AI2MMUM: AI-AI Oriented Multi-Modal Universal Model Leveraging Telecom Domain Large Model

TL;DR

This paper introduces AI2MMUM, a versatile multi-modal model for 6G wireless systems that effectively handles diverse physical layer tasks by leveraging a large language model backbone and domain-specific fine-tuning.

Contribution

The paper presents a scalable, task-aware multi-modal universal model that integrates radio and language modalities with a novel fine-tuning approach for 6G wireless tasks.

Findings

Achieves state-of-the-art performance on five wireless channel tasks

Demonstrates effective multi-modal data processing for physical layer tasks

Utilizes a flexible architecture with fixed encoders and lightweight task heads

Abstract

Designing a 6G-oriented universal model capable of processing multi-modal data and executing diverse air interface tasks has emerged as a common goal in future wireless systems. Building on our prior work in communication multi-modal alignment and telecom large language model (LLM), we propose a scalable, task-aware artificial intelligence-air interface multi-modal universal model (AI2MMUM), which flexibility and effectively perform various physical layer tasks according to subtle task instructions. The LLM backbone provides robust contextual comprehension and generalization capabilities, while a fine-tuning approach is adopted to incorporate domain-specific knowledge. To enhance task adaptability, task instructions consist of fixed task keywords and learnable, implicit prefix prompts. Frozen radio modality encoders extract universal representations and adapter layers subsequently bridge radio and language modalities. Moreover, lightweight task-specific heads are designed to directly output task objectives. Comprehensive evaluations demonstrate that AI2MMUM achieves SOTA performance across five representative physical environment/wireless channel-based downstream tasks using the WAIR-D and DeepMIMO datasets.