: Selected by IEEE JSAC Popular Documents - July 2023 · First Price of Outstanding Papers of Computer Academy of Guangdong (China) PDF | Code |
 | 5. Semantic Communications for Wireless Sensing: RIS-aided Encoding and Self-supervised Decoding Hongyang Du, et al IEEE Journal on Selected Areas in Communications, 2023 We propose the inverse semantic communications as a new paradigm. Using the sensing data collected from real-world, we show that our framework can reduce the data volume by 95%. Highlight: Selected by IEEE JSAC Popular Documents - August 2023 PDF | Code |
 | 6. AI-Generated Incentive Mechanism and Full-Duplex Semantic Communications for Information Sharing Hongyang Du, et al IEEE Journal on Selected Areas in Communications, 2023 To facilitate semantic information sharing among users, we design a contract theoretic AI-generated incentive mechanism that generates the optimal contract design. Highlight: Selected by IEEE JSAC Popular Documents - October 2023 PDF | Code |
News
- [Nov/2025] I served as the Local Chair of The 2nd ACM Workshop on Open and AI RAN in conjunction with Mobicom 2025.
- [Aug/2025] I am happy to participate in the IEEE/CIC International Conference on Communications in China and deliver tutorial 1, "TUT-1: Toward Artificial General Intelligent (AGI)-Driven Communications with Generative AI and Large Language Models".
- [Apr/2025] I am invited to deliver Lecture 5, Generative Diffusion Model with Its Applications, for the Communication-Specific Large AI Models Master Class organized by Chaspark.
- [Mar/2025] We organize a workshop "Embracing Generative AI towards 6G RAN" in the 2025 IEEE 102nd Vehicular Technology Conference VTC2025-Fall in Chengdu, China, October 19–22, 2025.
- [Feb/2025] We organize a workshop "Multi-modal and Generative Semantic Communications Towards Cloud-Edge-End Intelligence" in the 2025 IEEE 101st Vehicular Technology Conference VTC2025-Spring, Norway, 17–20 June 2025.
- [Jan/2025] I am honored to join as an Associate Editor for the Intelligent Communications: Modelling, Operation and Digital Twin track of IEEE Communications Surveys & Tutorials (IEEE COMST). I am eager to contribute to advancing research in this field.
- [Jan/2025] As the corresponding author, I am happy that our paper "Supervised Score-Based Modeling by Gradient Boosting" has been accepted to the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25). See you in Philadelphia, Pennsylvania.
- [Jan/2025] I am honored to join as an Associate Editor for the Big Data and Machine Learning for Communications track of IEEE Open Journal of the Communications Society (IEEE OJ-COMS). I look forward to serving the research community in this role.
- [Dec/2024] I am honored to join as an Associate Editor for the Machine Learning and Communications track of IEEE Transactions on Communications (IEEE TCOM). I look forward to serving our research community and advancing the field in this new role.
- [Dec/2024] I am honored to receive the IEEE ComSoc Best Young Professional Award in the "Best Early Career" category for the contributions to the integration of Generative AI with communication networks.
More News
- [Dec/2024] Our paper "Blockchain-Aided Secure Semantic Communication for AI-Generated Content in Metaverse" has been awarded the 2023 Best Paper Award from IEEE Open Journal of the Computer Society by the IEEE Computer Society Publications Board.
- [Nov/2024] I am invited as a keynote speaker at the International Conference on the Next Generation Intelligent Networks, organized by Xijiao Institute for Cyber Science and Technology.
- [Nov/2024] Our project "Gaiety: Generative AI-empowered Edge Hub for Accessible and Immersive Meta-Home" received an Honorary Mention in the 2024 ComSoc Student Competition "Communications Technology Changing the World".
- [Oct/2024] Our paper "DIsFU: Protecting Innocent Clients in Federated Unlearning" has been awarded the Best Paper Award in International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP).
- [Sept/2024] I am honored to join as an Associate Editor for the Wireless Networks and Mobile Services track of IEEE Transactions on Vehicular Technology (TVT) and am excited to contribute to our community in this capacity.
- [Aug/2024] I have accepted a Letter of Appointment from the University of Hong Kong (HKU) as an Assistant Professor in the Department of Electrical and Electronic Engineering (EEE). I look forward to contributing to cutting-edge research and collaborating with distinguished colleagues and talented students.
- [July/2024] I am honored to receive the NTU Graduate College's Research Excellence Award.
- [Jun/2024] Our paper, "Mixture of Experts for Intelligent Networks: A Large Language Model-enabled Approach", was selected for the Best Paper Award in International Wireless Communications & Mobile Computing Conference (IWCMC), Ayia Napa, Cyprus, 27–31 May 2024.
