Artificial Intelligence for Robust and Scalable Wireless Communication

Artificial Intelligence (AI) has emerged as a key enabler of next-generation wireless communication, particularly in optimizing resource allocation, user localization, and beamforming in millimeter-wave (mmWave) and multiple-input multiple-output (MIMO) systems. These high-frequency networks face inherent challenges such as severe path loss, sensitivity to user mobility, and the need for precise beam alignment. Traditional signal processing techniques often struggle to maintain performance under such dynamic and uncertain conditions, motivating the integration of machine learning to achieve more adaptive and intelligent wireless systems.In this work, we investigated multiple AI-driven approaches for enhancing wireless communication. First, we studied user localization in mmWave systems equipped with MIMO antennas and reflective intelligent surfaces. Using MATLAB-based equation modeling, we validated localization strategies and subsequently developed a Python interface to visualize real-time beam directions and user positions. Building on this, we explored computer vision techniques to further improve user localization and dynamically adjust beam steering in response to user mobility.Beyond system-level implementations, we also explored the role of foundation models in wireless applications, focusing on their ability to generalize from limited data and remain robust to imperfect or noisy inputs. To achieve this, we optimized a transformer-based architecture through masking-based self-supervision and evaluated its performance across downstream communication tasks. Our results suggest that integrating foundation models with traditional wireless architectures can significantly enhance both adaptability and reliability, paving the way for AI-augmented communication systems that are scalable and resilient to real-world challenges.