AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Transformers in Pseudo-Random Number Generation: A Dual Perspective on Theory and Practice

Ran Li, Lingshu Zeng

AAAI 2026 · Architectures and efficiency › Attention and transformers · approach: Transformer expressivity and learnability · 1 citations (OpenAlex)

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
train GPT-2 on MT19937 output at 8, 12 and 16 bitsGPT-2 · MT19937 simulationtraining accuracy: approximately 1.0 at all bit-widthsImproved
increase bit-width from 8 to 16 (ablation)GPT-2 · MT19937 simulationconvergence steps: 500 steps -> 1,000 -> 2,000 stepsHurt
generate from Transformer checkpoints at accuracy 0.63-0.89GPT-2 PRNG · NIST STStests passed: 11 of 15 passedMixed

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