{
  "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.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2608.28086",
  "author_total": 6,
  "authors": [
    {
      "name": "Zijun Zhang"
    },
    {
      "name": "Li Qiao"
    },
    {
      "name": "Mahdi Boloursaz Mashhadi"
    },
    {
      "name": "Zhen Gao"
    },
    {
      "name": "Mehdi Bennis"
    },
    {
      "name": "Kaibin Huang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/6w5432ffbaq87.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2608.28086",
  "fulltext_url": null,
  "id": "6w5432ffbaq87",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2608.28086",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.CV"
    ],
    [
      "arxiv",
      "cs.IT"
    ],
    [
      "arxiv",
      "eess.IV"
    ],
    [
      "arxiv",
      "math.IT"
    ],
    [
      "openalex",
      "2208|Advanced Wireless Communication Technologies"
    ]
  ],
  "openalex": "W7204820798",
  "pdf_url": "https://arxiv.org/pdf/2608.28086",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-28",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/6w5432ffbaq87.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:28Z",
      "native_id": "2608.28086",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2608.28086"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.IT",
      "subfield": "general"
    }
  ],
  "title": "Ada-TokenCom: Rate-Adaptive Token Communications via Large-Model-Driven Token Compression and Generation",
  "title_text": "Ada-TokenCom: Rate-Adaptive Token Communications via Large-Model-Driven Token Compression and Generation",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:28Z",
  "url": "https://research.draconitic.com/paper/6w5432ffbaq87",
  "venue": "arXiv",
  "versions": []
}