Chaochao Yan

Ph.D. student in Computer Science at UT Arlington

About me

I am a Ph.D. student in Computer Science starting from 2017 at the University of Texas at Arlington, USA. My current research interests focus on drug discovery and medical images analysis. My supervisor is Dr. Junzhou Huang.

Previously, I received my master's degree from the Institute of Automation, Chinese Academy of Sciences(CASIA) in 2017. I worked on 3D computer vision for my master in Robot Vision Group, National Laboratory of Pattern Recognition(NLPR). In 2014, I got my bachelor's degree from the Huazhong University of Science and Technology(HUST).

Email: chaochao.yan at

Google Scholar


Chaochao Yan, Qianggang Ding, Peilin Zhao, Shuangjia Zheng, Jinyu Yang, Yang Yu, Junzhou Huang. RetroXpert: Decompose Retrosynthesis Prediction like A Chemist. NeurIPS 2020 (pdf).

Chaochao Yan, Sheng Wang, Jinyu Yang, Tingyang Xu, Junzhou Huang. Re-balancing Variational Autoencoder Loss for Molecule Sequence Generation. ACM BCB 2020 (pdf).

Chaochao Yan, Jiawen Yao, Ruoyu Li, Zheng Xu, Junzhou Huang. Weakly Supervised Deep Learning for Thoracic Disease Classification and Localization on Chest X-rays. ACM BCB 2018 (pdf).


Nvidia, MD

Applied research intern

Worked with Shun Miao and Adam Harrison on Chest X-rays abnormalities classification and lesions localization using weakly supervised deep learning models.

Google, CA

Software engineer intern

Ads images classification with deep convolutional neural networks.

Tencent AI Lab, Shenzhen, China

Research intern

Worked on retrosynthesis prediction with Peilin Zhao.

Google, CA

Software engineer intern

Working on mobile object detection with Marco Fornoni, Yin Cui, Andrew Howard, and Boqing Gong at Google Research, remotely from Texas due to the COVID-19.


Retrosynthesis Prediction with Deep Attention Neural Networks

May 2020. We propose a template-free deep learning framework for the retrosynthesis prediction, which is a key component of drug discovery. The proposed model achieves the state-of-the-art retrosynthesis performance and scales well to the large real-world dataset.

Thoracic Disease Classification and Localization on Chest X-rays

June 2018. We propose a weakly-supervised deep learning framework for classifying common thoracic diseases as well as localizing suspicious lesion regions on chest X-rays. The comprehensive experiments are performed on ChestX-ray14 dataset. The proposed model achieves 0.832 in average AUC score, which is the new state-of-the-art.


University of Texas at Arlington

Augu 2017 - Present

Pursing Ph.D. in Computer Science

Institue of Automation, Chinese Academy of Sciences

Sept 2014 - July 2017

Master of Engineering in Computer Technology

Master thesis: Mobile 6-DOF Localization Technique for Outdoor Scene.

Huazhong University of Science and Technology

Sept 2010 - June 2014

Bachelor of Engineering in Automation


Get in Touch