{
  "abstract": "Advanced artificial intelligence models think in tokens; contemporary communication systems carry bits. The direct way to bridge this gap is to transmit tokens, but that makes a model-specific representation part of the air interface, coupling the endpoints through a shared tokenizer, codebook, and often a neural transceiver. We take a different route: keep bits in the payload and let tokens control how those bits are generated and protected. The resulting token-bit interface transition aligns task-side tokens with source- and channel-coding units, translates token relevance into codec controls, and preserves the induced priority order across the coding chain. We instantiate it for image classification, where a vision transformer scores the task relevance of each image region from its attention maps: those scores steer block-wise JPEG rate allocation, then group the compressed bits for protection at different polar-code rates. The payload remains an explicit, reconstructable bitstream recovered by a correspondingly configured decoder. Over-the-air experiments on a software-defined radio testbed show improved accuracy--latency tradeoffs over separate source-channel coding, performance competitive with far more memory-intensive neural joint source-channel coding, and graceful degradation under channel mismatch. Token communication, then, need not transmit tokens explicitly; what it needs is an interface through which tokens determine how bits are communicated.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.15256",
  "author_total": 5,
  "authors": [
    {
      "name": "Chanho Park"
    },
    {
      "name": "Bumsu Park"
    },
    {
      "name": "Soonhee Kwon"
    },
    {
      "name": "Sangrim Lee"
    },
    {
      "name": "Namyoon Lee"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5078vnjy0qj89.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.15256",
  "fulltext_url": null,
  "id": "5078vnjy0qj89",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.15256",
  "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.IT"
    ],
    [
      "arxiv",
      "eess.IV"
    ],
    [
      "arxiv",
      "eess.SP"
    ],
    [
      "arxiv",
      "math.IT"
    ],
    [
      "openalex",
      "1707|Advanced Data Compression Techniques"
    ]
  ],
  "openalex": "W7213325320",
  "pdf_url": "https://arxiv.org/pdf/2609.15256",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-14",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/5078vnjy0qj89.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:29Z",
      "native_id": "2609.15256",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.15256"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.IT",
      "subfield": "general"
    }
  ],
  "title": "Thinking in Tokens, Talking in Bits: A Practical Interface for Token Communication",
  "title_text": "Thinking in Tokens, Talking in Bits: A Practical Interface for Token Communication",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:29Z",
  "url": "https://research.draconitic.com/paper/5078vnjy0qj89",
  "venue": "arXiv",
  "versions": []
}