AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Improving Text-guided CAD Prototyping via Modality-Specific Tokenization

Ruiyu Wang, Shizhao Sun, Weijian Ma, Jiang Bian

ICLR 2026 · Large language models › Language, safety and interpretability · approach: Controlled text generation

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 primitive pooling (curve-based) to the tokenizer instead of single sketch-extrusion unit (ablation)CAD-Tokenizer · Text-to-CADF1-Avg: 78.3 -> 86.5Improved
add primitive pooling (curve-based) to the tokenizer instead of single sketch-extrusion unit (ablation)CAD-Tokenizer · Text-to-CADinvalidity ratio: 70.7 -> 4.94Improved
pool loops instead of curves (ablation)CAD-Tokenizer · Text-to-CADF1-Avg: 86.5 -> 86.3No clear effect
use pooling loops instead of curves for reconstruction (ablation)CAD-Tokenizer · reconstructionF1-Skt: 94.1 -> 91.5Hurt
replace BPE with CAD-Tokenizer (ablation)LLaMA SFT · Text-to-CADF1-Avg: 76.2 -> 86.5Improved
add FSA-guided decoding instead of top-p sampling (ablation)CAD-Tokenizer · Text-to-CADF1-Avg: 80.4 -> 86.5Improved
add FSA-guided decoding instead of beam search (ablation)CAD-Tokenizer · Text-to-CADinvalidity ratio: 45.2 -> 4.94Improved
use CAD-Tokenizer instead of Vanilla-LLaMA tokenizer on editingLLaMA · CAD editingF1-Skt: 78.8 -> 88.6Improved
use CAD-Tokenizer instead of Vanilla-LLaMA tokenizer on generationLLaMA · Text-to-CADinvalidity ratio: 80.5 -> 1.50Improved
compare CAD-Tokenizer against task-specific CADFusion on VLM scoreCADFusion · Text-to-CADVLM score: 5.41 -> 3.82Hurt
use CAD-Tokenizer instead of task-specific CAD-EditorCAD-Editor · CAD editingF1-Skt: 73.3 -> 88.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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