Ke Li

I recently graduated with a Ph.D. from UC Berkeley, where I was advised by Jitendra Malik, and am now a Reseach Scientist at Google and a Member of the Institute for Advanced Study (IAS). My research interests are in machine learning, computer vision and algorithms. I received my bachelor's in computer science from the University of Toronto. I can be reached by e-mail at ke [dot] li [at] eecs [dot] berkeley [dot] edu. In my spare time, I organize the IAS Seminar Series on Theoretical Machine Learning with Sanjeev Arora - check out past seminars here and follow us on Twitter for future seminar announcements.

Google Scholar  |  Twitter

For a quick introduction to my research, see the following talk videos:

IAS Workshop on Theory of Deep Learning (Video) (Slides): this is on generative modelling and nearest neighbour search and is aimed at machine learning researchers
CMU ML/Duolingo Seminar (Video) (Slides): this is an extended version of the above (with more details on nearest neighbour search) and is aimed at machine learning graduate students
CIFAR Deep Learning and Reinforcement Learning Summer School (Video) (Slides): this is on generative modelling and is aimed at a broader audience in the style of a tutorial
IAS Special Year Seminar (Video): this is on meta-learning and is aimed at machine learning researchers

Research Directions

I am interested in tackling fundamental problems that cannot be solved using a straightforward application of conventional techniques. Below are the major areas that I contributed to:

Selected Papers

Generative Modelling

Learning to Optimize

Fast Nearest Neighbour Search

Instance Segmentation

Other Topics


CS 189: Introduction to Machine Learning (Summer 2018) — Instructor


Overcoming Mode Collapse and the Curse of Dimensionality (Extended Version) No More Mode Collapse Implicit Maximum Likelihood Estimation Tutorial on Implicit Generative Models Fast k-Nearest Neighbour Search via Dynamic Continuous Indexing Meta-Learning: Why It's Hard and What We Can Do Learning to Optimize Meta-Learning

Professional Service

Seminars: Journals: Conferences: