Kyle Hsu

aka 徐銘謙, 徐宏愷

kylehkhsu at gmail dot com

I'm currently an undergraduate researcher at the Vector Institute working with Roger Grosse and Dan Roy. I'll graduate with a bachelor's in engineering science as a robotics engineering major from the University of Toronto in June 2020.

Previously, I was a visiting student researcher at Berkeley AI Research, where I worked with Sergey Levine and Chelsea Finn on unsupervised meta-learning as a member of the Robotic AI & Learning Lab. Prior to that, I spent a summer in Germany as a DAAD RISE Scholar working on scalable abstraction-based controller synthesis with Rupak Majumdar at the Max Planck Institute for Software Systems. My first research experiences were in optoelectronics and photonics under Joyce Poon at the University of Toronto and Ming C. Wu at UC Berkeley.

Starting May 2020, I will be hosted by Shane Gu as a research intern at Google Brain in Mountain View.

Curriculum Vitae  /  Google Scholar  /  LinkedIn  /  GitHub

Research

I've had the fortune of participating in a range of interesting research projects with talented and patient collaborators.

Unsupervised Curricula for Visual Meta-Reinforcement Learning
Allan Jabri, Kyle Hsu, Benjamin Eysenbach, Abhishek Gupta, Sergey Levine, Chelsea Finn
Neural Information Processing Systems (NeurIPS), 2019
spotlight presentation
arXiv / poster / project page

We develop an algorithm that constructs a task distribution for an unsupervised meta-learner by modeling interaction in a visual environment. The task distribution adapts as the agent explores the environment and learns to learn.

Unsupervised Learning via Meta-Learning
Kyle Hsu, Sergey Levine, Chelsea Finn
International Conference on Learning Representations (ICLR), 2019
arXiv / poster / project page / code

We propose CACTUs, a simple unsupervised learning → clustering → meta-learning pipeline for image classification pre-training. CACTUs can be thought of as a method that enables unsupervised meta-learning.

Lazy Abstraction-Based Controller Synthesis
Kyle Hsu, Rupak Majumdar, Kaushik Mallik, Anne-Kathrin Schmuck
International Symposium on Automated Technology for Verification and Analysis (ATVA), 2019
invited paper
arXiv / project page / demo / code

This paper gives a self-contained presentation of lazy, multi-layered ABCS for reachability and safety specifications.

Lazy Abstraction-Based Control for Safety Specifications
Kyle Hsu, Rupak Majumdar, Kaushik Mallik, Anne-Kathrin Schmuck
Conference on Decision and Control (CDC), 2018
arXiv / project page / code

In this work, we restrict our attention to safety specifications, and extend multi-layered ABCS to be lazy: we entwine abstraction and synthesis to enable on-demand construction of the abstractions.

Multi-Layered Abstraction-Based Controller Synthesis for Continuous-Time Systems
Kyle Hsu, Rupak Majumdar, Kaushik Mallik, Anne-Kathrin Schmuck
International Conference on Hybrid Systems: Computation and Control (HSCC), 2018
pdf / project page / code

We generalize abstraction-based controller synthesis (ABCS) and present multi-layered ABCS: we construct multiple abstractions of the system at varying spatiotemporal granularity, and do synthesis by adaptively switching between these layers.

Germanium Wrap-Around Photodetectors on Silicon Photonics
Ryan Going, Tae Joon Seok, Jodi Loo, Kyle Hsu, Ming C. Wu
Optics Express, 2015

We present a new photodetector architecture in which we wrap the germanium diode around the silicon waveguide on four faces.

alphabetical authorship order


This guy makes a nice website.