Sahar Dastani
I am a PhD student at Mila/ÉTS, advised by Prof. Christian Desrosiers and Prof. Hervé Lombaert. My research is at the intersection of computer vision, deep learning, and efficient neural networks, with a focus on robustness under distribution shifts and geometric transformations. I am also a visiting researcher at Zebra working on GenAI applications.
Previously, I was a research assistant at CHU Sainte-Justine in Montreal with Dr. Philippe Jouvet. I obtained my M.Sc. and B.Sc. in Computer Science from Amirkabir University of Technology (AUT), advised by Dr. M. Hassan Shirali‑Shahreza and Dr. Mohammad Akbari.
Highlights & News
- Two papers accepted at NeurIPS 2025: TRUST and OVSS TTA.
- Served as a reviewer for NeurIPS 2025.
- Prompt Learning With Bounding Box accepted at IEEE T-BME 2025.
- Purge-Gate accepted at ICCV 2025.
- SMART-PC accepted at ICML 2025.
- Two papers accepted at CVPR 2025: Spectral State Space Model and Spectral Informed Mamba.
- Reviewer for IEEE TMI-2024.
- Reviewer for CVPR 2025.
- TTA in Point Clouds with Weight Averaging accepted at WACV 2025 (Oral).
- WATT accepted at NeurIPS 2024.
- Joined Prof. Desrosiers and Prof. Lombaert's lab as a PhD student.
- Abstract on Psychomotor Agitation Detection accepted at WFPICCS.
- Awarded the Upper Bound Talent Bursary 2024.
- Awarded the Professor Cho Diversity Scholarship.
- TA for Representation Learning at UdeM with A. Agrawal.
- Program reporter for CIFAR DLRL summer school.
- RelationalUNet accepted at MLMI 2023.
- Joined CHU Sainte‑Justine as research assistant.
- Graduated from AUT (M.Sc., CS) with GPA 4/4.
- Joined Holoo as Machine Learning Specialist.
- Started master’s at AUT.
- Graduated from AUT (B.Sc., CS).
Publications
Contact
Email: sahar.dastani-oghani.1@ens.etsmtl.ca
Scholar: profile · LinkedIn: profile · GitHub: Sahardastani