Kevin J Liang

Kevin is a Research Scientist at Facebook AI Applied Research (FAIR). His research interests are primarily in deep learning, particularly computer vision, continual learning, federated learning, and adversarial attacks. Before Facebook, he was at Duke University, where he completed his PhD while advised by Lawrence Carin, as well as a BSE in Electrical and Computer Engineering and Biomedical Engineering before that.

Kevin's Publications

May 04, 2021



Continual Learning using a Bayesian Nonparametric Dictionary of Weight Factors

Naively trained neural networks tend to experience catastrophic forgetting in sequential task settings, where data from previous tasks are unavailable. …

Nikhil Mehta, Kevin J Liang, Vinay K Verma, Lawrence Carin

May 04, 2021

March 17, 2021



MixKD: Towards Efficient Distillation of Large-scale Language Models

Large-scale language models have recently demonstrated impressive empirical performance. Nevertheless, the improved results are attained at the price of bigger models, more power consumption, and slower inference, which hinder their applicability to low-resource (both memory and computation) platforms.…

Kevin J Liang, Weituo Hao, Dinghan Shen, Yufan Zhou, Weizhu Chen, Changyou Chen, Lawrence Carin

March 17, 2021