Yu Fang

I am a second year Ph.D. student in Computer Science at the University of North Carolina at Chapel Hill, working with Prof. Mingyu Ding and Prof. Daniel Szafir. Before that, I obtained my master’s degree at ShanghaiTech University, advised by Prof. Dinggang Shen and Prof. Zhiming Cui.

I am broadly interested in embodied AI and 3D vision. My long-term goal is to bridge the gap between simulation and the real world, and to develop agents with human-level perception and reasoning. My current focus includes: 1) synthetic data generation for sim-to-real applications, 2) VLAs for robotic manipulation, and 3) 3D/4D perception on robots and AI glasses from egocentric viewpoints.

Publications

ReBot: Scaling Robot Learning with Real-to-Sim-to-Real Robotic Video Synthesis

Yu Fang, Yue Yang, Xinghao Zhu, Kaiyuan Zheng, Gedas Bertasius, Daniel Szafir, Mingyu Ding.

arXiv, 2025.

[project page] [paper]

Geometry-Aware Attenuation Field Learning for Sparse-View CBCT Reconstruction

Zhentao Liu, Yu Fang, Changjian Li, Han Wu, Yuan Liu, Zhiming Cui, Dinggang Shen.

IEEE Transactions on Medical Imaging (TMI), 2024.

[project page] [paper] [code]

SNAF: Sparse-view CBCT Reconstruction with Neural Attenuation Fields

Yu Fang, Lanzhuju Mei, Changjian Li, Yuan Liu, Wenping Wang, Zhiming Cui, Dinggang Shen.

arXiv, 2022.

[paper]

Curvature-enhanced Implicit Function Network for High-quality Tooth Model Generation from CBCT Images

Yu Fang, Zhiming Cui, Lei Ma, Lanzhuju Mei, Bojun Zhang, Yue Zhao, Zhihao Jiang, Yiqiang Zhan, Yongsheng Pan, Min Zhu, Dinggang Shen.

International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2022.

[paper] [pdf] [poster] Early Accept

A Fully Automatic AI System for Tooth and Alveolar Bone Segmentation from Cone-beam CT Images

Zhiming Cui*, Yu Fang*, Lanzhuju Mei*, Bojun Zhang*, Bo Yu, Jiameng Liu, Caiwen Jiang, Yuhang Sun, Lei Ma, Jiawei Huang, Yang Liu, Yue Zhao, Chunfeng Lian, Zhongxiang Ding, Min Zhu, Dinggang Shen.

Nature Communications, 2022.

[paper] [pdf] [code]