The paper examines how boundary representation (B‑rep) encoders for CAD models fail to handle variations that do not change the underlying solid, such as different modeling operations or software export settings. By demonstrating that existing encoders collapse under these perturbations, the authors introduce the canonical region graph, a representation derived directly from the solid that is theoretically invariant to repartitioning and rigid motions. This new input format matches the best baseline on standard benchmarks and remains stable across all tested perturbations.
By Heinrich Jiang, Hager Yasser Mohamed, Alexander Hitt, Valeriia Lomakina, Henning Jiang, Jennifer Jang
Boundary representation (B‑rep) is the standard format for parametric 3D models in CAD systems, yet the same solid can be encoded by different B‑reps due to varying operations, kernel rebuilds, or export settings. Existing B‑rep encoders fail to handle these variations, collapsing on standard benchmarks and real‑world perturbations. The authors introduce the canonical region graph, an input representation derived directly from the solid, which offers theoretical invariance to repartitioning and rigid motions and performs as well as the best baseline while remaining stable across all tested perturbations.
arXiv:2608.28853v1 Announce Type: cross
Abstract: Equivariant graph neural networks provide a principled way to model geometric systems, but efficient first-order architectures remain limited in how...
By Alessio Borgi, Mario Severino, Fabrizio Silvestri, Pietro Li\`o
arXiv:2607. 20642v1 Announce Type: cross Abstract: Computer aided design (CAD) is ubiquitous: virtually any modern object was designed using editable CAD tools.
By Heinrich Jiang, Jennifer Jang
arXiv:2608.31045v1 Announce Type: new
Abstract: Rotational symmetry is one of the most important structural principles in machine learning on 3D data. In applications ranging from physics and materia...
By Peter Lippmann, Fred A. Hamprecht
arXiv:2506. 09398v4 Announce Type: replace Abstract: We consider the task of predicting Hamiltonian matrices to accelerate electronic structure calculations, which plays an important role in physics, chemistry, and materials science.
By Haiyang Yu, Yuchao Lin, Xuan Zhang, Xiaofeng Qian, Shuiwang Ji
arXiv:2607. 03798v1 Announce Type: cross Abstract: Symmetry is everywhere in nature and society.
By Yoshihiro Maruyama
MidSurfNet is a learning-based method for pairing faces in thin‑walled CAD models, addressing the key subproblem of mid‑surface abstraction for finite element analysis. It uses a dual‑stream scorer—one geometry stream and one attributed‑topology stream—fused by a pair‑conditioned gate to make per‑pair decisions that replace manual thresholds. The method organizes retained relations into variable‑cardinality face groups independent of processing order, and on a new MidSurf dataset of 1,575 annotated models it achieves an 87.32% pair‑level F1‑score and a 75.42% completion rate, outperforming rule‑based baselines, especially on multi‑wall‑thickness cases.
By Li Ye, Xinhang Zhou, Xingyu Yang, Ruofeng Tong, Hailong Li, Peng Du, Min Tang
arXiv:2610.16822v1 Announce Type: cross
Abstract: Architecture attribute predictors reduce the cost of neural architecture search by estimating accuracy or latency from a small set of evaluated candi...
By Yuxiang Zeng, Kun Xie, Yang Wang, Jigang Wen, Xiaocan Li, Guangxing Zhang, Gaogang Xie, Jiannong Cao
arXiv:2607. 04262v1 Announce Type: new Abstract: Convolutional Neural Network (CNN) and Vision Transformer (ViT) for image classification exploit a dense grid of pixels containing redundant information.
By Sarabeshwar Balaji, Shubham Mohanty, Akash Anil
GraphCAD introduces a geometry-aware generative framework for Computer-Aided Design (CAD) that models CAD construction using an Edge-Adjacency Graph (EAG), a novel graph-based representation. The method employs a hybrid graph diffusion process to jointly capture discrete topological connectivity and continuous spatial geometry, and incorporates a geometry-aware denoising mechanism that maps node attributes to SE(3)-equivariant encoded point sets. Experiments on the newly created EAGBench dataset demonstrate that GraphCAD can generate complex CAD models with more than 50 faces, achieving state‑of‑the‑art geometric fidelity and distributional alignment compared to sequence‑based baselines.
By Wenhao Zheng, Xianggen Liu, Li Yue, Jiancheng Shi, Jiancheng Lv
arXiv:2601. 16622v2 Announce Type: replace-cross Abstract: Equivariant Graph Neural Networks (EGNNs) have become a widely used approach for modeling 3D atomistic systems.
By Lin Huang, Chengxiang Huang, Ziang Wang, Yiyue Du, Chu Wang, Haocheng Lu, Yunyang Li, Xiaoli Liu, Arthur Jiang, Jia Zhang