AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Energy-Efficient Random Variate Generation via Compressed Lookup Tables

Johann Ukrow, Anna Kazachkova, Nicolas Alder, Sven Köhler, Rainer Schlosser, Ralf Herbrich

ICLR 2026 · Architectures and efficiency › RNNs and normalization · approach: Distributed LLM inference systems

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use cLUT instead of JAX samplingdiscrete sampler · Python, n in [10^6,10^7)sampling time (s): 0.7982 -> 0.1016Improved
use cLUT instead of NumPy samplingdiscrete sampler · Python, n in [10^1,10^5)sampling time (s): 0.6680 -> 0.0374Improved
use cLUT instead of Alias methodC sampler · C, n in [10^7,10^8)energy per sample (nJ): 887.653 -> 450.155Improved
use cLUT instead of Alias methodC sampler · C, n in [10^3,10^4)time per sample (ns): 26.803 -> 15.475Improved
use cLUT instead of NumPy discrete samplerTrueSkill · TrueSkillsampling time and energy: 1.65 -> 0.46Improved
use cLUT instead of NumPy continuous mixture samplerTrueSkill · TrueSkillsampling time: 0.88 -> 0.46Improved
use cLUT instead of JAX default samplerdiffusion model · Diffusion modelenergy: 4702.91 -> 2962.17Improved
use cLUT instead of JAXdiscrete sampler preprocessing · Python, n in [10^6,10^7)preprocessing time (s): 0.6528 -> 0.3925Improved
use cLUT instead of NumPydiscrete sampler preprocessing · Python, n in [10^6,10^7)preprocessing time (s): 0.0308 -> 0.3925Hurt
use cLUT instead of Alias methodC sampler · peak memorymemoryHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy