ToDMA: Large Model-Driven Token-Domain Multiple Access for Semantic Communications

TL;DR

This paper introduces ToDMA, a novel large model-driven token domain multiple access scheme for semantic communications that leverages context and multimodal large language models to improve transmission efficiency and quality.

Contribution

The paper proposes a new token domain multiple access framework utilizing large language models to mitigate token collisions and enhance semantic communication performance.

Findings

Achieves lower latency than orthogonal schemes.

Provides better distortion and perceptual quality than non-orthogonal methods.

Effective for both text and image transmission tasks.

Abstract

Token communications (TokCom) is an emerging generative semantic communication concept that reduces transmission rates by using context and multimodal large language model (MLLM)-based token processing, with tokens serving as universal semantic units across modalities. In this paper, we propose a semantic multiple access scheme in the token domain, referred to as token domain multiple access (ToDMA), where a large number of devices share a token codebook and a modulation codebook for source and channel coding, respectively. Specifically, each transmitter first tokenizes its source signal and modulate each token to a codeword. At the receiver, compressed sensing is employed first to detect active tokens and the corresponding channel state information (CSI) from the superposed signals. Then, the source token sequences are reconstructed by clustering the token-associated CSI across multiple time slots. In case of token collisions, some active tokens cannot be assigned and some positions in the reconstructed token sequences are empty. We propose to use pre-trained MLLMs to leverage the context, predict masked tokens, and thus mitigate token collisions. Simulation results demonstrate the effectiveness of the proposed ToDMA framework for both text and image transmission tasks, achieving significantly lower latency compared to context-unaware orthogonal communication schemes, while also delivering superior distortion and perceptual quality compared to state-of-the-art context-unaware non-orthogonal communication methods.