用语音轨迹模拟记忆，实现无限上下文下的高速精准生成。
Memory as Resonance: A Biomimetic Architecture for Infinite Context Memory on Ergodic Phonetic Manifolds
- 将语言建模为非线性流形上的连续路径，取代传统静态缓存。
- 压缩比超3000倍，检索延迟仅约34毫秒，准确率达92%。
- 适合需要长上下文、低延迟的生成应用，如实时对话系统。
当前大模型的记忆受物理悖论制约：随着学习进行，内存逐渐耗尽。线性累积（O(N)）的键值状态将上下文视为静态数据仓库，最终迫使模型在遗忘与延迟之间做出毁灭性选择。我们挑战这一离散正统，提出长期记忆并非存储物品，而是轨迹的持续存在。我们引入语音轨迹记忆（PTM），一种神经符号架构，将语言编码为由无理旋转矩阵驱动的遍历流形上的连续路径。通过解耦导航（恒定的O(1)几何信号）与重建（概率生成行为），PTM相对于密集缓存实现了超过3000倍的压缩。我们证明，检索成为共振过程：语音痕迹通过“信号共识”机制稳定模型，防止幻觉，确保高达约92%的事实准确性。尽管这种激进抽象改变了生成质感，却实现了与深度无关的即时访问延迟（约34毫秒）。结果表明，无限上下文并不需要无限硅资源；它需要将记忆视为作用于持久不变物理信号的重建过程。
原文摘要 · Abstract (English)
The memory of contemporary Large Language Models is bound by a physical paradox: as they learn, they fill up. The linear accumulation (O(N)) of Key-Value states treats context as a warehouse of static artifacts, eventually forcing a destructive choice between amnesia and latency. We challenge this discrete orthodoxy, proposing that long-term memory is not the storage of items, but the persistence of a trajectory. We introduce Phonetic Trajectory Memory (PTM), a neuro-symbolic architecture that encodes language not as a sequence of tensors, but as a continuous path on an ergodic manifold governed by irrational rotation matrices. By decoupling the navigation (an invariant O(1) geometric signal) from the reconstruction (a probabilistic generative act), PTM achieves a compression magnitude of greater than 3,000x relative to dense caches. We demonstrate that retrieval becomes a process of resonance: the phonetic trace stabilizes the model against hallucination via "Signal Consensus" mechanism, securing up to approximately 92% factual accuracy. While this aggressive abstraction alters generative texture, it unlocks immediate access latency (approximately 34ms) independent of depth. Our results suggest that infinite context does not require infinite silicon; it requires treating memory not as data to be stored, but as a reconstructive process acting on a conserved, undying physical signal.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。