- Paper: “Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity”.
- Paper: “Personalized Adaptation via In-Context Preference Learning”.
- Past work includes using generative models for causal effect estimation, causal structure learning from observational data, and human-centric reinforcement learning.
Research Experience
- May 2024 - Nov. 2024: Research Intern at Autodesk, teaching large vision language models intuitive physics using simulation data.
- Sep. 2021 - Present: Ph.D. Student at UofT & Vector Institute, Thesis: Learning data-driven algorithms for causal decision making.
- Sep. 2020 - Aug. 2021: Data Scientist at Cafe Bazaar, optimizing video watch time by automating mid-roll ad breaks using speech recognition.
- Jul. 2019 - Sep. 2020: Research Intern at Max Planck Institute for Software Systems, human-machine collaboration in reinforcement learning.
Education
Ph.D. in Computer Science at the University of Toronto, supervised by Rahul G. Krishnan; External advisor: Vasilis Syrgkanis from Stanford University. B.Sc. in Computer Engineering and Mathematics at Sharif University of Technology.
Background
Research Interests: Understanding the concepts and mechanisms that aid humans in optimal decision-making, particularly in applications where simulation is costly or infeasible, such as healthcare. Research areas include causal inference from observational data and its intersection with machine learning, imitation learning, and reinforcement learning from offline observations.