From multilingual models for edge AI to new prognostics models for cancer patients, an international collaboration at U of T Engineering is developing innovative solutions to complex problems.
Two of the initiative’s key partners are U of T’s Centre for Analytics & Artificial Intelligence Engineering (CARTE) and the Institute of Information & Communications Technology Planning & Evaluation (IITP), South Korea.
For the last six months, 34 graduate students from across South Korea, sponsored by IITP, have been in Toronto, working with mentors at CARTE and U of T’s Department of Mechanical & Industrial Engineering (MIE) on challenges brought forward by partners from several different sectors.
All teams used AI and machine learning (ML) in their projects and presented their findings at The Hall at the Engineering Partnership Office on June 18. In the audience were U of T Engineering faculty members and representatives from all project partners — including Lorex Technology Inc., Kijiji Canada Ltd. and Guhuza, among many others.
“Our team developed an AI model for predicting mortality in prostate cancer patients. We took a multi-modal approach to integrate time-series data and textual records from patient visits, while accounting for the irregular visit intervals,” says Eunseon Seong, one of the students who worked on a project with Sunnybrook Health Sciences Centre.
“The project provided us with invaluable insights into building AI systems in real-world clinical settings”.
Dr. Kevin Ferreira, Senior Director of Artificial Intelligence and Head of LG Electronics Toronto AI Lab, was at the ceremony.
“This is the second year that we have partnered with this program, and we continue to be impressed by the caliber and creativity of the participating students,” says Ferreira.
“This year’s projects tackled some of the most exciting frontiers in AI research — from building efficient multilingual language models for edge deployment, to advancing knowledge distillation techniques that make large models faster, more efficient and environmentally sustainable, to designing robust evaluation frameworks for agentic AI systems.”
“Each project reflects our commitment to developing AI that is not only powerful, but practical and scalable. The student teams, mentored by our Toronto AI Lab researchers, brought fresh perspectives and technical excellence, delivering contributions that aid in advancing our research initiatives.”
In addition to working on the projects, all students took three graduate-level courses offered by MIE, and had access to customized AI drop-in clinics provided by CARTE.
They also attended a number of applied AI seminars offered at U of T, and used a dedicated workspace to facilitate collaborative opportunities and apply their knowledge and skills in the booming AI ecosystem in Toronto.
“Since 2024, MIE has hosted more than 30 grad students annually from South Korea through this program to take advantage of the variety of AI/ML courses that we offer,” says Professor Markus Bussmann, Chair of the Department of Mechanical & Industrial Engineering, who was also at the event.
“Through this engagement and other partnerships with South Korea, including hosting an international doctoral cluster with Korea Advanced Institute of Science and Technology (KAIST), and a new Global Industrial Technology Cooperation Center between South Korea and Canada on AI and Manufacturing, led by MIE Professor Chi-Guhn Lee, we are building an international community of researchers able to make real-world impact with AI.”
“This partnership between CARTE and IITP is a perfect example of how international collaboration can accelerate innovation and train the next generation of AI leaders,” says Professor Alex Mihailidis (BME), Associate Vice-President for International Partnerships at U of T.
“By bringing together talented students, world-class mentors and real-world challenges, we’re creating solutions that are not only technically advanced, but also socially meaningful. This is exactly the kind of initiative we need more of.”
The full list of projects and partner organizations in the latest round includes:
- Optimizing Real-Time Candidate Matching for Staffing Efficiency — Guhuza
- Comprehensive Quality Scoring for Marketplace Listings — Kijiji Canada Ltd.
- Efficient Multi-Lingual Language Models for Edge AI — LG Electronics Toronto AI Lab
- Knowledge Distillation for Edge AI Deployment — LG Electronics Toronto AI Lab
- Evaluation Frameworks for Agentic AI Systems — LG Electronics Toronto AI Lab
- Anomaly Detection for Security Camera Footage — Lorex Technology Inc.
- Realistic Hair Removal and Reconstruction in Images — ModiFace Inc.
- Enhancing Robustness and Transparency in Conversational AI Scoring — Nexxt Intelligence Inc.
- Prognostics for Musculoskeletal Health in Prostate Cancer Patients — Sunnybrook Health Sciences Centre
To learn more about partnership opportunities with CARTE on applied research or training programs in AI, please connect online.
– This story was originally published on the University of Toronto’s Faculty of Applied Science and Engineering News Site on June 19, 2025, by Tyler Irving.