arXiv 2610.26834 · cs.LG · 2026-10-19

Kronecker Delta Rule for Long Context Linear Attention

Anamaria-Roberta Hartl, Levente Zólyomi, Michael List, Günter Klambauer, Sebastian Böck, Sepp Hochreiter

NX-AI

在最新榜 #304 本站收录于 2026-10-22

一句话要点

KronLSTM 提出克罗内克 Delta 规则，只沿单一方向修正记忆矩阵，让长上下文线性注意力更稳定。

KronLSTM introduces a Kronecker delta rule that revises matrix memory along one direction, giving stable long-context linear attention that often beats DeltaNet.

28HF 点赞

–GitHub stars

–引用（Semantic Scholar）

35.3热度分

阅读 arXiv 原文 PDF Hugging Face 讨论

主题与学科

高效训练与推理大语言模型

AI × 数学

同主题：高效训练与推理

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation ▲511
Scaling Properties of Same-Family On-Policy Distillation ▲327
Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation ▲251
On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics ▲205
Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation ▲181

数据说明

元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。

要点由本站根据摘要自写，不转载摘要原文，请阅读原文。