AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solvers

Dimitrios Mallis, Ahmet Serda Karadeniz, Sebastian Cavada, Danila Rukhovich, Niki Foteinopoulou, Kseniya Cherenkova, Anis Kacem, Djamila Aouada

ICCV 2025 · Vision-language and multimodal › Robot action and navigation · approach: Embodied multimodal LLM agents · 44 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
use JSON point-based serialization instead of the SGPBench implicit serialized graph (ablation)GPT-4o CAD sketch QA · SGPBench 2D CQAaccuracy: 0.674 -> 0.748Improved
use schema-embedded JSON instead of tabular HTML (ablation)GPT-4o CAD sketch QA · SGPBench 2D CQAaccuracy: 0.710 -> 0.748Improved
use point-based instead of implicit parametrization with serialized graph (ablation)GPT-4o CAD sketch QA · SGPBench 2D CQAaccuracy: 0.674 -> 0.744Improved
over-parametrize sketches instead of point-based only (ablation)JSON serialization · SGPBench 2D CQAaccuracy: 0.748 -> 0.747No clear effect
give precise rendering instead of hand-drawn sketch image (ablation)GPT-4o CAD sketch QA · SGPBench 2D CQAaccuracy: 0.616 -> 0.754Improved
use rendering instead of text-based serialization (ablation)GPT-4o CAD sketch QA · SGPBench 2D CQAaccuracy: 0.748 -> 0.754Improved
add CAD-Assistant tool augmentation to GPT-4o plannerGPT-4o · SGPBench 2D CQAaccuracy: 0.686 -> 0.791Improved
add CAD-Assistant tool augmentation to GPT-4o plannerGPT-4o · SGPBench 3D CQAaccuracy: 0.782 -> 0.857Improved
add CAD-Assistant tool augmentation to smaller GPT-4 mini plannerGPT-4 mini · SGPBench 2D CQAaccuracy: 0.594 -> 0.614No clear effect
add multimodal sketch recognizer (MMrecog) (ablation)CAD-Assistant 0-shot · SketchGraphs autoconstrainingCF1: 0.318 -> 0.329Improved
add constraint checker (ConstrCheck) on top of MMrecog (ablation)CAD-Assistant 0-shot · SketchGraphs autoconstrainingCF1: 0.329 -> 0.484Improved
add 5-shot demonstrations (ablation)CAD-Assistant · SketchGraphs autoconstrainingCF1: 0.484 -> 0.529Improved

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