Ada-TokenCom: Rate-Adaptive Token Communications via Large-Model-Driven Token Compression and Generation

Zijun Zhang; Li Qiao; Mahdi Boloursaz Mashhadi; Zhen Gao; Mehdi Bennis; Kaibin Huang

cs.ITAug 28, 2026

Ada-TokenCom: Rate-Adaptive Token Communications via Large-Model-Driven Token Compression and Generation

Authors: Zijun Zhang, Li Qiao, Mahdi Boloursaz Mashhadi, Zhen Gao, Mehdi Bennis, Kaibin Huang

Organizations: School of Information and Electronics, Beijing Institute of Technology (Zhuhai), Zhuhai 519088, China · Department of Electrical and Computer Engineering, The University of Hong Kong, Pokfulam Road, Hong Kong SAR · University of Surrey, Guildford, U.K. · Centre for Wireless Communications, University of Oulu, 90014 Oulu, Finland

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.

Figures & tables

Panel of Figure 1 — Fig. 1: Block diagram of the proposed Ada-TokenCom framework.

Panel of Figure 2 — Fig. 2: Self-information as a function of token position (a) with class label as conditional information ( cond ) and (b) with null label ( uncond ), averaged over 1000 images from ImageNet-V2 datatset, for pretrained AR models with different parameter scales.

Panel of Figure 3 — Fig. 3: Visualization of self-information on a $16\times 16$ VQGAN latent grid using LlamaGen-L. Fluctuations predominantly occur at positions associated with discontinuities, which are induced by flattening the 2D latent grid and mapping the grid into 1D token sequence.

Panel of Figure 4 — Fig. 4: Visualization for (a) heatmap of conditional entropy on a $16\times 16$ VQGAN latent grid, and (b) samples of their decoded image with specified lengths of head tokens.

Model	Params 1	Inference Cost 2	Avg. Bits (cond)	Avg. Bits (uncond)
LlamaGen-B	72 M + 111 M	52.56 G	11.42	11.54
LlamaGen-L	72 M + 343 M	173.57 G	11.22	11.33
Taming Transf.	76 M + 1411 M	364.00 G	8.09	8.37

TABLE I: Average conditional self-information per token under different AR models.

Fig. 5: Performance comparison between the proposed Ada-TokenCom framework and benchmark image compression methods on the ImageNet-V2 dataset.

Panel of Figure 7 — Fig. 6: Visualization of image reconstruction at different token truncating levels for t2i and c2i scenarios.

			QPSK		16QAM
Code	Rate	Polynominal	$\alpha_{m}$	$\beta_{m}$	$\alpha_{m}$	$\beta_{m}$
Uncoded	$1$	$-$	1.742	-2.188	8.662	-13.306
Conv Code	$1/2$	$[5,7]_{8}$	0.320	0.011	1.103	-0.277
Conv Code	$2/3$	$[51,31,13]_{8}$	0.157	0.225	0.506	0.623
Conv Code	$1/5$	[35, 33, 27, 37, 23] 8	0.086	0.070	0.268	0.075
Turbo Code	$1/3$	$[1,5/7,5/7]_{8}$	0.031	0.560	0.087	1.630

TABLE II: Candidate Sets of Channel Coding and Modulations Schemes

$n^{*}$	256	224	192	160	128	96	64	32
$A$	0.937	0.931	0.922	0.913	0.898	0.880	0.861	0.843

TABLE III: Semantic quality

A

(CLIP) Under Different Prefix Lengths

n^{*}

Fig. 7: Performance comparison of reconstruction among the proposed LlamaGen-based Ada-TokenCom framework, SwinJSCC with rate and SNR adaptation on the ImageNet-V2 dataset.

Panel of Figure 11 — Fig. 8: Visualization of image reconstruction at different channel bandwidth ratios for the Ada-TokenCom framework and SwinJSCC with rate and SNR adaptation at $\text{SNR}=12\text{dB}$ . The value shown on each image denotes CBR / CLIP score.

Panel of Figure 12 — Fig. 9: Effect of the Lyapunov weight $\eta$ on terminal budget utilization at (a) $C_{\mathrm{th}}=500$ and (b) $C_{\mathrm{th}}=1500$ under four SNR regimes.

