AI Paper Atlas

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

Aligning Constraint Generation with Design Intent in Parametric CAD

Evan Casey, Tianyu Zhang, Shu Ishida, John Roger Thompson, Amir Khasahmadi, Joseph George Lambourne, Pradeep Kumar Jayaraman, Karl D.D. Willis

ICCV 2025 · Large language models › Agents, code and math · approach: Code generation benchmarks · 10 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
add supervised fine-tuning on solver-verified ideal sketchesVitruvion · SketchGraphs test% fully constrained: 8.87 -> 34.24Improved
add RLOO post-training with solver rewardsSFT Vitruvion · SketchGraphs test% fully constrained: 34.24 -> 93.05Improved
add GRPO post-training with solver rewardsSFT Vitruvion · SketchGraphs test% fully constrained: 34.24 -> 91.59Improved
add ReMax post-trainingSFT Vitruvion · SketchGraphs test% fully constrained: 34.24 -> 79.84Improved
add Iterative DPOSFT Vitruvion · SketchGraphs test% fully constrained: 34.24 -> 64.91Improved
add Expert IterationSFT Vitruvion · SketchGraphs test% fully constrained: 34.24 -> 71.70Improved
add ReMax post-trainingSFT Vitruvion · SketchGraphs test% stable (bins=4): 92.48 -> 75.77Hurt
add Iterative DPOSFT Vitruvion · SketchGraphs test% not solvable: 3.85 -> 7.64Hurt
use RLOO instead of Expert Iteration (online vs offline)Vitruvion · SketchGraphs testPass@1: 64.09 -> 83.57Improved
increase samples from 1 to 8 (ablation)RLOO · SketchGraphs testsuccess rate (Pass@K): 83.57 -> 84.96No clear effect
increase samples from 1 to 8 (ablation)SFT · SketchGraphs testsuccess rate (Pass@K): 33.32 -> 42.62Improved
add RLOO post-trainingSFT Vitruvion · SketchGraphs test (diversity)% Unique@8: 46.71 -> 32.11Hurt

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