Hang Long — accepted AI-conference papers

2026

LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtents

Tianhao Zhao, Youjia Zhang, Hang Long, Jinshen Zhang, Wenbing Li, Yang Yang +4

ICML 2026poster

In this paper, we introduce LATO, a novel topology-preserving latent representation that enables scalable, flow matching-based synthesis of explicit 3D meshes. LATO represents a mesh as a Vertex Displacement Field (VDF) anchored on surface, incorporating a sparse voxel Variational Autoencoder (VAE) …

Cited by 0 Source ↗Scholar ↗

2026

MeshRipple: Structured Autoregressive Generation of Artist-Meshes

Junkai Lin, Hang Long, Huipeng Guo, Jielei Zhang, Jiayi Yang, Tianle Guo +5

CVPR 2026

Meshes serve as a primary representation for 3D assets. Autoregressive mesh generators serialize faces into sequences and train on truncated segments with sliding-window inference to cope with memory limits. However, this mismatch breaks long-range geometric dependencies, producing holes and fragmen

Cited by 0 Source ↗Scholar ↗