Signals 4 · free daily AI digest

LoGo: Token-Level Dynamic Local-Global Attention

Paper recorded by Signals 4 on 2026-08-30 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-08-30 on arXiv · recorded by Signals 4 on 2026-09-01

Category: cs.LG · 机器学习 · first seen 2026-09-01

Abstract

As context lengths scale, attention increasingly becomes a primary computational bottleneck in large language models. Standard Transformers remain powerful but computationally inefficient, as they allocate the same attention budget to every token regardless of its contextual demand. Existing local-global hybrids provide a more efficient alternative by mixing restricted- and full-context attention,

Read on arXiv →

#198 most recent of 215 cs.LG papers we have recorded · ↑ newer: BEACON: Behavioral and Semantic Enrichment of AlphaEarth Embeddings th · ↓ older: MedCache: Efficient and Temporally Valid Memory for Longitudinal Clini
Cite this page: LoGo: Token-Level Dynamic Local-Global Attention: the #198 most recent of 215 cs.LG papers we have recorded (as of 2026-08-30). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/logo-token-level-dynamic-local-global-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