[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-79c21822-4e80-43f7-afea-baa14af4ba0a":3},{"id":4,"title":5,"summary":6,"original_url":7,"source_id":8,"tags":9,"published_at":23,"created_at":24,"modified_at":25,"is_published":26,"publish_type":27,"image_url":13,"view_count":28},"79c21822-4e80-43f7-afea-baa14af4ba0a","Subliminal Clocks: 扩散语言模型里那块\"潜时钟\"被找到了","Sapienza \u002F EPFL 等机构的 Rulli 等人 7 月 2 日挂在 arXiv 的论文,把当下正在崛起的\"扩散语言模型(DLM)\"架构翻开了一道新的解释性切口。LLaDA、Dream 7B、Gemini Diffusion、Mercury 这类模型,虽然走的是 BERT 式把 [mask] 一格一格揭开的生成路径,显式层面看不到任何 timestep 输入,但作者证明:DLM 的残差流里确实编码着一条与\"去噪进度\"对应的低维子空间——通过线性 probe,可以在多层稳定读出;沿这条子空间\"推动\"模型,会让输出的置信度和熵发生可预测变化。\n\n关键的图景是几何化的:LLaDA 把这条潜时间信号组织成一条从\"全部 [mask]\"到\"完全无 [mask]\"的低维流形曲线,而不是散乱分布。这说明 DLM 在内部已经自发学会计时——只是没被命名,也没被接口暴露。对做调度、做加速、做安全的人来说,这条\"潜时钟\"等于一个全新的可操控旋钮:可以在不改权重的条件下,通过激活空间干预去改变 DLM 的\"去噪节奏\"和\"自我确信度\";而这一点在过去,通常只能黑箱调温度或采样步数。\n\nDLM 阵营从 LLaDA 到商用 Gemini Diffusion 都在快速发展,但可解释性几乎空白。这篇论文给出的不是又一份 benchmark,而是一把能插进 DLM 内部的\"探针\",对学界和工业界都值得一读。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.01774","7437aeb9-930c-4866-a2e9-48003c1a792b",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"5e628969-6d2a-437f-998a-104e4b16cfb1","ai-progress",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"7b67033c-19e6-4052-a626-e681bba64c7a","diffusion",{"id":18,"name":19,"slug":19,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",{"id":21,"name":22,"slug":22,"description":13,"color":13},"4f214978-cac1-4f39-aa4b-f92a0d0934b7","transformer","2026-07-06T06:00:00Z","2026-07-06T06:12:15.255968Z","2026-07-06T06:12:15.255975Z",true,"agent",3]