# Evolving Semantic Communication with Generative Model

arXiv: https://arxiv.org/abs/2403.20237 · HTML: https://mlsanity.com/paper/2403.20237/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Mar 2024.

## Built on by (most cited first, 8 of 8)

- [Generative Video Semantic Communication via Multimodal Semantic Fusion with Large Model](https://mlsanity.com/paper/2502.13838/) (2025)
- [Generative Semantic Communication: Architectures, Technologies, and Applications](https://mlsanity.com/paper/2412.08642/) (2024)
- [Retrieval-augmented Generation for GenAI-enabled Semantic Communications](https://mlsanity.com/paper/2412.19494/) (2024)
- [SING: Semantic Image Communications using Null-Space and INN-Guided Diffusion Models](https://mlsanity.com/paper/2503.12484/) (2025)
- [SQ-GAN: Semantic Image Communications Using Masked Vector Quantization](https://mlsanity.com/paper/2502.09520/) (2025)
- [Enabling Training-Free Semantic Communication Systems with Generative Diffusion Models](https://mlsanity.com/paper/2505.01209/) (2025)
- [Rateless Joint Source-Channel Coding, and a Blueprint for 6G Semantic Communications System Design](https://mlsanity.com/paper/2502.06095/) (2025)
- [Evolving Token Communication with Parametric Memory Network](https://mlsanity.com/paper/2605.01869/) (2026)

## Abstract (arXiv)

Recently, learning-based semantic communication (SemCom) has emerged as a promising approach in the upcoming 6G network and researchers have made remarkable efforts in this field. However, existing works have yet to fully explore the advantages of the evolving nature of learning-based systems, where knowledge accumulates during transmission have the potential to enhance system performance. In this paper, we explore an evolving semantic communication system for image transmission, referred to as ESemCom, with the capability to continuously enhance transmission efficiency. The system features a novel channel-aware semantic encoder that utilizes a pre-trained Semantic StyleGAN to extract the channel-correlated latent variables consisting of serval semantic vectors from the input images, which can be directly transmitted over a noisy channel without further channel coding. Moreover, we introduce a semantic caching mechanism that dynamically stores the transmitted semantic vectors in the local caching memory of both the transmitter and receiver. The cached semantic vectors are then exploited to eliminate the need to transmit similar codes in subsequent transmission, thus further reducing communication overhead. Simulation results highlight the evolving performance of the proposed system in terms of transmission efficiency, achieving superior perceptual quality with an average bandwidth compression ratio (BCR) of 1/192 for a sequence of 100 testing images compared to DeepJSCC and Inverse JSCC with the same BCR. Code of this paper is available at urlhttps://github.com/recusant7/GANSeCom.