ABOUT ME

压缩.jpg

Dr. Shanghang Zhang is a Tenure Track Assistant Professor at the Computer Science Department of Peking University. She has been the postdoc research fellow at Berkeley AI Research Lab (BAIR), EECS, UC Berkeley, working with Prof. Kurt Keutzer and Prof. Trevor Darrell. Her research focuses on OOD Generalization that can enable the machine learning systems to generalize to new domains, categories, and modalities using limited labels, with applications to IoT problems including autonomous driving and intelligent manufacture, as reflected in her over 40 papers on top-tier journals and conference proceedings, including NeurIPS, ICLR, ACM MM, TNNLS, TMM, CVPR, ICCV, and AAAI (Google Scholar Citations: 3100, H-index: 23, I10-index: 35). She has also been the author and editor of the book “Deep Reinforcement Learning: Fundamentals, Research and Applications” published by Springer Nature. This book is selected to Annual High-Impact Publications in Computer Science by Chinese researchers and its Electronic Edition has been downloaded 120,000 times worldwide. Her recent work “Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting” has received the AAAI 2021 Best Paper Award.  It ranks the 1st place of Trending Research on PaperWithCode and its Github receives 2,600+ Stars. She has been selected to “2018 Rising Stars in EECS, USA”. 

Research Interest

Out of Distribution Generalization

Domain adaptation

Low shot learning

Neural science

Education

2013 - 2018

Carnegie Mellon University

Advised by Prof. Jose M.F. Moura, and Joao P. Costeira.

2010 - 2013

Peking University

Advised by Prof. Wen Gao and Xiaodong Xie.

2006 - 2010

Southeast University

Awards

AAAI Best Paper Award, 2021

Rising Stars in EECS, US 2018

NIPS travel award; CVPR Doctoral Consortium Travel Award, 2018

Qualcomm Innovation Fellowship (QInF), Finalist Award, 2015

Chiang Chen Overseas Graduate Fellowship, 2013 (10 winners nationwide)

Academic Service