Structure-Aware Multimodal LLM Framework for Trustworthy Near-Field Beam Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Mengyuan, Lu, Qianfan, Tian, Jiachen, Hu, Hongjun, Han, Yu, Li, Xiao, Wen, Chao-kai, Jin, Shi
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912970718576640
author Li, Mengyuan
Lu, Qianfan
Tian, Jiachen
Hu, Hongjun
Han, Yu
Li, Xiao
Wen, Chao-kai
Jin, Shi
author_facet Li, Mengyuan
Lu, Qianfan
Tian, Jiachen
Hu, Hongjun
Han, Yu
Li, Xiao
Wen, Chao-kai
Jin, Shi
contents In near-field extremely large-scale multiple-input multiple-output (XL-MIMO) systems, spherical wavefront propagation expands the traditional beam codebook into the joint angular-distance domain, rendering conventional beam training prohibitively inefficient, especially in complex 3-dimensional (3D) low-altitude environments. Furthermore, since near-field beam variations are deeply coupled not only with user positions but also with the physical surroundings, precise beam alignment demands profound environmental understanding capabilities. To address this, we propose a large language model (LLM)-driven multimodal framework that fuses historical GPS data, RGB image, LiDAR data, and strategically designed task-specific textual prompts. By utilizing the powerful emergent reasoning and generalization capabilities of the LLM, our approach learns complex spatial dynamics to achieve superior environmental comprehension...
format Preprint
id arxiv_https___arxiv_org_abs_2603_16143
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Structure-Aware Multimodal LLM Framework for Trustworthy Near-Field Beam Prediction
Li, Mengyuan
Lu, Qianfan
Tian, Jiachen
Hu, Hongjun
Han, Yu
Li, Xiao
Wen, Chao-kai
Jin, Shi
Signal Processing
Artificial Intelligence
In near-field extremely large-scale multiple-input multiple-output (XL-MIMO) systems, spherical wavefront propagation expands the traditional beam codebook into the joint angular-distance domain, rendering conventional beam training prohibitively inefficient, especially in complex 3-dimensional (3D) low-altitude environments. Furthermore, since near-field beam variations are deeply coupled not only with user positions but also with the physical surroundings, precise beam alignment demands profound environmental understanding capabilities. To address this, we propose a large language model (LLM)-driven multimodal framework that fuses historical GPS data, RGB image, LiDAR data, and strategically designed task-specific textual prompts. By utilizing the powerful emergent reasoning and generalization capabilities of the LLM, our approach learns complex spatial dynamics to achieve superior environmental comprehension...
title Structure-Aware Multimodal LLM Framework for Trustworthy Near-Field Beam Prediction
topic Signal Processing
Artificial Intelligence
url https://arxiv.org/abs/2603.16143