mlsanityData to 7 Oct 2026

neuralCAD-Edit: An Expert Benchmark for Multimodal-Instructed 3D CAD Model Editing

arXiv 2604.16170 ↗First posted 17 Apr 2026cs.CV cs.CEcited by 3

Not on the map. Why?

Abstract (arXiv)

We introduce neuralCAD-Edit, the first benchmark for editing 3D CAD models collected from expert CAD engineers. Instead of text conditioning as in prior works, we collect realistic CAD editing requests by capturing videos of professional designers, interacting directly with CAD models in CAD software, while talking, pointing and drawing. We recruited ten consenting designers to contribute to this contained study. We benchmark leading foundation models against human CAD experts carrying out edits, and find a large performance gap in both automatic metrics and human evaluations. Even the best foundation model (GPT 5.2) scores 53% lower (absolute) than CAD experts in human acceptance trials, demonstrating the challenge of neuralCAD-Edit. We hope neuralCAD-Edit will provide a solid foundation against which 3D CAD editing approaches and foundation models can be developed. Code/data: https://autodeskailab.github.io/neuralCAD-Edit

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 44 of its 67 references that are in the map. First posted on arXiv 17 Apr 2026.

Builds on

44 of 67 references.

References · 44

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2023Segment Anythingcited by 8,158
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  5. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  6. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  7. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  8. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  9. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  10. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  11. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
  12. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
32 more
  1. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  2. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  3. 2022DiffEdit: Diffusion-based semantic image editing with mask guidancecited by 643
  4. 2022Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionalitycited by 523
  5. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  6. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 339
  7. 2023WhisperX: Time-Accurate Speech Transcription of Long-Form Audiocited by 320
  8. 2023Perception Test: A Diagnostic Benchmark for Multimodal Video Modelscited by 310
  9. 2025SAM 3D: 3Dfy Anything in Imagescited by 230
  10. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 229
  11. 2025TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Modelscited by 204
  12. 2021ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrationscited by 193
  13. 2025GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Taskscited by 142
  14. 2024BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometrycited by 101
  15. 2025HD-EPIC: A Highly-Detailed Egocentric Video Datasetcited by 101
  16. 2021JoinABLe: Learning Bottom-up Assembly of Parametric CAD Jointscited by 77
  17. 2025CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generationcited by 65
  18. 2025Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Modelscited by 43
  19. 2025Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilitiescited by 43
  20. 2024CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solverscited by 40
  21. 2025CADCrafter: Generating Computer-Aided Design Models from Unconstrained Imagescited by 31
  22. 2024Query2CAD: Generating CAD models using natural language queriescited by 28
  23. 2024CadVLM: Bridging Language and Vision in the Generation of Parametric CAD Sketchescited by 28
  24. 2025BlenderGym: Benchmarking Foundational Model Systems for Graphics Editingcited by 27
  25. 2025CADDreamer: CAD Object Generation from Single-view Imagescited by 22
  26. 2025CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editingcited by 19
  27. 2025AutoBrep: Autoregressive B-Rep Generation with Unified Topology and Geometrycited by 16
  28. 2025BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patchcited by 12
  29. 20253D-LATTE: Latent Space 3D Editing from Textual Instructionscited by 10
  30. 2025VideoCAD: A Dataset and Model for Learning Long-Horizon 3D CAD UI Interactions from Videocited by 9
  31. 2025GenCAD-3D: CAD Program Generation using Multimodal Latent Space Alignment and Synthetic Dataset Balancingcited by 7
  32. 2025MeshPad: Interactive Sketch-Conditioned Artist-Reminiscent Mesh Generation and Editingcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026CADEngBench: It Looks Like CAD, but Does It Work? Evaluating Parametric Design, Assembly Reasoning, and Physics Simulationcited by 3
  2. 2026CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Designcited by 1
  3. 2026AgenticCADedit: A Stateful, Tool-Mediated Agentic Approach to Multimodal 3D CAD Editingcited by 0