Yanshuai Cao


Research Team Lead

PhD Computer Science, University of Toronto

Yanshuai Cao is currently a research team lead at Borealis AI. His long-term research goal is to create machines that can learn from as little supervision as possible and as quickly as humans do when facing new data. Currently, his research spans generative models, continual learning, computer vision and natural language processing. Previously, he also explored Bayesian nonparametric methods to that same end.

Yanshuai received his PhD in Computer Science from the Department of Computer Science at the University of Toronto, where he was advised by Professor David J. Fleet and Professor Aaron Hertzmann.

Research Areas

Computer Vision

Natural Language Processing


July 12, 2020

Evaluating Lossy Compression Rates of Deep Generative Models

International Conference on Machine Learning (ICML), 2020
Authors: *S. Huang, *A. Makhzani, Y. Cao , R. Grosse
* Denotes equal contribution
July 12, 2020

On Variational Learning of Controllable Representations for Text without Supervision

International Conference on Machine Learning (ICML), 2020
Authors: P. Xu , J. Cheung , Y. Cao
June 3, 2020

Better Long-Range Dependency by Bootstrapping A Mutual Information Regularizer

International Conference on Artificial Intelligence and Statistics (AISTATS), 2020
Authors: *Y. Cao , *P. Xu
* Denotes equal contribution
July 28, 2019

A Cross-Domain Transferable Neural Coherence Model

Association for Computational Linguistics (ACL), 2019
Authors: P. Xu , H. Saghir, J. Kang , L. Long, A. J. Bose, Y. Cao , J. Cheung
Dec. 3, 2018

Few-Shot Self Reminder to Overcome Catastrophic Forgetting

Workshop on Continual Learning (NeurIPS), 2018
Authors: J. Wen, Y. Cao , R. Huang
Dec. 3, 2018

Compositional Hard Negatives for Visual Semantic Embeddings via an Adversary

Workshop on ViGIL (NeurIPS), 2018
Authors: *A. J. Bose, *H. Ling, Y. Cao
* Denotes equal contribution
July 15, 2018

Adversarial Contrastive Estimation

Association for Computational Linguistics (ACL), 2018
Authors: *A. J. Bose, *H. Ling, *Y. Cao
* Denotes equal contribution
April 30, 2018

Improving GAN Training via Binarized Representation Entropy (BRE) Regularization

International Conference on Learning Representations (ICLR), 2018
Authors: Y. Cao , G. W. Ding , K. Lui , R. Huang
Aug. 6, 2017

Implicit Manifold Learning on Generative Adversarial Networks

Workshop on Implicit Models (ICML), 2017
Authors: K. Lui , Y. Cao , M. Gazeau, K. S. Zhang
Aug. 6, 2017

Automatic Selection of t-SNE Perplexity

Workshop on AutoML (ICML), 2017
Authors: Y. Cao , L. Wang