About

Jie Deng is a research assistant at Zhejiang University, advised by Prof. Gaoang Wang (CVNext Lab), He obtained his B.S. in Electrcal Engineering from University of Washington, Seattle, and his M.S. in Electrical and Computer Engineering from Georgia Institute of Technology. Jie stays curious about the wider landscape of computer vision and deep learning, and actively seeks new collaboration opportunities. His work centers around virtual environment simulation/generation, generative models, and LLM reasoning. He is a highly self-motivated, and curious student applying to Ph.D. programs for 2026 Fall. He is also actively looking for research opprtunities.

Experiences

May. 2023 -- Present, Zhejiang University, Hangzhou, China
Research Assistant, Advised by Prof. Gaoang Wang.

Education

M.S. 2021 - 2023 Georgia Institute of Technology, Atlanta, USA. M.S. in Electrical and Computer Engineering
B.S. 2015 - 2019 University of Washington (UW) , Seattle, USA. B.S. in Electrical and Computer Engineering

Selected Publications

* Equal contribution. ‡ Corresponding author.

Also see Google Scholar.

CityGen: Infinite and Controllable City Layout Generation

Jie Deng*, Wenhao Chai*, Jianshu Guo*, Qixuan Huang, Jeng-Neng Hwang, Gaoang Wang‡

[Paper] [Code]

CityGen is a city layout generation framework that can generate infinite and controllable city layouts.

CityCraft: A Diffusion and LLM Powered Framework for Automatic Comprehensive Virtual City Generation

Jie Deng*, Wenhao Chai*, Junsheng Hwang*, Zhonghan Zhao, Qixuan Huang, Jianshu Guo, Mingyan Gao, Xi Li, Jeng-Neng Hwang, Der-Horng Lee‡, Gaoang Wang‡

[Paper] [Code]

CityCraft is a comprehensive virtual city generation framework that leverages diffusion models to generate realistic and diverse city layouts, and large language models to generate for urban landuse planning, and Blender for procecural modeling.

Rare Heart Transplant Rejection Classification Using Diffusion-based Synthetic Image Augmentation

Han Bao*, Jie Deng*, Shihao Xing, Wenqi Shi, Benoit Marteau, Bibhuti Das, Bahig Shehata, Shriprasad Deshpande, May D. Wang‡

[Paper]

In this work, we developed an automated diagnosis pipeline to streamline the heart transplant histopathology image quantification and classification, in order to provide objectivity for clinical decision support for pathologists.

Top