The 12th International Conference on Communication and Information Processing

2026年第十二届通信与信息处理国际会议

November 13-16, 2026 // Lingshui, Hainan, China

Prof. Gang Feng

University of Electronic Science and Technology of China, China

Gang Feng received his BEng and MEng degrees in Electronic Engineering from the University of Electronic Science and Technology of China (UESTC), in 1986 and 1989, respectively, and Ph.D. degree in Information Engineering from The Chinese University of Hong Kong in 1998. He joined the School of Electric and Electronic Engineering, Nanyang Technological University as an assistant professor and an associate professor in 2000 and 2005 respectively. At present he is a professor with the National Key Laboratory of Wireless Communications, UESTC of China. Dr. Feng has extensive research experience and has published widely in wireless networking research. He is the recipient of IEEE Communications Society Technical Committee on Transmission Access and Optical Systems (TAOS) Best Paper Award (2019)，ICC 2019 best paper award , Best Paper Award of IEEE Internet of Things Journal 2022，and Best Paper Award of IEEE Transactions on Services Computing. He served as a Distinguished Lecturer in VTS IEEE 2023. His research interests include AI Enabled wireless networking, distributed and collaborative machine learning, next generation cellular networks, etc. He is a fellow of IEEE.

Speech Title: Efficient multi-agent collaborative decision-making mechanisms in 6G networks
Abstract: To address the core challenges in multi-agent collaborative decision-making, including policy adaptation difficulties and declining inference efficiency under dynamic environments and growing agent populations, this presentation introduces an efficient collaborative decision-making mechanism that integrates three key modules: fine-tuning and continuous optimization, LLM-guided reinforcement learning (RL) decision-making, and joint inference for agent deployment. Specifically, we first employ compression technologies such as LoRA and pruning to perform lightweight fine-tuning, enabling rapid customization of task-specific policies while preserving the generalization capability of pre-trained knowledge. Then, we introduce a large language model (LLM) as a high-level semantic guide that transforms environmental observations and sub-goals into natural-language-shaped reward potential functions. This guides the underlying RL policy toward directed exploration in sparse-reward scenarios. Finally, we design a multi-scale joint inference framework that integrates local policies with global information at the decision level via shared attention mechanisms and hierarchical message passing among agents, effectively alleviating communication and computational bottlenecks.

Prof. Yejun He

Shenzhen University, China

Yejun He received the Ph.D. degree in information and communication engineering from the Huazhong University of Science and Technology (HUST), Wuhan, China, in 2005. In 2006, he joined Shenzhen University, where he is currently a Distinguished Professor and the Director of Sino-British Antennas and Propagation Joint Laboratory of MOST, the Director of Guangdong Engineering Research Center of Base Station Antennas and Propagation, and the Director of the Shenzhen Key Laboratory of Antennas and Propagation. He was selected as an Expert with Special Government Allowance from the State Council in China in 2024. He has authored or coauthored more than 380 research articles, eight books, and holds about 40 patents, with an h-index of 52 and over 10,000 citations. His research interests include wireless communications, antennas, and radio frequency. Dr. He is a Fellow of IET and a Fellow of the China Institute of Communications.

Speech Title: Enhancing Over-the-Air Computation in Low-Altitude UAV Networks Based on Pinching-Antenna Systems
Abstract: In low-altitude networks, unmanned aerial vehicle (UAV) swarms are expected to serve as distributed sensing platforms that continuously collect environmental and operational data, where efficient aggregation of distributed data is critical for latency-critical aerial applications. Over-the-air computation (AirComp) improves spectral efficiency through analog signal superposition, but its performance is often limited by heterogeneous air-to-ground channels and strict UAV peakpower constraints, resulting in computation distortion dominated by the weakest link. This talk introduces a pinching-antenna system (PASS) enhancing AirComp in low-altitude UAV network, where the base station (BS) employs dielectric waveguides and can adjust the radiation (pinching) positions to flexibly shape the effective transmission channels. Such a BS-side antenn reconfiguration provides an additional degree of freedom, thereby enhancing the received signal strength and facilitating magnitude alignment. We aim to minimize the computation mean squared error (MSE) by jointly optimizing the BS receive decoding vector, the UAV transmit power, the PASS pinching positions, and the UAV locations. To solve the resulting non-convex problem, we develop an alternating-optimization framework that admits closedform update for the design of decoding vectors and transmit power, alternating linear search for the pinching positions, and a successive convex approximation algorithm with a trust region for UAV location optimization. Related key technologies and challeges are also presented.

Prof. Feifei Gao

Tsinghua University, China

Feifei Gao (Fellow, IEEE) received the B.Eng. degree from Xi'an Jiaotong University, Xi'an, China in 2002, the M.Sc. degree from McMaster University, Hamilton, ON, Canada in 2004, and the Ph.D. degree from National University of Singapore, Singapore in 2007. Since 2011, he joined the Department of Automation, Tsinghua University, Beijing, China, where he is currently a tenured full professor.
Prof. Gao's research interests include signal processing for communications, array signal processing, convex optimizations, and artificial intelligence assisted communications. He has authored/coauthored more than 200 refereed IEEE journal papers and more than 150 IEEE conference proceeding papers that are cited more than 28000 times in Google Scholar. Prof. Gao has served as an Editor of IEEE Transactions on Wireless Communications, IEEE Journal of Selected Topics in Signal Processing (Lead Guest Editor), IEEE Transactions on Cognitive Communications and Networking, IEEE Signal Processing Letters (Senior Editor), IEEE Communications Letters (Senior Editor), IEEE Wireless Communications Letters, and China Communications. He has also served as the symposium co-chair for 2019 IEEE Conference on Communications (ICC), 2018 IEEE Vehicular Technology Conference Spring (VTC), 2015 IEEE Conference on Communications (ICC), 2014 IEEE Global Communications Conference (GLOBECOM), 2014 IEEE Vehicular Technology Conference Fall (VTC), as well as Technical Committee Members for more than 50 IEEE conferences.

Speech Title: Key Technologies and Prototype Design for Integrated Sensing and Communications System
Abstract: In the future, millions of base stations (BSs) and billions of users (UEs) will natively build an integrated sensing and communications (ISAC) system, which can utilize intelligent ubiquitous methods to realize the ultimate goal of sensing, i.e., constructing the global mapping from real physical world to digital twin world, while providing communications services at the same time. For this purpose, we conduct a series of theoretical and technical researches on ISAC, in which we decompose the real physical world into static environment, dynamic targets, and various object materials. The ubiquitous static environment occupies the vast majority of the physical world, for which we design static environment reconstruction (SER) scheme to obtain the layout and point cloud information of static buildings. The dynamic targets floating in static environments create the spatiotemporal transition of the physical world, for which we design comprehensive dynamic target sensing (DTS) scheme to detect, estimate, track, image and recognize the dynamic targets in real-time. The object materials enrich the electromagnetic laws of the physical world, for which we develop object material recognition (OMR) scheme to estimate the electromagnetic coefficient of the objects. Finally, based on these theoretical researches, we build an ISAC hardware prototype platform working in millimeter wave frequency band, realizing high-precision SER, DTS, and basic OMR, which provides preliminary verification for building the digital twin for communications networks.