Welcome

Shuai Xiao,  PhD 

Email: benjaminforever AT sjtu.edu.cn shuai.xiao AT cc.gatech.edu shuai.xsh AT gmail/alibaba  Google Scholar, Github.

Biography

Now I'm an algorithm director at Alibaba Search and Recommendation Department. Before that, I joined Artificial Intelligence Department of Ant Group (formerly known as Ant Financial) , recruited by Alibaba with honor "Ali Star"("阿里星" in Chinese).

I obtained the Ph.D. degree of School of Electronic Information and Electrical Engineering from Shanghai Jiao Tong University in 2018, supervised by Prof. Hongyuan Zha and Prof Xiaokang Yang.  I studied at Georgia Institute of Technology as a visiting scholar from 2016-2018, supervised by Prof. Le Song.  Before that, I graduated from advanced class with the B.Sc. degree in electronic and information engineering from Huazhong University of Science and Technology in 2013. 

My research interest broadly lies in statistical machine learning, deep learning, and their applications.  I've worked on Graph Neural Networks for financial risk control,  Reinforcement Learning for recommendation systems and financial decision-making,   multimodal perception and generation.

I'm also very fortunate to work closely with talented researchers: Junchi Yan,  Mehrdad Farajtabar, Hanjun Dai, Liangda Li, Shuang Yang, Hongteng Xu, and Xiaojing Ye, Jiangchao Yao, Xiaoming Liu, Xu Chen. 

News

• 2024/12: Video Temporal Sentence Groudning accepted by ICASSP 2025.

• 2024/07: Our Diverse recommendation paper accepted by ACM CIKM 2024.

• 2024/07: Our Video Try-On paper accepted by ACM MM 2024.

• 2024/07: Our work about Diffusion-based Virtual Try-On and Acceleration of Vision-Language accepted by ECCV 2024.

• 2024/04: The Diffusion-based Video Clothes Try-On paper is out and the project URL is here.

• 2024/03: Our Clothes Virtual Try-On paper is out. The project page is here. Stay tuned. 

• 2024/03:  Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection accepted by CVPR 2024. The paper proposes a refining framework to obtain high-quality pseudo labels on the unlabeled target domain for Autonomous driving. 

• 2024/02:  Enhancing Cross-domain Click-Through Rate Prediction via Explicit Feature Augmentation accepted by WWW 2024. The paper transfers knowledge from data-rich text-search domain to data-sparse image search domain with heterogeneous input. The method is fully-launched in image search in Taobao.

• 2023/12：I'm honored to be selected into  Oriental Talents Program  ("东方英才" in Chinese).

• 2022/02:  Traffic Anomaly Prediction Based on Joint Static-Dynamic Spatio-Temporal Evolutionary Learning accepted by TKDE 2022.

• 2022/01:  Tile Networks: Learning Optimal Geometric Layout for Whole-page Recommendation accepted by AISTATS 2022.

• 2022/01：I'm honored to be awarded as  Shanghai Industrial Elite  ("上海产业菁英高层次人才" in Chinese).

• 2021/11: I serve as Adjunct Professor of Xi'an Jiaotong University (XJTU) for the academic-industrial joint program. 

• 2019/08:  Model-based Constrained MDP for Budget Allocation in Sequential Incentive Marketing accepted by CIKM 2019 Research Track.

• 2018/12:  Learning Temporal Point Processes via Reinforcement Learningaccepted by NeurIPS18 (Spotlight).

• 2018:  Learning Time Series Associated Event Sequences with Recurrent Point Process Networks accepted by IEEE Transactions on Neural Networks and Learning Systems (TNNLS).

• 2017/11:  Learning Conditional Generative Models for Temporal Point Processes  accepted by AAAI 2018.

• 2017/11:  1st Place in Home Depot Deep Learning Competition, 2017.

• 2017/10:  NIPS 2017 Travel Award.

• 2017/09:  Wasserstein Learning of Deep Generative Point Process Models accepted by NIPS 2017.

• 2017/06:  The demo code of paper  Modeling The Intensity Function Of Point Process Via Recurrent Neural Networks  was released.

• 2016/11:  Nominee for IBM PhD fellowship.

• 2016/07:  Merger&Acquisition data from CrunchBase for our paper  Modeling contagious Merger and Acquisition via Point Processes with a Profile Regression Prior  was released.

Collaborators

Prof. Hongyuan Zha, Georgia Tech

Prof. Le Song, Georgia Tech

Prof. Xiaokang Yang, Shanghai Jiao Tong University

Prof. Junchi Yan, Shanghai Jiiao Tong University

Prof. Ya Zhang, Shanghai Jiiao Tong University

Prof. Xiaojing Ye, Georgia State Univerisity

Prof Hongteng Xu, Renmin University

Prof Xu Chen, Renmin University

Prof Xiaoming Liu, Xi'an JiaoTong University

Prof Jiangchao Yao, Shanghai Jiiao Tong University

Prof Wei Zhang, East China Normal University

Prof Xiangfeng Wang, East China Normal University

Prof. Changsheng Li, Beijing Institute of Technology

Prof. Bo Jin, Tongji University

Prof. Xiang Bai, Huazhong University of Science and Technology

Shuang Yang, Ph.D. , Meta

Weilin Huang,  Ph.D. , Alibaba

Mehrdad Farajtabar, Ph.D. , Deepmind

Hanjun Dai, Ph.D. , Google Brain

Liangda Li, Ph.D. ,  Yahoo