Ada-TokenCom: Rate-Adaptive Token Communications via Large-Model-Driven Token Compression and Generation
- URL: http://arxiv.org/abs/2608.28086v1
- Date: Fri, 28 Aug 2026 08:54:28 GMT
- Title: Ada-TokenCom: Rate-Adaptive Token Communications via Large-Model-Driven Token Compression and Generation
- Abstract summary: Ada-TokenCom is a rate-adaptive TokenCom framework based on large autoregressive models.<n>We propose a mixed reconstruction/generation scheme, where the transmitter encodes and transmits the highly informative tokens.<n>We show that our proposed Ada-TokenCom framework outperforms both digital and deep joint source-channel coding-based semantic communication baselines.
- Score: 52.99258064220833
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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 papers
- Video TokenCom: Textual Intent-Guided Multi-Rate Video Token Communications with UEP-Based Adaptive Source-Channel Coding [24.169863403324314]
Token Communication (TokenCom) is a new paradigm, motivated by the recent success of Large AI Models (LAMs) and Multimodal Large Language Models (MLLMs)<n>We propose a novel Video TokenCom framework for textual intent-guided multi-rate video communication.
arXiv Detail & Related papers (2026-03-02T23:36:38Z) - Communication-Inspired Tokenization for Structured Image Representations [74.17163003465537]
COMmunication inspired Tokenization (COMiT) is a framework for learning structured discrete visual token sequences.<n>Our experiments demonstrate that while semantic alignment provides grounding, attentive sequential tokenization is critical for inducing interpretable, object-centric token structure.
arXiv Detail & Related papers (2026-02-24T09:53:50Z) - Wireless TokenCom: RL-Based Tokenizer Agreement for Multi-User Wireless Token Communications [59.84545048095092]
Token Communications (TokenCom) has recently emerged as an effective new paradigm, where tokens are the unified units of communications computations.<n>We investigate a multi-user downlink wireless TokenCom scenario, where the base station transmits multiple users.
arXiv Detail & Related papers (2026-02-12T19:00:33Z) - Joint Semantic-Channel Coding and Modulation for Token Communications [37.814311208185906]
We consider the problem of token communication, studying how to transmit tokens efficiently and reliably.<n>We propose a joint semantic-channel and modulation scheme for the token encoder, mapping point tokens to standard digital constellation points.<n>The proposed method outperforms both joint semantic-channel coding and traditional separate coding.
arXiv Detail & Related papers (2025-11-19T18:56:32Z) - MergeDNA: Context-aware Genome Modeling with Dynamic Tokenization through Token Merging [65.07273789940116]
This paper introduces a hierarchical architecture that jointly optimize a dynamic genomic tokenizer and latent Transformers with context-aware pre-training tasks.<n> MergeDNA achieves superior performance on three popular DNA benchmarks and several multi-omics tasks with fine-tuning or zero-shot evaluation.
arXiv Detail & Related papers (2025-11-17T19:27:41Z) - Token Communication in the Era of Large Models: An Information Bottleneck-Based Approach [55.861432910722186]
UniToCom is a unified token communication paradigm that treats tokens as the fundamental units for both processing and wireless transmission.<n>We propose a generative information bottleneck (GenIB) principle, which facilitates the learning of tokens that preserve essential information.<n>We employ a causal Transformer-based multimodal large language model (MLLM) at the receiver to unify the processing of both discrete and continuous tokens.
arXiv Detail & Related papers (2025-07-02T14:03:01Z) - Token Communications: A Large Model-Driven Framework for Cross-modal Context-aware Semantic Communications [78.80966346820553]
We introduce token communications (TokCom), a large model-driven framework to leverage cross-modal context information in generative semantic communications (GenSC)<n>In this paper, we introduce the potential opportunities and challenges of leveraging context in GenSC, explore how to integrate GFM/MLLMs-based token processing into semantic communication systems, present the key principles for efficient TokCom at various layers in future wireless networks.
arXiv Detail & Related papers (2025-02-17T18:14:18Z) - Adaptive Semantic Token Selection for AI-native Goal-oriented Communications [11.92172357956248]
We propose a novel design for AI-native goal-oriented communications.
We exploit transformer neural networks under dynamic inference constraints on bandwidth and computation.
We show that our model improves over state-of-the-art token selection mechanisms.
arXiv Detail & Related papers (2024-04-25T13:49:50Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.