Angel X. Chang

Angel X. Chang

Canada CIFAR AI Chair

Academic Affiliations

Assistant Professor – Simon Fraser University (Computing Science); Faculty – GrUVi Lab (Simon Fraser University); Faculty – SFU Nat LangLab (Simon Fraser University)

Industry and Research Affiliations

Hans Fischer Fellow – Institute for Advanced Study (Technical University of Munich)

Areas of Expertise

Artificial intelligence; machine learning; natural language processing; computer vision; computer graphics

Angel works at the intersection of language and vision to create computer models with knowledge and understanding of the world.

From text to 3D

Angel Chang works at the intersection of language and vision to create computer models with knowledge and understanding of the world. Her research connects language to 3D representations of shapes and scenes and grounds language for embodied agents in indoor environments. She has worked on methods for synthesizing 3D scenes and shapes from natural language, and various datasets for 3D scene understanding. In general, she is interested in the semantics of shapes and scenes, the representation and acquisition of common sense knowledge, and reasoning using probabilistic models. Through her collaborative research, Angel has developed methods for generating coloured 3D shapes from natural language and for turning input text into computer-generated scenes that can then be further refined through textual interaction by the user.

Angel is a Canada CIFAR AI Chair with Amii, an Assistant Professor at Simon Fraser University, and a recipient of the Hans Fischer Fellowship from the Technical University of Munich’s Institute for Advanced Study. She is also a faculty member of the GrUVi Lab and Nat Lang Lab, both at Simon Fraser University. Prior to this, she was a visiting research scientist at Facebook AI Research and a research scientist at Eloquent Labs working on dialogue. She received her Ph.D. in Computer Science from Stanford, where she was part of the Natural Language Processing Group and was advised by Chris Manning. Over the past ten years, Angel has produced more than 50 publications, including refereed publications, preprint/workshop papers and invited talks. She also received the SGP 2018 and SGP 2020 Dataset Awards from the Symposium on Geometry Processing for her work on the ShapeNet and ScanNet datasets.