Ada-TokenCom: Rate-Adaptive Token Communications via Large-Model-Driven Token Compression and Generation
Abstract
Token Communications (TokenCom) has recently emerged as a new paradigm in which tokens serve as unified units for communication and computation, enabling efficient multimodal semantic and goal-oriented transmission. In this paper, we develop Ada-TokenCom, a rate-adaptive TokenCom framework based on large autoregressive models, which integrates next-token prediction with arithmetic coding to achieve ultra-low bitrate semantic communication at the token level. We propose a mixed reconstruction/generation scheme, where the transmitter encodes and transmits the highly informative tokens at the beginning of the token sequence leveraging a pre-trained autoregressive large model, while the receiver uses an identical model to predict the rest. Moreover, we design a Lyapunov-based algorithm to dynamically optimize both the source compression rate and the modulation and coding scheme, adapting to time-varying network conditions. Simulation results demonstrate that our proposed Ada-TokenCom framework outperforms both digital and deep joint source-channel coding-based semantic communication baselines.
Related
- Convolution Quadrature with Adaptive History Compression for Variable-Order Fractional Reaction--Diffusion Equations
- Wideband Directional ℋ2-Matrix Compression for the Electric Field Integral Equation with Geometry-Adaptive Cluster Trees
- On the Adaptive Covering Complexity of Strings: Unifying Relative and Self-Referential Compression
- Simultaneous Matrix-Free HSS Compression and Factorization with Adaptive Ranks
- Adaptive Local Proper Orthogonal Decomposition via Graph Partitioning and Provable Error-Bounded Lossy Compression for Parametric Series in Finite-Dimensional Function Spaces
BibTeX
@misc{zhang2026adatokencom,
title = {{Ada-TokenCom: Rate-Adaptive Token Communications via Large-Model-Driven Token Compression and Generation}},
author = {Zijun Zhang and Li Qiao and Mahdi Boloursaz Mashhadi and Zhen Gao and Mehdi Bennis and Kaibin Huang},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.28086},
eprint = {2608.28086},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.28086},
}
RIS
TY - UNPB
TI - Ada-TokenCom: Rate-Adaptive Token Communications via Large-Model-Driven Token Compression and Generation
AU - Zijun Zhang
AU - Li Qiao
AU - Mahdi Boloursaz Mashhadi
AU - Zhen Gao
AU - Mehdi Bennis
AU - Kaibin Huang
PY - 2026
DA - 2026/08/28
PB - arXiv
DO - 10.48550/arxiv.2608.28086
UR - https://arxiv.org/abs/2608.28086
AB - Token Communications (TokenCom) has recently emerged as a new paradigm in which tokens serve as unified units for communication and computation, enabling efficient multimodal semantic and goal-oriented transmission. In this paper, we develop Ada-TokenCom, a rate-adaptive TokenCom framework based on large autoregressive models, which integrates next-token prediction with arithmetic coding to achieve ultra-low bitrate semantic communication at the token level. We propose a mixed reconstruction/generation scheme, where the transmitter encodes and transmits the highly informative tokens at the beginning of the token sequence leveraging a pre-trained autoregressive large model, while the receiver uses an identical model to predict the rest. Moreover, we design a Lyapunov-based algorithm to dynamically optimize both the source compression rate and the modulation and coding scheme, adapting to time-varying network conditions. Simulation results demonstrate that our proposed Ada-TokenCom framework outperforms both digital and deep joint source-channel coding-based semantic communication baselines.
ER -