← 研踪 PaperTrailarXiv:2610.29526 · v2
Geometric state space, memory representation and architectures
首次提交 2026-10-21 18:14
版本更新 2026-11-18 03:14
雷达观测 2026-11-19 19:08
摘要
We introduce a geometric framework for deriving attention architectures. A sequence forms a memory , and an attention pairing determines how that memory acts on each token state. Different representations of this action recover familiar architectures: softmax attention reads individual key--value pairs, linear attention accumulates their contributions in matrix statistics, and Intention fits a regression map from keys to values. The framework also suggests new architectures by changing the geometry of the query--key pairing, the function carried by each value, or the space representing the memory. ImageNet-1K experiments illustrate these constructions through geometric CAFormer variants, a ViT with query-dependent values, and a linear ViT with a wider memory representation.
作者备注:14 pages
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-18 03:14 · 最新观测版本
Geometric state space, memory representation and architectures
We introduce a geometric framework for deriving attention architectures. A sequence forms a memory , and an attention pairing determines how that memory acts on each token state. Different representations of this action recover familiar architectures: softmax attention reads individual key--value pairs, linear attention accumulates their contributions in matrix statistics, and Intention fits a regression map from keys to values. The framework also suggests new architectures by changing the geometry of the query--key pairing, the function carried by each value, or the space representing the memory. ImageNet-1K experiments illustrate these constructions through geometric CAFormer variants, a ViT with query-dependent values, and a linear ViT with a wider memory representation.
查看此版本解读 →查看此版本原文 ↗