Hey there! I'm Victor.

profile picture profile picture

I will start as a Assistant Professor at the Cheriton School of Computer Science at the University of Waterloo and a Faculty Member at Vector Institute in July, 2024. Until then, I am working as a Postdoc Researcher at Microsoft Research New York City. I am on Twitter but email is preferred at [email protected]. I cannot take on more interns/external collaborations at this time, but will be able to do so in 2024.

I am actively looking for strong and motivated students with research experience in Machine Learning and Natural Language Processing. Our lab offers an exceptional platform for exploring how machines, like humans, can swiftly adapt to novel situations via language understanding. As a member of our lab, your work will span a diverse set of areas including ML, RL, NLP, CV, and extending to applications in software engineering, incentive design, and computational biology. Moreover, your work will provide collaboration opportunities with industry research labs such as the Vector Institute, Microsoft Research, Meta AI Research, and Salesforce Research. If you are interested in working with me, please first complete this form, then apply through the University of Waterloo CS PhD program (deadline typically Dec 1) and mention me in your application. Unfortunately, due to the volume of requests, I cannot personally comment on most applications - specifically, I cannot offer insights into your likelihood of admission nor the status of your application to the University of Waterloo.

Should I apply to MS or PhD? At the University of Waterloo, MS is similar to years 1-2 of a PhD student (e.g.~in the United States) and I expect MS students to transition into PhD. In this sense, MS students are expected to perform productive research similar to a junior PhD students. If you are a very accomplished undergraduate student with ample research experience, I welcome you to apply directly to the PhD program. Otherwise, please apply to the MS program and rest assured that I will advise MS students like junior PhD students. If you already have a MS degree, please apply to the PhD program.

Research

My lab's research is on Reading to Learn: how we can use language understanding to generalize and learn more efficiently. Why should we read to learn? Most machine learning techniques train on vast amount of labeled data or experience for specific problems. When the problems change (e.g. driving in a new country, controlling a new robot, language interface for a new database), the expensive solution we trained no longer generalizes to new problems. The strength of humans lies in our ability to adapt to new problems adeptly through reading. For instance, understanding the traffic rules of a new country, the workings of a new coffee machine, or the content of a new database can be accomplished through reading the manual. The thesis of this research is:

By reading language specifications that characterize key aspects of the problem, we can efficiently learn solutions that generalize to new problems.

Our work in reading to learn spans several areas, including interactive learning, robotics, semantic parsing, and conversation agents. Our recent work has focused on learning policies that generalize to new environments by reading manuals, automated curriculum learning to pretrain language grounding, and automatically generating reward functions from language for robotic control.

Education

Industry roles

Students I have worked with