This paper introduces a novel neural network framework called M2BeamLLM for beam prediction in millimeter-wave (mmWave) massive multi-input multi-output (mMIMO) communication systems. M2BeamLLM integrates multi-modal sensor data, including images, radar, LiDAR, and GPS, leveraging the powerful reasoning capabilities of large language models (LLMs) such as GPT-2 for beam prediction. By combining sensing data encoding, multimodal alignment and fusion, and supervised fine-tuning (SFT), M2BeamLLM achieves significantly higher beam prediction accuracy and robustness, demonstrably outperforming traditional deep learning (DL) models in both standard and few-shot scenarios. Furthermore, its prediction performance consistently improves with increased diversity in sensing modalities. Our study provides an efficient and intelligent beam prediction solution for vehicle-to-infrastructure (V2I) mmWave communication systems.

However, applying LLMs have been proposed for channel prediction the high operating frequency results in substantial [8], beam prediction [9], and port prediction for fluid antennas path loss. To address this challenge, massive multiple-input [10]. Built on these developments, in this paper, we propose a multiple-output (mMIMO) antenna arrays are extensively employed, vision-aided beam prediction framework, named BeamLLM, which utilize highly directional beamforming techniques which utilizes LLMs to process RGB images, thereby enabling to mitigate propagation losses.