English

VLF-MSC: Vision-Language Feature-Based Multimodal Semantic Communication System

Computer Vision and Pattern Recognition 2025-11-14 v1 Systems and Control Systems and Control

Abstract

We propose Vision-Language Feature-based Multimodal Semantic Communication (VLF-MSC), a unified system that transmits a single compact vision-language representation to support both image and text generation at the receiver. Unlike existing semantic communication techniques that process each modality separately, VLF-MSC employs a pre-trained vision-language model (VLM) to encode the source image into a vision-language semantic feature (VLF), which is transmitted over the wireless channel. At the receiver, a decoder-based language model and a diffusion-based image generator are both conditioned on the VLF to produce a descriptive text and a semantically aligned image. This unified representation eliminates the need for modality-specific streams or retransmissions, improving spectral efficiency and adaptability. By leveraging foundation models, the system achieves robustness to channel noise while preserving semantic fidelity. Experiments demonstrate that VLF-MSC outperforms text-only and image-only baselines, achieving higher semantic accuracy for both modalities under low SNR with significantly reduced bandwidth.

Keywords

Cite

@article{arxiv.2511.10074,
  title  = {VLF-MSC: Vision-Language Feature-Based Multimodal Semantic Communication System},
  author = {Gwangyeon Ahn and Jiwan Seo and Joonhyuk Kang},
  journal= {arXiv preprint arXiv:2511.10074},
  year   = {2025}
}

Comments

To appear in the AI4NextG Workshop at NeurIPS 2025

R2 v1 2026-07-01T07:35:16.839Z