Constant-Memory Recall: Learned Associations in a Fixed Matrix State

1. 12:00
   arXiv · Machine Learning Theory

   Constant-Memory Recall: Learned Associations in a Fixed Matrix State

   论文研究了一个小规模 DeltaNet 变体，在 32 KiB 固定循环矩阵状态下记忆 32 个键值对，达到 99.95% 平均准确率。填充上下文扩展至 1,798 tokens 时召回率仍接近完美，但清零第一块记忆后召回消失。参数匹配的向量和 Transformer 基线仍接近随机水平，包括额外搜索训练后的 Transformer。

Current heat 9·Comparable peak 10（Oct 2）·Comparable change over 24 hours –

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.