MoSAR: Mixture of Semantic Attention Regimes for Learning Adaptive and Approximable Attention Geometries
Paper recorded by Signals 4 on 2026-09-25 in cs.CL. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-25 on arXiv · recorded by Signals 4 on 2026-09-28
Category: cs.CL · 自然语言处理 · first seen 2026-09-28
Abstract
The quadratic complexity of dense self-attention remains a central bottleneck for long-context language modeling. Many efficient alternatives address this cost by deciding in advance where attention should be sparse or local. We argue that attention approximation should instead be approached as a geometric problem, with the relevant interaction geometry learned from data: natural-language dependen
Read on arXiv →
Cite this page: MoSAR: Mixture of Semantic Attention Regimes for Learning Adaptive and Approximable Attention Geometries: the #15 most recent of 267 cs.CL papers we have recorded (as of 2026-09-25). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/mosar-mixture-of-semantic-attention-regimes-for-learning-adaptive-and-approximab.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free