Signals 4 · free daily AI digest

Complex KDA: Understanding and Enhancing the Expressivity of Kimi Delta Attention

Paper recorded by Signals 4 on 2026-09-21 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-21 on arXiv · recorded by Signals 4 on 2026-09-22

Category: cs.LG · 机器学习 · first seen 2026-09-22

Abstract

Linear RNNs based on the delta-rule enable efficient sequence modeling, but their linear updates with a low-rank correction constrain their expressivity. Prior work has shown that composing two delta-rule transitions in a single recurrent update can model a 2D rotation, but this increases the rank and the cost of the updates compared to a single transition. We show that Kimi Delta Attention (KDA)

Read on arXiv →

#11 most recent of 250 cs.LG papers we have recorded · ↑ newer: Mobile Imaging Solutions for Medical Diagnosis: Trends and Application · ↓ older: Detecting Agitation Before Behavioral Escalation in Autistic Youth Thr
Cite this page: Complex KDA: Understanding and Enhancing the Expressivity of Kimi Delta Attention: the #11 most recent of 250 cs.LG papers we have recorded (as of 2026-09-21). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/complex-kda-understanding-and-enhancing-the-expressivity-of-kimi-delta-attention.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions