Token Encoding for Semantic Recovery

TL;DR

This paper introduces TokCode, a token encoding framework that enhances semantic recovery in wireless communication by mitigating token loss without extra transmission overhead.

Contribution

It proposes a novel token encoding method and a foundation model adaptation algorithm that together improve robustness against token loss in semantic communication.

Findings

TokCode reduces semantic distortion under harsh channel conditions.

It approaches the performance upper-bound even with 40-60% token loss.

The framework supports plug-and-play deployment without additional transmission overhead.

Abstract

Token-based semantic communication is promising for future wireless networks, as it can compact semantic tokens under very limited channel capacity. However, harsh wireless channels often cause missing tokens, leading to severe distortion that prevents reliable semantic recovery at the receiver. In this article, we propose a token encoding framework for robust semantic recovery (TokCode), which incurs no additional transmission overhead and supports plug-and-play deployment. For efficient token encoder optimization, we develop a sentence-semantic-guided foundation model adaptation algorithm (SFMA) that avoids costly end-to-end training. Based on simulation results on prompt-based generative image transmission, TokCode mitigates semantic distortion and can approach the performance upper-bound, even under harsh channels where 40% to 60% of tokens are randomly lost.