Saeid Asgari

I am a Principal Machine Learning Research Scientist at Autodesk AI Research and an Adjunct Research Professor at the School of Computing Science (ranked #1 in Computer Vision in Canada), Simon Fraser University (SFU), Canada. Previously, I explored real-world machine learning and computer vision problems in startup environments.

I completed my PhD in Computing Science at SFU under the supervision of Prof. Ghassan Hamarneh. During my PhD I had multiple research visits/internships at different research institutions such as MILA (Montreal, Canada), Siemens Healtheneers (Princeton, USA), and Imagia (Montreal, Canada).

Outside of work, I have a strong passion for soccer and running track - the 100m sprint. I've had the privilege of competing and earning a few medals in inter-university competitions in these areas.

Email  /  LinkedIn  /  Google Scholar  /  X

I lead research and development initiatives focused on interpretable and safe machine learning systems that are robust, reliable, and fair. Recently been focusing more on generative models incluing LLMs and VLMs.

Benchmarking and Understanding of Reliability of ML Models: Designing experiments and building datasets for robustness analysis, including domain generalization and memorization in generative models.

Data Bias Analysis: Building tools for analysis of known and hidden data biases.

Interpretability and Explainability: Building tools for understanding ML models' behavior and developing safe ML models.

Mitigations of Biases: Modifying datasets and designing new models to better handle biases, out-of-domain samples, and improve generalization.

Design template by Jon Barron