AI模型内部有个“隐形时钟”
扩散语言模型（DLM）是一种新型AI，它生成文本时不像传统模型那样一步步“猜下一个词”，而是从一团噪声中逐渐“还原”出句子。但奇怪的是，这类模型并没有被明确告知当前处于还原的哪个阶段。这篇研究发现，模型内部其实偷偷藏了一个“隐形时钟”——它的神经元活动里编码了当前去噪进度的信号。研究者不仅能从模型内部读出这个“时间”，还能通过微调这个信号，让模型变得更自信或更犹豫。这就像你发现一个黑箱里其实有刻度盘，虽然设计时没装，但它自己长出来了。这不是你明天能用的功能，但它揭示了AI内部可能自发形成我们没教过的抽象概念，对理解模型行为有启发。
📄 原文摘要(英文)
Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive models. Unlike standard diffusion-based approaches, DLMs are not explicitly conditioned on a timestep, raising a natural question: do these models internally represent denoising progress, and how is such information used downstream? In this work, we show that DLMs do in fact encode a latent representation related to the diffusion timestep within their residual streams. We find that this signal can be reliably extracted using probes across layers, indicating that denoising progress is decodable from internal activations. We further demonstrate that steering the model along a low-dimensional subspace associated with the inferred timestep allows us to systematically modulate its notion of denoising progress, leading to predictable changes in model confidence and entropy. Finally, we analyse the geometry of the identified representation, showing that it exhibits structured and interpretable properties in activation space, and shedding light on how such a signal is processed by these models.