Liyuan Deng — accepted AI-conference papers

2026

BrepVGAE: Variational Graph Autoencoder with Unified Latent Representation for B-rep

Hao Guo, Liyuan Deng, Yongkang Dai, Ruohan Wang, Jiahao Li, Yunpeng Bai +1

CVPR 2026

Due to the heterogeneity of faces and edges in B-rep, conventional graph-based representations is incapable of establishing a unified formulation for faces and edges, thereby constraining the capabilities of B-rep generative models. We propose a B-rep Variational Graph Auto Encoding (BrepVGAE), the

Cited by 0 Source ↗Scholar ↗

2025

MamTiff-CAD: Multi-Scale Latent Diffusion with Mamba+ for Complex Parametric Sequence

Liyuan Deng, Yunpeng Bai, Yongkang Dai, Xiaoshui Huang, Hongping Gan, Dongshuo Huang +2

ICCV 2025poster

Parametric Computer-Aided Design (CAD) is crucial in industrial applications, yet existing approaches often struggle to generate long sequence parametric commands due to complex CAD models' geometric and topological constraints. To address this challenge, we propose MamTiff-CAD, a novel CAD parametr…

Cited by 0 Source ↗PDF ↗Scholar ↗