Thinking in Tokens, Talking in Bits: A Practical Interface for Token Communication
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.
Related
- On generalized k-token graphs with distinguishable tokens and a maximum capacity of s tokens per vertex
- On generalized token graphs with tokens of different colors
- Automorphisms of Token Graphs That Send $4$-Cycles Generated by Two Edges to Cycles Generated by a $4$-Cycle and Two Tokens
- Why Adaptive Optimizers Underestimate Rare Tokens
- Interactive Visualization for Geometry Learning: The Impact of Augmented Reality on Students' Critical Thinking Skills
BibTeX
@misc{park2026thinking,
title = {{Thinking in Tokens, Talking in Bits: A Practical Interface for Token Communication}},
author = {Chanho Park and Bumsu Park and Soonhee Kwon and Sangrim Lee and Namyoon Lee},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.15256},
eprint = {2609.15256},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.15256},
}
RIS
TY - UNPB
TI - Thinking in Tokens, Talking in Bits: A Practical Interface for Token Communication
AU - Chanho Park
AU - Bumsu Park
AU - Soonhee Kwon
AU - Sangrim Lee
AU - Namyoon Lee
PY - 2026
DA - 2026/09/14
PB - arXiv
DO - 10.48550/arxiv.2609.15256
UR - https://arxiv.org/abs/2609.15256
AB - 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.
ER -