AI Paper Atlas

Research map / Large language models / Agents, code and math

Computer-Aided Design as Language

NeurIPS 2021 · Large language models › Agents, code and math · approach: Neural program synthesis and transpilation · 40 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 triplet rather than byte serializationUnconditional sketch generation · Onshape test sketchesaverage bits/sketch: 133.281 -> 127.607Helped
Interleave each constraint after the entities it refers to (ablation)Byte sketch model · Onshape test sketchesaverage bits/sketch: 133.281 -> 128.053Helped
Interleave each constraint after the entities it refers to (ablation)Triplet sketch model · Onshape test sketchesaverage bits/sketch: 127.607 -> 122.818Helped
Condition generation on the sketch renderTriplet sketch model · Image-conditioned Onshape test sketchesaverage bits/sketchHelped
Compress byte sequences with Brotli (ablation)Byte sketch model · Onshape training datatraining objectiveHurt
Apply nucleus sampling with top-p 0.9 (ablation)Unconditional byte and triplet models · Generated sketchesinvalid-sample rate: 36 % -> 25 %; 14 % -> 6 %Helped

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