I am an Associate Professor at the School of Computer Science and Engineering, Nanyang Technological University, Singapore. My research interests lie mainly in Computational Narrative Intelligence, Multi-modal Understanding and Reasoning, and Machine Learning.

Story is a powerful tool for communication, an exhibit of creativity, and a timeless form of entertainment. Computational Narrative Intelligence (CNI) aims to create intelligent machines that can understand and create stories, manage interactive narratives, and respond appropriately to stories told to them. I have made contributions to all major areas of CNI, ranging from story generation and interactive narratives to human cognition, from learning story knowledge to story understanding.

I believe that in order to simulate human intelligence, artificial intelligence must first acquire human-level knowledge from an approximation of the human experience, which is inherently multimodal. Further, inspired by the observation that human intelligence emerges from the interaction of multiple cognitive processes, I am interested in understanding the interactions between different neural network components and developing techniques that coordinate the learning of different neural network components beyond simplistic stochastic gradient descent.

From 2017 to 2019, I was a Senior Research Scientist at Baidu Research USA. From 2015 to 2017, I was a Research Scientist at Disney Research, leading a group of postdocs and interns. Prior to that, I worked as a postdoc with Leon Sigal and Jill Lehman. In 2014, I received my Ph.D. degree from Georgia Institute of Technology, working with Mark Riedl.

[Hiring] I have multiple open positions for Ph.D. students, postdocs, and research engineers. If you are interested, please send me your CV.

What's New
Nov 2020: Our paper An Empirical Study on the Relation between Network Interpretability and Adversarial Robustness has been accepted by the journal Springer Nature Computer Science.
Nov 2020: Our paper on improving data efficiency of multimodal sequence alignment has been accepted at WACV 2021.
Dec 2019: New preprint that applies the theory of Graphon to optimize the organization of CNN layers: Searching for Stage-wise Neural Graphs In the Limit
May 2019: Our paper on emotion recognition and attribution from video was accepted by the IEEE Transactions on Multimedia.
Nov 2018: Learning Gaussian embeddings for actors and persona accepted at AAAI 2019 (~16.2% acceptance rate).
Feb 2018: Spotlight presentation on multimodal sequence alignment (~6.8% acceptance rate) at CVPR 2018.

gs.ude.utn@il.gnayob :liamE

Research Areas

Multimodal Reasoning

Story Understanding

Acquiring Story Knowledge

Story Generation