Talks & Teachings

Talks

  • Two Pathways to Trustworthy AI: Transparent Representations and Robust Adaptation, MBZUAI (Rising-Star Talk, International Symposium on Trustworthy Foundation Models 2025). May 2025.
  • Two Pathways to Trustworthy AI: Transparent Representations and Robust Adaptation, Google Research. May 2025.
  • Human-Centric Alignment through Multilevel Feedback Integration, Stanford University. Mar. 2025.
  • Multi-FR: A Multi-Objective Optimization Method for Achieving Two-sided Fairness in E-commerce Recommendation, Microsoft Research. Oct. 2021.
  • Joint Multisided Exposure Fairness for Search and Recommendation, Mila (Selected as 1 of 6 Contributed Talks, Montreal AI Symposium 2022). Sep. 2022.
  • Joint Multisided Exposure Fairness for Search and Recommendation, Bell Canada. Aug. 2022.
  • Joint Multisided Exposure Fairness for Search and Recommendation, Microsoft Research. Apr. 2022.

Teachings (Head TA)

Applications of Machine Learning in Real-World Systems
COMP 597/598
McGill University. Led weekly discussion sections and instructional activities. Winter 2021 & 2022.

    This is a graduate-level course for students who are interested in learning how to apply machine learning algorithms to solve real-world problems. We will start with a quick review of machine learning basics and then focus on a few selected interesting topics including communication networks, web search and recommendation, LLMs, generative models, smart grid, and medical applications. We will also discuss some high-impact industry machine learning products and the research problems behind their successes. The class consists of lectures, student-led presentations, class discussions, and class projects. The course is taught by Prof. Xue (Steve) Liu.