The rapid evolution of wireless technologies is transforming communication systems into platforms that not only exchange data but also sense environments, interpret context, and support intelligent decision-making. In this new paradigm, communication becomes tightly coupled with sensing and computation, forming the foundation of future autonomous networks.

Our lab explores AI-enabled integrated approaches that unify physical-layer sensing, high-speed communication, and distributed computation. By developing novel PHY/MAC algorithms and scalable protocols, we aim to achieve systems that can dynamically adapt to their environment, optimize resource utilization, and enable seamless interaction among connected intelligent devices.

Ultimately, our research seeks to lay the groundwork for next-generation wireless networks where sensing and communication are no longer separate functions, but co-designed components of an intelligent, cooperative ecosystem.

Future wireless systems are becoming increasingly complex, with heterogeneous devices, diverse applications, and highly dynamic environments. Traditional rule-based control and optimization methods often fall short in adapting to such complexity.

To address this challenge, our lab envisions a Large Language Model (LLM)-based Wireless Orchestrator that serves as an intelligent controller for next-generation networks. Leveraging the reasoning and adaptation capabilities of LLMs, the orchestrator can interpret network states, predict resource demands, and autonomously generate control strategies across multiple layers of the wireless stack.

By integrating LLMs with wireless communication protocols, we aim to enable networks that are self-optimizing, context-aware, and resilient—capable of coordinating spectrum usage, managing interference, and supporting emerging applications such as immersive reality, autonomous systems, and large-scale IoT.

This research direction represents a step toward human-like intelligence in wireless orchestration, where networks not only connect devices but also understand, adapt, and collaborate in real time.