- [Apr/2024] We will organize a workshop "Empowering Wireless Communications and Networking with Generative AI" in IEEE/CIC International Conference on Communications in China (ICCC 2024), welcome to submit papers.
- [Mar/2024] We will give a tutorial "Generative Artificial Intelligence-empowered Networks: Optimization and Applications" in IEEE/CIC International Conference on Communications in China (ICCC 2024), welcome to participate.
- [Dec/2023] I am honored to receive the Singapore Data Science Consortium (SDSC) Dissertation Research Fellowship.
- [Dec/2023] My two projects got the FIRST PRIZE and SECOND PRIZE in the 2024 ComSoc Social Network Technical Committee (SNTC) Student Competition, respectively. We will give presentations in IEEE ICC 2024. See you in Denver, CO, USA.
- [Nov/2023] Our project, "Artificial Intelligence-driven Eyewear: Keys to Metaverse" received an Honorary Mention in the 2023 ComSoc Student Competition "Communications Technology Changing the World." As the team leader, I am happy to witness our project to be recognized as one of the top 16 projects globally.
- [Jun/2023] It is a great honour to have been invited by Queen Mary University of London to give a talk about Exploring the Role of Generative AI in Wireless Networks: Applications, Optimization, and Challenges.
- [May/2023] I am delighted to be invited by the Future Network of Intelligence Institute in The Chinese University of Hong Kong-Shenzhen to give a talk about Generative AI in Intelligent Networks. The slides are available here.
- [Apr/2023] I had the pleasure of visiting University of Technology Sydney, University of Sydney, and University of New South Wales in Australia. Relaxing days.
- [Dec/2022] I visited Sungkyunkwan University in Korea, hosted by Prof. Dong In Kim. It was a memorable month.
- [Nov/2022] I am honored to receive the IEEE Daniel E. Nobel Fellowship Award (One person each year).
- [Jan/2022] I am honored to be recognized as the Exemplary Reviewer of the IEEE TCOM, 2021.
Selected Recognitions
- IEEE ComSoc Best Young Professional Award for Best Early Career Researcher
- Only six persons are selected globally each year; only one person is selected for the Best Early Career Researcher category.
- IEEE Daniel E. Nobel Fellowship Award
- Only one person is selected globally each year.
- IEEE Signal Processing Society Scholarship
- Singapore Data Science Consortium (SDSC) Dissertation Research Fellowship
- Only ten people are selected in Singapore each year.
- Best Paper Award, IEEE Open Journal of the Computer Society
- Best Paper Award, IWCMC 2024 Conference
- May 27–31, 2024.
- Exemplary Editor, IEEE Open Journal of the Communications Society
- Exemplary Reviewer, IEEE Transactions on Communications
- Exemplary Reviewer, IEEE Communications Letters
Selected Academic Services
- Associate Editor, IEEE Communications Surveys & Tutorials (Impact Factor: 34.4) (2025–)
- Associate Editor, IEEE Open Journal of the Communications Society (Impact Factor: 6.3) (2025–)
- Associate Editor, IEEE Transactions on Communications (Impact Factor: 7.7) (2024–)
- Associate Editor, IEEE Transactions on Vehicular Technology (Impact Factor: 6.8) (2024–)
- Guest Editor, IEEE Vehicular Technology Magazine, "Integrating Generative AI into Future Internet of Vehicles (IoV)", 2024
- Local Chair, Open and AI RAN Workshop with ACM MobiCom, 2025
- Assistant to the Editor-in Chief, IEEE Communications Surveys & Tutorials (2022–2024)
- Workshop Co-chair, "Empowering Wireless Communications and Networking with Generative AI" in IEEE ICCC 2024
- Contributor, "IEEE ComSoc Best Readings in Generative AI and Large Language Models for Networking"
- Senior Program Committee: The Fortieth AAAI Conference on Artificial Intelligence (AAAI-26)
- Reviewer: ICLR, TPAMI, COMST, JSAC, TMC, TSP, TWC, TIFS, TCOM, TVT, WCM, IoTJ, Network, WCL, CL, and more.
Teaching
- ELEC3342 Digital system design, Fall 2025
- ELEC3846 Numerical methods and optimization, Spring 2025, Spring 2026
- SC1005 Digital Logic, Fall 2023
- SC2103 Digital Systems Design, Spring 2023
- CE3006 Digital Communications, Fall 2022
"Life does not always go your way. Looking back will not bring joy. Dreams may fade, but what you hold now is real. Do not waste the moonlit night; raise your cup and treasure those beside you."
“生活中有很多的不如意，如果一不开心，就寄希望于当初，那你永远不会开心。
幻境再美终是梦，珍惜眼前始为真，莫使金樽空对月，举杯幸会有缘人。”---------《武林外传》