Amir Eskandari

I am a PhD student in the School of Computing at Queen's University in Ontario, Canada. I am supervised by Dr. Farhana Zulkernine and Dr. Jordan Poppenk. I am also a PhD trainee at Connected Minds CFREF. I am solving the personalization problem in large language models, exploring RAG-based methods and RL-based fine-tuning approaches. My research broadly spans graph machine learning and LLM post-training.

Prior to my PhD, I was a graduate research assistant at AUT. I proudly hold an M.Sc. degree from AmirKabir University of Technology and a B.Sc. degree from IKIU, both in the field of Electrical Engineering. During my master's, I worked on multi-variate time-series imputation using GNNs. At AUT, I was supervised by Dr. Vahid Pourahmadi.

I love talking about science and technology. Shoot me an email if you'd like to discuss!

Google Scholar | LinkedIn | GitHub | Twitter | Email: amir.eskandari@queensu.ca

News
[Dec 2026] My paper has been accepted for publication in Transactions on Machine Learning Research (TMLR).
[Sep 2025] I started a new internship position as Machine Learning Associate at Vector Institute!
[Aug 2025] Our paper got published in Machine Learning with Applications (Elsevier)!
[Jul 2025] One paper got accepted in ICMV 2025.
[May 2025] Two papers got accepted in IEEE COMPSAC.
Selected Publications
TMLR
InfGraND: An Influence-Guided GNN-to-MLP Knowledge Distillation
A. Eskandari, A. Anand, E. Rashno, F. Zulkernine.
TMLR
ASMa: Asymmetric Spatio-temporal Masking for Skeleton Action Representation Learning
A. Anand, A. Eskandari, E. Rashno, F. Zulkernine.
ACM Survey (Under Review)
Survey: Transformer-based Models in Multimodal Data Processing
E. Rashno, A. Eskandari, A. Anand, F. Zulkernine.
COMPSAC 2025
SDA-GRIN for Adaptive Spatial-Temporal Multivariate Time Series Imputation
A. Eskandari, A. Anand, D. Sharma, F. Zulkernine.