![Loading Events](https://r1.ieee.org/northjersey/wp-content/plugins/the-events-calendar/src/resources/images/tribe-loading.gif)
Large Language Models (LLMs) for NextG Wireless Networks
September 5 @ 14:00 - 15:00
Special Presentation by Dr. Hao Zhou and Chengming Hu (McGill U., Canada) Hosted by the Future Networks Artificial Intelligence & Machine Learning (AIML) Working Group Date/Time: Thursday, September 5th, 2024 @ 6 PM EDT Topic: Large Language Models (LLMs) for NextG Wireless Networks: Fundamentals and Case Studies in Network Optimization and Prediction Abstract: Large language models (LLMs) have received considerable attention recently due to their outstanding comprehension and reasoning capabilities, leading to great progress in many fields. The advancement of LLM techniques also offers promising opportunities to automate many tasks in the communication networks field. After pre-training and fine-tuning, LLMs can perform diverse downstream tasks based on human instructions, paving the way to artificial general intelligence (AGI)-enabled 6G. This talk will first present a comprehensive overview of LLM fundamentals and applications to wireless networks, discussing wireless-specific LLM training, fine-tuning, and practical deployment. Then, it will present two case studies on specific network optimization and prediction problems, showing detailed prompt and algorithm designs along with simulation results. Speakers: Dr. Hao Zhou is currently a Postdoctoral Researcher at the School of Computer Science, McGill University. He completed my PhD degree at University of Ottawa, Canada, from 2019 to 2023. His research focuses on the intersection between machine learning, optimization, and networked systems, especially for 5G/6G wireless networks and power systems. Dr. Zhou is dedicated to developing novel machine learning algorithms to address a series of optimization problems in networked systems, including resource allocation, computational task offloading, energy efficiency enhancement, energy management and trading, network security, etc. He has published more than 30 peer-reviewed papers, including reputable journals in IEEE Communication and Power Energy Societies, e.g., IEEE Wireless Communications, IEEE Trans. Smart Grid, and IEEE Communications Survey & Tutorials. He has received the Best Paper Award at the 2023 IEEE ICC conference, and the 2023 IEEE ComSoc CSIM TC Best Journal Paper Award for his contributions to transfer learning-enabled wireless network slicing. Dr. Zhou’s PhD Thesis entitled “ML-Based Optimization of Large-Scale Systems: Case Study in Smart Microgrids and 5G RAN” won the 2023 Faculty of Engineering’s Best Doctoral Thesis Award at University of Ottawa. Chengming Hu is currently a Ph.D. candidate at McGill University, Canada. He received M.Sc. in Quality Systems Engineering with Concordia Institute for Information Systems Engineering (CIISE), Concordia University, Canada, in 2019. His research interests focus on investigating computational intelligence techniques to enhance the effectiveness and security of IoT systems, including ensemble learning, knowledge distillation, language model, and feature learning, etc. He is actively working on various real-world applications, including power systems, communication systems, and transportation systems. His work has been published in top-tier, peer-reviewed conferences and journals, including ICLR, IEEE TSG, and IEEE PESGM, etc. Co-sponsored by: Artificial Intelligence & Machine Learning (AIML) Working Group Virtual: https://events.vtools.ieee.org/m/431215