linear attention
AssessTechniques
An attention formulation that avoids quadratic cost by restructuring the computation.
Why it's here
Placed in Assess: 4 article(s) of evidence from 2 source(s), led by research-stage coverage, with 0 in the last 30 days. Confidence 48%.
Evidence (4)
- 3Hacker News·8/18/2026researchUsing railway motion as a flatbed scanner
The article describes a project that uses an industrial linear scanning camera to capture ultra-wide images from moving trains and ferries by stitching successive vertical slices into a single frame. The author discusses the technical challenges of compensating for motion and producing cleaner scan-line images, drawing on prior scanning-back and slit-scanning techniques.
- 5Ars Technica AI·7/29/2026researchAI Applied to Deciphering Lost Languages
The article examines efforts to use AI to help decipher ancient languages that lack the usual anchors, such as bilingual inscriptions or close relatives. It highlights Linear A and Etruscan as difficult cases where traditional linguistic methods have not yet fully solved the writing systems or their grammar.
- 4Hacker News·7/28/2026researchWalkthrough of the DeltaNet family of linear attention variants
This article explains how the DeltaNet family of linear attention methods is derived, starting from standard causal softmax attention and progressively simplifying it into linear attention forms. It then connects these ideas to DeltaNet, Gated DeltaNet, and Kimi Delta Attention, with an emphasis on the underlying state updates and how they can be implemented recurrently and chunkwise.
- 8Hacker News·6/28/2026researchLineShine Becomes No. 1 on the TOP500 at ISC 2026
At ISC 2026, the TOP500 list crowned LineShine in Shenzhen, China as the new No. 1 supercomputer, powered by a large CPU-only Armv9 system. The report also notes LineShine's strong HPCG performance, Italy's new HPC7 system entering the top ranks, and Fugaku remaining highly competitive despite its age.