Saved in:
Bibliographic Details
Main Authors: Zhang, Yusong, Sun, Yuxuan, Guo, Lei, Chen, Wei, Ai, Bo, Gunduz, Deniz
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.04621
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915373492731904
author Zhang, Yusong
Sun, Yuxuan
Guo, Lei
Chen, Wei
Ai, Bo
Gunduz, Deniz
author_facet Zhang, Yusong
Sun, Yuxuan
Guo, Lei
Chen, Wei
Ai, Bo
Gunduz, Deniz
contents 6G networks promise revolutionary immersive communication experiences including augmented reality (AR), virtual reality (VR), and holographic communications. These applications demand high-dimensional multimodal data transmission and intelligent data processing in real-time, which is extremely challenging over resource-limited wireless communication systems. Moreover, a joint understanding of the environment, context, and user intent is essential to deliver task-relevant content effectively. This article presents a novel multimodal large language model (MLLM) integrated semantic communications framework, termed MLLM-SC, which fully leverages reasoning and generative capabilities of pre-trained foundation models for context-aware and task-oriented wireless communication. The MLLM-SC framework adopts a device-edge collaborative architecture. At the edge, MLLM-empowered semantic guidance module analyzes multimodal inputs, user intents, and channel conditions to generate importance-aware attention maps prioritizing semantically critical information. An importance-aware semantic encoder and a resource-adaptive semantic decoder are jointly designed and optimized, which can utilize the semantic guidance for adaptive bandwidth allocation and high-quality content reconstruction or generation. Extensive case studies on visual question answering for AR/VR applications and diffusion-driven image generation validate the effectiveness of MLLM-SC.
format Preprint
id arxiv_https___arxiv_org_abs_2507_04621
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multimodal LLM Integrated Semantic Communications for 6G Immersive Experiences
Zhang, Yusong
Sun, Yuxuan
Guo, Lei
Chen, Wei
Ai, Bo
Gunduz, Deniz
Machine Learning
Artificial Intelligence
Networking and Internet Architecture
6G networks promise revolutionary immersive communication experiences including augmented reality (AR), virtual reality (VR), and holographic communications. These applications demand high-dimensional multimodal data transmission and intelligent data processing in real-time, which is extremely challenging over resource-limited wireless communication systems. Moreover, a joint understanding of the environment, context, and user intent is essential to deliver task-relevant content effectively. This article presents a novel multimodal large language model (MLLM) integrated semantic communications framework, termed MLLM-SC, which fully leverages reasoning and generative capabilities of pre-trained foundation models for context-aware and task-oriented wireless communication. The MLLM-SC framework adopts a device-edge collaborative architecture. At the edge, MLLM-empowered semantic guidance module analyzes multimodal inputs, user intents, and channel conditions to generate importance-aware attention maps prioritizing semantically critical information. An importance-aware semantic encoder and a resource-adaptive semantic decoder are jointly designed and optimized, which can utilize the semantic guidance for adaptive bandwidth allocation and high-quality content reconstruction or generation. Extensive case studies on visual question answering for AR/VR applications and diffusion-driven image generation validate the effectiveness of MLLM-SC.
title Multimodal LLM Integrated Semantic Communications for 6G Immersive Experiences
topic Machine Learning
Artificial Intelligence
Networking and Internet Architecture
url https://arxiv.org/abs/2507.04621