Prof. Ping Wang of York University

In this talk, I will present our recent work on enhancing the robustness and adaptability of deep learning-based semantic communication (SemCom) systems, which are increasingly vital for efficient next-generation wireless networks. Traditional SemCom approaches often struggle with wireless channel uncertainties, source data outliers, and poor generalization. To address these challenges, we propose a novel SemCom framework powered by latent diffusion models. The framework introduces three key innovations: an outlier-robust encoder trained via semantic adversarial perturbations; a lightweight, single-layer latent adapter for one-shot learning and improved adaptation to out-of-distribution data; and an end-to-end consistency distillation (EECD) method enabling low-latency, high-quality denoising in noisy environments. Together, these components significantly enhance the resilience, adaptability, and semantic fidelity of SemCom systems in real-world scenarios.

Biography:

Ping Wang is a Professor at the Department of Electrical Engineering and Computer Science, York University, and a Tier 2 York Research Chair. Prior to that, she was with Nanyang Technological University, Singapore, from 2008 to 2018. Her recent research interests focus on integrating Artificial Intelligence (AI) techniques into communications networks. Her scholarly works have been widely disseminated through top-ranked IEEE journals/conferences and received the IEEE Communications Society Best Survey Paper Award in 2023, and the Best Paper Awards from IEEE prestigious conference WCNC in 2012, 2020 and 2022, from IEEE Communication Society: Green Communications & Computing Technical Committee in 2018, from IEEE flagship conference ICC in 2007. She has been serving as the associate editor-in-chief for IEEE Communications Surveys & Tutorials and an editor for several reputed journals, including IEEE Transactions on Wireless Communications. She is a Fellow of the IEEE and a Distinguished Lecturer of the IEEE Vehicular Technology Society (VTS). She is also the Chair of the Education Committee of IEEE VTS.

Address:Canada

Prof. Lian Zhao of Toronto Metropolitan University

The sixth-generation (6G) communication networks are anticipated to enable a variety of innovative applications and provide extreme connectivity for mobile devices. To meet the evolving service demands in highly dynamic network environments, mobile edge computing (MEC) and artificial intelligence (AI) will be two pivotal technologies in 6G. MEC extends computing and storage capabilities within radio access networks, coping with the increasing computing demands from mobile users. Meanwhile, AI facilitates intelligent resource management by enabling network entities to learn and build knowledge about network dynamics. In this talk, I will explore AI-assisted resource management for MEC-enabled networks, addressing the computing challenges caused by device mobility and heterogeneity. Two AI-assisted resource management approaches will be introduced, each tailored to support a representative MEC use case: the Internet of Vehicles and mobile virtual reality video streaming. Finally, a future research plan will be outlined focused on holistic network virtualization through digital twin technologies, aimed at further enhancing the flexibility and efficiency of AI-assisted network management towards 6G.

Biography:

Dr. Lian Zhao is a professor at Toronto Metropolitan University. She has been an IEEE Communication Society (ComSoc) and IEEE Vehicular Technology (VTS) Distinguished Lecturer (DL); received the Best Land Transportation Paper Award from IEEE VTS in 2016 and 2024 respectively. She had served as an Editor for IEEE Transactions on Wireless Communications, IEEE Internet of Things Journal, and IEEE Transactions on Vehicular Technology. She is an Associate Editor-in-Chief for China Communications, and a Senior Editor for IEEE Wireless Communication Letters. She serves as TPC Chair for VTC2025-Fall, served as an Industry Panel co-Chair for IEEE Globecom 2024, co-Chair of various technical Symposiums for IEEE Globecom, ICC, PIMRC etc. She has been an elected member for the Board of Governor and a Fellow of IEEE.

Address:Canada

Prof. Dongmei Zhao of McMaster University

A digital twin (DT) is a virtual replica of a physical system (PS) that continuously mirrors the real-time state of its physical counterpart. A key indicator of DT quality is the degree of timely and accurate synchronization between the DT and its PS. Achieving tight PS-DT synchronization requires the DT to periodically communicate with the PS and use the received updates to extract the true status of the PS. This process requires sufficient network resources to ensure the desired information freshness and accuracy.  When the PSs are mobile devices, such as vehicles, maintaining high-quality DTs become particularly challenging due to dynamic network conditions caused by mobility. In this talk, we will first discuss network and resource management issues in supporting PS-DT synchronization and then present our recent work addressing the challenges of supporting DTs for vehicles.

Biography:

Dongmei Zhao received the Ph.D degree in Electrical and Computer Engineering from University of Waterloo, Waterloo, Ontario, Canada in June 2002. In July 2002 she joined the Department of Electrical and Computer Engineering at McMaster University, where she is a professor. She is currently an Associate Editor for the IEEE Internet of Things Journal. She also serves as a leading Co-Chair for the Emerging Technologies, 6G and Beyond Track of the IEEE Vehicular Technology Conference (VTC) Fall 2025. She is a Distinguished Lecturer of IEEE Vehicular Technology Society. Her recent research interests focus on network resource management and digital twins.