Mohammadreza Bakhtyari
I am a Ph.D. candidate in Computer Science at the Université du Québec à Montréal (UQAM), advised by Vladimir Makarenkov. I develop learning and inference methods that generalize across datasets and tasks, with a focus on amortized and probabilistic inference, meta-learning, and structured neural architectures. My current work studies how synthetic priors and permutation-aware models transfer to real-world tabular data.
My doctoral research is supported by the FRQNT / PBEEE scholarship.
Research interests
- Amortized & probabilistic inference
- Meta-learning & in-context learning
- Structured & permutation-aware architectures
- Generalization & transfer
Selected publications
Google ScholarNews
TabK accepted at NeurIPS 2026.
ClustRecNet published in IEEE Access.
Awarded the FRQNT / PBEEE doctoral scholarship.
Education
Ph.D. in Computer ScienceUniversité du Québec à Montréal
M.Sc. in Algorithms and ComputationsUniversity of Tehran
Teaching & mentoring
Research AssistantUniversity of TehranMentored undergraduate researchers in deep learning and signal processing, including the faculty’s top-ranked thesis in 2022.
Faculty LecturerUniversity of TehranFundamentals of Programming, Computer Architecture, and Advanced Programming (Python).
Teaching AssistantUniversity of TehranMachine Learning Algorithms (M.Sc.) · Deep Learning Algorithms (Ph.D.). Recognized as an Outstanding Teaching Assistant in Machine Learning.