AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Bidirectional Query-Driven Generation of Parametric CAD Sketch

Yang Liu, Daxuan Ren, Yijie Ding, Jianmin Zheng, Fang Deng

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling

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 bidirectional query mechanism (ablation)CADSketcher · Partial-to-full completion (SketchGraphs)F1: 48.6 -> 59.2Improved
add hybrid positional encoding (ablation)CADSketcher · Partial-to-full completion (SketchGraphs)F1: 57.0 -> 59.2Improved
add confidence gate for expansion direction (ablation)CADSketcher · Partial-to-full completion (SketchGraphs)F1: 51.5 -> 59.2Improved
add validity compiler (ablation)CADSketcher · Partial-to-full completion (SketchGraphs)Invalid rate: 0.03 -> 0Improved
add validity compiler (ablation)CADSketcher · Partial-to-full completion (SketchGraphs)F1: 52.8 -> 59.2Improved
add iterative partial context updating (ablation)CADSketcher · Partial-to-full completion (SketchGraphs)F1: 50.9 -> 59.2Improved
add bidirectional query mechanism (ablation)CADSketcher · Partial-to-full completion (SketchGraphs)ACC_skt: 33.7 -> 45.6Improved
use CADSketcher instead of Vitruvion autoregressive baselineparametric sketch completion · Partial-to-full completion (SketchGraphs)ACC_tok: 35.2 -> 72.8Improved
use CADSketcher on out-of-distribution datasetCADSketcher · Cross-dataset: CAD as a Language, partial-to-fullACC_skt: 7.96 -> 14.1 vs Dual-ARImproved
CADSketcher versus CAD-VLM on early-stage expansion coverageCADSketcher · Early-stage sketch expansion (SketchGraphs)COV: 75.2 -> 77.0Improved

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