HuggingFace Daily Papers·· 2 天前
KronLSTM：基于 Kronecker Delta Rule 的长上下文线性注意力架构
Kronecker Delta Rule for Long Context Linear Attention
AI 导读
研究者提出 KronLSTM，一种基于 Kronecker Delta Rule 的线性注意力架构，通过单方向修正目标关联来减少对已存储信息的干扰，适合长上下文语言建模。
正文 · 原文
Abstract:We propose KronLSTM, a linear attention architecture based on the Kronecker Delta Rule, a novel update rule for associative matrix memories. KronLSTM extends the xLSTM family with a memory-revision mechanism that corrects targeted associations while modifying the memory only along a single direction in matrix space. This minimally invasive memory revision reduces interference with previously stored information compared with delta-rule updates, making it particularly well suited for long-context language modeling. The resulting memory dynamics can be mathematically described as a Markov chain that converges to a steady-state distribution, while the expected norm of the memory matrix remains uniformly bounded throughout the entire input sequence. Hence, KronLSTM ensures stable memory dynamics without requiring additional normalization and stabilization mechanisms for the memory state. Experiments show that KronLSTM is competitive with, and often outperforms, existing linear attention architectures, including models of the (Gated) DeltaNet family, with particularly strong performance on long context benchmarks. These results establish the Kronecker Delta Rule as an effective and analytically tractable foundation for stable associative memory in recurrent linear attention architectures. Our code (this https URL) and models (this https URL) are open-source.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.26834 [cs.LG] |
| (or arXiv:2610.26834v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.26834 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Anamaria-Roberta Hartl [view email]
[v1]
Mon, 19 Oct 2026 17:56:52 UTC (267 KB)
来源：HuggingFace Daily Papers · arxiv.org