AI4CE Lab

AI4CE Lab

The AI4CE lab (pronounced "A-I-force") at New York University conducts multidisciplinary use-inspired research to develop novel algorithms and systems for intelligent agents to accurately understand and efficiently interact with materials and humans in dynamic and unstructured environments.

Selected publications11

All publications →
GARF: Learning Generalizable 3D Reassembly for Real-World Fractures

GARF: Learning Generalizable 3D Reassembly for Real-World Fractures

Sihang LiZeyu JiangGrace ChenChenyang XuSiqi TanXue WangIrving FangKristof ZyskowskiShannon P. McPherronRadu IovitaChen FengJing Zhang

Assembly

ICCV 2025
Metric-Free Exploration for Topological Mapping by Task and Motion Imitation in Feature Space

Metric-Free Exploration for Topological Mapping by Task and Motion Imitation in Feature Space

Yuhang HeIrving FangYiming LiRushi Bhavesh ShahChen Feng

Navigation

RSS 2023
VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion

VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion

Yiming LiZhiding YuChris ChoyChaowei XiaoJose M. AlvarezSanja FidlerChen FengAnima Anandkumar

3D Learning Highlight

CVPR 2023
DeepMapping: Unsupervised Map Estimation From Multiple Point Clouds

DeepMapping: Unsupervised Map Estimation From Multiple Point Clouds

Li DingChen Feng

Mapping Oral

CVPR 2019
FoldingNet: Point cloud auto-encoder via deep grid deformation

FoldingNet: Point cloud auto-encoder via deep grid deformation

Yaoqing YangChen FengYiru ShenDong Tian

3D Learning Spotlight

CVPR 2018

Current members28

All people →

Funding

We are grateful for support from the following agencies, organizations and companies.

Visitors