arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2609.15256eess.SPcs.ITeess.IVmath.IT

以令牌思考,以比特交谈:令牌通信的实用接口

Thinking in Tokens, Talking in Bits: A Practical Interface for Token Communication

Chanho Park, Bumsu Park, Soonhee Kwon, Sangrim Lee, Namyoon Lee

首次发表
浏览论文内容

中文总结 AI 辅助

提出令牌-比特接口,让令牌控制比特的生成与保护,实现图像分类中优于分离编码、媲美神经联合编码的精度-延迟性能。

中文摘要 AI 辅助

先进的人工智能模型以令牌(token)进行思考;当代通信系统传输比特(bit)。弥合这一差距的直接方式是传输令牌,但这会使模型特定的表示成为空中接口的一部分,通过共享的令牌化器、码本以及通常的神经收发器将端点耦合在一起。我们采取不同的路线:在有效载荷中保留比特,让令牌控制这些比特如何生成和保护。由此产生的令牌-比特接口转换将任务侧令牌与信源和信道编码单元对齐,将令牌相关性转化为编解码器控制,并在整个编码链中保持所诱导的优先级顺序。我们将其应用于图像分类任务,其中视觉变换器(vision transformer)根据其注意力图为每个图像区域的任务相关性打分:这些分数引导分块JPEG速率分配,然后对压缩比特进行分组,以不同的极化码速率进行保护。有效载荷仍然是由相应配置的译码器恢复的显式、可重建的比特流。在软件定义无线电测试平台上的空中实验表明,与分离的信源信道编码相比,在精度-延迟权衡方面有所改善,性能与内存密集度更高的神经联合信源信道编码相当,并且在信道失配下具有优雅的退化。因此,令牌通信不必显式传输令牌;它需要的是一个接口,通过该接口令牌决定比特如何通信。

英文摘要

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.

发表机构

  • Department of Electrical Engineering, POSTECH(POSTECH电气工程系)
  • LG Electronics(LG电子)

机构由 AI 辅助整理,请以论文原文为准。

补充信息

↑