WISELab

About Me

Junting Chen received the Ph.D. degree in electronic and computer engineering from The Hong Kong University of Science and Technology (HKUST), Hong Kong SAR China, and the B.Sc. degree in electronic engineering from Nanjing University, Nanjing, China. He is currently an Associate Professor and Presidential Young Fellow with the School of Science and Engineering, the Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Guangdong, China. Prior to joining CUHK-Shenzhen, he was a Postdoctoral Research Associate with the Ming Hsieh Department of Electrical Engineering, University of Southern California (USC), Los Angeles, CA, USA, from 2016–2018, and with the Communication Systems Department of EURECOM, Sophia-Antipolis, France, from 2015–2016; he was also with the Wireless Information and Network Sciences Laboratory at MIT, Cambridge, MA, USA, from 2014–2015.

Dr. Chen works in the field of signal processing, optimization, and machine learning for wireless communications and localization. He focuses on applications in 5G/6G cellular communications and localization, underwater acoustic communication and localization, low-altitude air-to-ground integrated communications, massive MIMO, and radio maps. As a young scholar, Dr. Chen has published over 100 papers in leading journals and conference proceedings, and has contributed to over 10 patents. He won the Charles Kao Best Paper Award in WOCC 2022. He currently serves as an editor for IEEE Transactions on Wireless Communications. He was recognized as the Top 2% Scientist in 2025. He was the co-chair for radio map workshops on IEEE Globecom 2025 and IEEE/CIC ICCC 2024, 2025, 2026.

Research Highlights

We are interested in signal processing, optimization, machine learning and artificial intelligence for wireless communications, sensing, and localization.

Large models for radio mapping

Large models can learn reusable radio-environment priors from measured, simulated, and map-assisted data from multimodal source, helping sparse measurements become dense channel, spectrum, and beam maps and assisting for network optimization and localization. A key research question is how the sequential token-by-token processing in the Transformer structure may align with physics-aware and uncertainty-aware radio propagation.

LEO communications and radio mapping

Low Earth orbit (LEO) satellite networks create fast-moving coverage footprints, time-varying interference, and large-scale global connectivity opportunities. Radio mapping provides a tool to understand and manipulate space-air-ground channels, supporting beam management, handover planning, and spectrum sharing.

Predictive semantic communications

Semantic communications transmit task-relevant meaning rather than raw bits, while prediction uses mobility, context, and channel forecasts to prepare communication before the link changes. Combining the two can reduce redundant traffic and help networks deliver the right information at the right time.

Multimodal vehicle sensing

The communication infrastructure, such as 5G/6G networks, has the capability to sense the environment, including vehicles. Radio sensing is more robust in some scenarios than other modality such as cameras and lidar. Multimodal fusion turns partial views from multimodal data into a more robust perception layer for localization, mapping, safety, and cooperative intelligent transportation.