Welcome
Joseph Jay Williams is the Director of the Intelligent Adaptive Interventions lab. He is an Assistant Professor at UofT in Computer Science with courtesy appointments in Psychology and Statistics, as well as Industrial Engineering, Economics, and the Vector Institute for Artificial Intelligence.
Joseph Jay Williams'
Intelligent Adaptive Interventions Lab
Intelligent Adaptive Interventions Lab
What is the Intelligent Adaptive Interventions Lab?
The Intelligent Adaptive Interventions Lab was created to explore Adaptive Experimentation. Through this type of of experimentation, we can design Intelligent Interventions for Behaviour Change;
How do we help people start doing things they want to, and stop doing things they don't?
One example of our work is to transform ubiquitous explanations and prompting questions (e.g. text in a webpage, email, SMS) into an Intelligent Adaptive Intervention. We do this by innovating in uses of A/B testing, such as the AdapComp toolkit, and using adaptive experiments that automatically analyze data and use it to give better versions to future users. Our adaptive experiments apply and advance machine learning algorithms and statistical tests.
Learn more at this Research Statement: tiny.cc/williamsresearch.
Our papers span publications in applied Artificial Intelligence & Machine Learning, HCI (Human Computer Interaction), Statistics, Cognitive/Social/Clinical Psychology, Digital Education, Mental Health, and more!
About Me
I am currently an Assistant Professor in Computer Science at the University of Toronto (with a Graduate appointment in Psychology and Statistics). Previously I was an Assistant Professor in the School of Computing (Information Systems & Analytics, and NUS HCI Lab) at National University of Singapore (NUS). Prior to that I was a Research Fellow at Harvard's VPAL (Vice Provost for Advances in Learning) Research Group, and a member of the Intelligent Interactive Systems group led by Krzysztof Gajos in Computer Science. I have a courtesy appointment as a Research Scientist in Computer Science at Worcester Polytechnic Institute, where I am a co-PI with Neil Heffernan on an NSF Cyberinfrastructure grant. We use the ASSISTments K12 online math platform to crowdsource randomized controlled trials from the broader scientific community.
I was previously a postdoc at Stanford University in the Graduate School of Education and Lytics Lab, working with the Office of the Vice Provost for Online Learning and Candace Thille's Open Learning Initiative. I received my PhD in Computational Cognitive Science from UC Berkeley's Psychology Department. I worked with Tania Lombrozo to investigate why prompting people to explain "why?" helps learning, and with Tom Griffiths on using Bayesian statistics and methods from machine learning to characterize learning, reasoning, and judgment.
Tedx Talk
Joseph's TEDxPortofSpain talk explains how we use this approach in education, using AdapComps/MOOClets to intelligently adapt explanations for how to solve math problems.
For more information, check out our Lab Vision page.
#Recent Accepted Publications
Two papers accepted to CHI' 24 on LLM Application, see them at www.intadaptint.org/papers!
#Highlights
We won the prestigious Xprize for transforming education through Perpetual-Experimentation. Read more at tiny.cc/ixprize and the paper tiny.cc/moocletpaper.
#Awards & ShoutOuts
Our QuickTA project combining AI (RL algorithms & #LLMs) with @TutorGen is one of 16 #ToolsCompetition finalists for the DARPA AI Tools for Adult Learning opportunity!
#Research Projects
We received a DSI (Data Science Institute) grant. Part of this is for crowdsourced interventions! We are working with 10+ researchers to bring their well-being intervention to life!
We gratefully acknowledge support from our sponsors:
Contact Us
Undergraduates & interested graduate students/postdocs interested in joining or collaborating, contact: iaiinterest@googlegroups.com.
Joseph can be contacted at
williams[at]cs[dot]toronto[dot]edu.