T16 – Trustworthy and Efficient Generative AI and Pretrained LLMs for Next-Generation Communications

Co-organizer: Dusit Niyato, Nanyang Technological University, Singapore
Co-organizer: Yijing Lin, Beijing University of Posts and Telecommunications, Beijing, China
Co-organizer:  Jiacheng Wang, Nanyang Technological University, Singapore
Co-organizer: Ruichen Zhang, Nanyang Technological University, Singapore

Abstract: This tutorial aims to explore the intersection of generative artificial intelligence (AI), large language models (LLMs), and next-generation communication networks such as 6G, Semantic
Communication, and ISAC. As generative AI technologies become increasingly central to intelligent networking, ensuring their trustworthiness and efficiency is of paramount importance. The tutorial is
structured into six focused modules. It begins with the use of generative diffusion models as autonomous network planners, highlighting their ability to guide scheduling, routing, and resource
optimization through reinforcement learning. Next, we explore the role of generative AI in integrated sensing and actuation for ISAC systems, emphasizing multimodal signal synthesis and communication-perception co-design. A central highlight of the tutorial is unlearning in pretrained LLMs, where we present recent advances in removing sensitive or outdated knowledge via fine-tuning removal, black-box unlearning, and federated collaboration. It can address both privacy and compliance in adaptive communication environments. We also discuss hallucination in LLM-generated outputs, an increasingly relevant challenge in Telecom applications, and introduce mitigation techniques spanning both model-side fine-tuning and system-level optimization using mobile-edge architectures. In addition, we examine scalable deployment strategies for LLMs in resource-constrained mobile and edge networks, presenting compression techniques and performance metrics validated by real-world case studies. This tutorial is ideal for researchers, engineers, and practitioners seeking to develop and deploy trustworthy and efficient generative AI models in modern communication infrastructures.

Co-organizer’s Bios:

Dusit Niyato

Dusit Niyato is a professor in the College of Computing & Data Science, at Nanyang Technological University, Singapore. He received Ph.D. in Electrical and Computer Engineering from the University of Manitoba, Canada. Dusit’s research interests are in the areas of sustainability, edge intelligence, decentralized machine learning, and incentive mechanism design. Dusit won the IEEE
Communications Society (ComSoc) Best Survey Paper Award, IEEE Asia-Pacific Board (APB) Outstanding Paper Award, the IEEE Computer Society Middle Career Researcher Award for Excellence in Scalable Computing and Distinguished Technical Achievement Recognition Award of IEEE ComSoc Technical Committee on Green Communications and Computing. Dusit also won a number of best paper awards including IEEE Wireless Communications and Networking Conference (WCNC), IEEE International Conference on Communications (ICC), IEEE ComSoc Communication Systems Integration and Modelling Technical Committee and IEEE ComSoc Signal Processing and Computing for Communications Technical Committee 2021. Currently, Dusit is serving as Editor-in-Chief of IEEE Communications Surveys and Tutorials (impact factor of 35.6 for 2023), an area editor of IEEE Transactions on Vehicular Technology, editor of IEEE Transactions on Wireless Communications, associate editor of IEEE Internet of Things Journal, IEEE Transactions on Mobile Computing, IEEE Wireless Communications, IEEE Network, IEEE Transactions on In- formation Forensics and Security (TIFS), and ACM Computing Surveys. He was a guest editor of IEEE Journal on Selected Areas on Communications. He is the Members-at-Large to the Board of Governors for 2024-2026, and was a Distinguished Lecturer of the IEEE Communications Society for 2016-2017. He was named the 2017-2022 highly cited researcher in computer science. He is a Fellow of IEEE and a Fellow
of IET.

Yijing Lin

Yijing Lin is a postdoc researcher with the State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications (BUPT), where she received the Ph.D degree in 2024. She received the B.E. degree from North China Electric Power University (NCEPU) in 2019. From 2022 to 2023, she was a visiting researcher with College of Computing and Data Science, at Nanyang Technological University, Singapore. She has published more than 20 papers including WWW, IJCAI, IEEE TSC, TCOM, TNSE, TVT etc. Her publications include ESI highly cited papers, IEEE ComSoc Best Readings and received four Best Paper Awards including IEEE OJCS, IEEE IWCMC, IEEE-CCF Service Computing Technical Committee. Her current research interests include blockchain and data unlearning.

Jiacheng Wang

Jiacheng Wang received the M.S and Ph.D. degrees in the School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, in 2018 and 2022, respectively. From 2021 to 2022, he was a visiting researcher with College of Computing and Data Science, at Nanyang Technological University, Singapore, where he is now the Postdoc Research Fellow. His research interests include Generative AI, Integrated Sensing and Communications, Network Optimization, and Edge Intelligence. He has published more than 50 papers including IEEE JSAC, IEEE TMC, IEEE TWC, IEEE TCCN, IEEE TVT, IEEE CMOST, IEEE WCM, IEEE Network, IEEE WCL, IEEE GLOBECOM, IEEE ICC, and IEEE WCNC. He was a Guest Editor of IEEE Wireless Communications, Open Journal of the Communications Society, IEEE Internet of Things Magazine, and IEEE Networking Letters.

Ruichen Zhang

Ruichen Zhang received the B.E. degree from Henan University (HENU), China, in 2018, and the Ph.D. degree from Beijing Jiaotong University (BJTU), China, in 2023. He is currently a Post-Doctoral Research Fellow with the College of Computing and Data Science, Nanyang Technological University (NTU), Singapore. In 2024, he was a Visiting Scholar with the College of Information and Communication Engineering, Sungkyunkwan University, Suwon, South Korea. His research interests include the Internet of Agents, LLM-empowered networking, reinforcement learning-enabled wireless communication, generative AI models, and heterogeneous networks. He has published more than 40 papers including IEEE JSAC, IEEE TWC, IEEE TCOM, IEEE TCCN, IEEE TVT, IEEE CMOST, IEEE WCM, IEEE Transactions on Cognitive Communications and Networking, IEEE WCL, IEEE GLOBECOM, IEEE ICC, etc. He is the Managing Editor of IEEE Transactions on Network Science and Engineering (TNSE) from 2025.