Fig. 10: Per-slot cumulative CLIP and

(1-\mathrm{LPIPS})

(upper row) with their historical average link utilization (lower row) under

\mathrm{SNR}\sim N(12,10)

when

C_{\mathrm{th}}=500

Method	Parameters / M (Encoder + Decoder)	Inference Cost / GFlops (Encoder + Decoder)	Encoder Latency	Decoder Latency
SwinJSCC	18.34 + 14.73	35.01 + 34.11	10 ms	6 ms
HiFiC	24.69 + 168.28	15.28 + 116.47	83 ms	188 ms
BPG	–	–	307–824 ms	29–43 ms
Ada-TokenCom (LlamaGen-L) 2	372.21 + 385.36	311.41 + 422.47	19 ms	1012 ms

TABLE IV: Comparison of model size, inference cost, and computation latency 1 .

Explore similar work

Video TokenCom: Textual Intent-Guided Multi-Rate Video Token Communications with UEP-Based Adaptive Source-Channel Coding
Mar 2, 2026Jingxuan Men, Mahdi Boloursaz Mashhadi, Ning Wang +3Semantic Communication
5GIC & 6GIC, Institute for Communication Systems (ICS), University of Surrey, U.K. · Smart Internet Lab, University of Bristol, U.K. · British Telecom Research Lab, BT Group plc, U.K.
Token Communications: A Large Model-Driven Framework for Cross-modal Context-aware Semantic Communications
Feb 17, 2025Li Qiao, Mahdi Boloursaz Mashhadi, Zhen Gao +3Semantic Communication
School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China · 5GIC & 6GIC, Institute for Communication Systems (ICS), University of Surrey, Guildford, United Kingdom · Centre for Wireless Communications, University of Oulu, 90014 Oulu, Finland +1
Token Encoding for Semantic Recovery
Apr 14, 2026Jingzhi Hu, Ouya Wang, Geoffrey Ye LiSemantic Communication Wireless Communications
Department of Electrical and Electronic Engineering, Imperial College London, London SW7 2AZ, UK.

Mar 2, 2026J/K move · Enter open · S save

Video TokenCom: Textual Intent-Guided Multi-Rate Video Token Communications with UEP-Based Adaptive Source-Channel Coding

Jingxuan Men, Mahdi Boloursaz Mashhadi, Ning Wang, Yi Ma+2

5GIC & 6GIC, Institute for Communication Systems (ICS), University of Surrey, U.K. · Smart Internet Lab, University of Bristol, U.K. · British Telecom Research Lab, BT Group plc, U.K.

Semantic Communication

Open paper AskPDF arXiv

Token Communication (TokenCom) is a new paradigm, motivated by the recent success of Large AI Models (LAMs) and Multimodal Large Language Models (MLLMs), where tokens serve as unified units of communication and computation, enabling efficient semantic- and goal-oriented information exchange in future wireless networks. In this paper, we propose a novel Video TokenCom framework for textual intent-guided multi-rate video communication with Unequal Error Protection (UEP)-based source-channel coding adaptation. The proposed framework integrates user-intended textual descriptions with discrete video tokenization and unequal error protection to enhance semantic fidelity under restrictive bandwidth constraints. First, discrete video tokens are extracted through a pretrained video tokenizer, while text-conditioned vision-language modeling and optical-flow propagation are jointly used to identify tokens that correspond to user-intended semantics across space and time. Next, we introduce a semantic-aware multi-rate bit-allocation strategy, in which tokens highly related to the user intent are encoded using full codebook precision, whereas non-intended tokens are represented through reduced codebook precision differential encoding, enabling rate savings while preserving semantic quality. Finally, a source and channel coding adaptation scheme is developed to adapt bit allocation and channel coding to varying resources and link conditions. Experiments on various video datasets demonstrate that the proposed framework outperforms both conventional and semantic communication baselines, in perceptual and semantic quality on a wide SNR range.

Abstract

Explore similar work

Video TokenCom: Textual Intent-Guided Multi-Rate Video Token Communications with UEP-Based Adaptive Source-Channel Coding

Token Communications: A Large Model-Driven Framework for Cross-modal Context-aware Semantic Communications

Token Encoding for Semantic Recovery