Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
Notable works in multimodal learning include InstructBLIP, Plug-and-Play VQA, and VisualGPT. His work in Data-centric AI covers understanding datasets (factor analysis of datasets), data influence on model decisions (HyDRA), selection of training data (COINCIDE), and synthesis of training data from generative AI (SPARCL). Another research direction is building AI that understands commonsense causal relations, with benchmarks such as BlackSwanSuite and M-SyMoN.
Research Experience
Prior to NTU, he was a Senior Research Scientist at Baidu Research USA, and a Research Scientist and Group Leader at Disney Research.
Education
Received Ph.D. degree from Georgia Institute of Technology.
Background
Associate Professor at the College of Computing and Data Science, Nanyang Technological University, Singapore. Research interests broadly in Multi-modal Learning, Data-centric AI, Machine Learning, and Computational Narrative Intelligence.
Miscellany
Teaches a PhD-level Deep Learning course, CE7454, which consistently receives student scores of 90/100 or above.