activity
20232026
collaborators
Showing 2026Show all

7 papers · 1 filter

eess.SP2026

UAV SAR Imaging via Diffusion Posterior Sampling under Non-Ideal Motion in ISAC Systems

Keying Zhu, Le Liang, Jie Yang +2

Unmanned aerial vehicle-enabled synthetic aperture radar (SAR) offers significant potential for providing communication services to ground users while sensing the surrounding envir…

cs.IT2026

A Graph Foundation Model for Large-Scale MIMO Detection

Xingyu Zhou, Le Liang, Hao Ye +5

Large-scale multiple-input multiple-output (MIMO) detection is fundamental to modern wireless networks but constrained by performance-complexity trade-offs. Existing detectors, whe…

eess.SP2026

Foundation Models for Wireless Communications: From PHY Intelligence to Network Autonomy

Le Liang, Jiajia Guo, Jun Zhang +6

6G networks will introduce unprecedented complexity, which calls for a paradigm shift in network optimization and management. Artificial intelligence (AI)-based solutions, especial…

cs.LG2026

A Graph Foundation Model for Wireless Resource Allocation

Yucheng Sheng, Jiacheng Wang, Le Liang +2

The aggressive densification of modern wireless networks necessitates judicious resource allocation to mitigate severe mutual interference. However, classical iterative algorithms…

cs.IT2026

Wireless Power Control Based on Large Language Models

Jiacheng Wang, Yucheng Sheng, Le Liang +2

This paper investigates the power control problem in wireless networks by repurposing pre-trained large language models (LLMs) as relational reasoning backbones. In hyper-connected…

eess.SP2026

Beam Prediction Based on Multimodal Large Language Models

Tianhao Mao, Le Liang, Jie Yang +3

Accurate beam prediction is a key enabler for next-generation wireless communication systems. In this paper, we propose a multimodal large language model (LLM)-based beam predictio…

cs.LG2026

Improving Channel Estimation via Multimodal Diffusion Models with Flow Matching

Xiaotian Fan, Xingyu Zhou, Le Liang +2

Deep generative models offer a powerful alternative to conventional channel estimation by learning complex channel distributions. By integrating the rich environmental information…