Pith. sign in

Hire: High recall approximate top-kestimation for efficient llm inference

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1 cs.SE 1

years

2026 2

verdicts

UNVERDICTED 2

roles

background 1

polarities

background 1

representative citing papers

Stochastic Sparse Attention for Memory-Bound Inference

cs.LG · 2026-05-03 · unverdicted · novelty 6.0

SANTA replaces full value-cache multiply-accumulates with stochastic gather-and-add sampling from the attention distribution to reduce memory bandwidth while preserving an unbiased estimator.

citing papers explorer

Showing 2 of 2 citing papers.