AI research is moving at lightning speed and it can be hard for industry-focused practitioners to keep up. Designed for a highly technical audience who wants to take their understanding of AI to the next level, Endless Summer School showcases new and interesting research from Vector's network of 700 researchers. This series delves into the latest advances in AI domains, helps to distill thousands of academic papers into the critical few insights practitioners need, and keeps technical practitioners at the cutting edge of AI research.

Description

The Endless Summer School (ESS) session will cover highlights on outstanding state-of-the-art research in Representation Learning selected in the International Conference on Learning Representation (ICLR). ICLR is one of the top premier academic conferences in the field of machine learning and artificial intelligence.

The ESS event throws light on recent advances in unsupervised learning, multimodal learning, domain adaptation, large language models and reinforcement learning. Furthermore, the event showcases a summary of selected papers at the ICLR 2023 conference, important takeaways, and features work of researchers who performed ground breaking research, the researchers will discuss their accepted work comprehensively.

This session facilitates the Vector community to develop the understanding of recent advancements presented at the conference and note the key takeaways that can be implemented in research and industry.

10:00 AM

Sedef Akinli Kocak, Director, Vector Institute
Opening remarks

10:02 AM

Michael Zhang, University of Toronto, Vector Institute
Talk Title: “ICLR 2023 Highlights and Takeaways”

11:00 AM

Franziska Boenisch, Vector Institute
Talk Title: “Stealing and Defending Transformer-Based Encoders”

11:20 AM

Tianyu (Patrick) Hua, University of British Columbia
Talk Title: “Self-supervision through Random Segments with Autoregressive Coding (RandSAC)"

11:40 AM

Ashish Gaurav, University of Waterloo, Vector Institute
Talk Title: “Learning Soft Constraints from Constrained Expert Demonstrations”

12:00 PM

Closing remarks & adjourn

Michael Ruoqi Zhang
Vector Institute; University of Toronto
PhD

Franziska Boenisch
Vector Institute
Postdoctoral Fellow

Tianyu Hua
University of British Columbia
Student

Ashish Gaurav
University of Waterloo
PhD Student

This event is open to Vector Sponsors, Vector Researchers, and invited health partners only. Any registration that is found not to be a Vector Sponsor, Vector Researcher or invited health partner will be asked to provide verification and, if unable to do so, will not be able to attend the event. Please contact events@vectorinstitute.ai with any questions.