# Text-Guided Token Communication for Wireless Image Transmission

Source: [Text-Guided Token Communication for Wireless Image Transmission](<https://www.sota2.com/research/paper/68fa5dcc1e209131ce9dcbab>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T18:25:11.159Z

Authors: Bole Liu, Li Qiao, Ye Wang, Zhen Gao, Yu Ma, Keke Ying, Tong Qin

Published: 2025-07-08T08:38:21.000Z

## Abstract

With the emergence of 6G networks and proliferation of visual applications, efficient image transmission under adverse channel conditions is critical. We present a text-guided token communication system leveraging pre-trained foundation models for wireless image transmission with low bandwidth. Our approach converts images to discrete tokens, applies 5G NR polar coding, and employs text-guided token prediction for reconstruction. Evaluations on ImageNet show our method outperforms Deep Source Channel Coding with Attention Modules (ADJSCC) in perceptual quality and semantic preservation at Signal-to-Noise Ratios (SNRs) above 0 dB while mitigating the cliff effect at lower SNRs. Our system requires no scenario-specific retraining and exhibits superior cross-dataset generalization, establishing a new paradigm for efficient image transmission aligned with human perceptual priorities.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2507.05781>)

[PDF](<https://arxiv.org/pdf/2507.05781.pdf>)