Mahdiyar Molahasani

Mahdiyar Molahasani

Research Scientist, Foundation Models & Generalization

About me

I work on making foundation models reliable when data and compute are imperfect: long-tailed and biased data, distribution shift, decentralized data, and tight inference budgets. My work spans theory and practice, from convergence analysis to training-free methods.

I'm a Senior Machine Learning Research Scientist at Captura in Vancouver, where I work on efficient inference and adaptation for vision-language models. I did my PhD at Queen's University with Ali Etemad and Michael Greenspan.

Interactive notes

NeurIPS 2026 Long tails as continual learning Train a model in your browser and watch long-tailed training land next to a model that never saw the rare classes. ICCV 2025 Fixing CLIP's background shortcut Watch a projection learned only from LLM-written sentences fix how CLIP classifies images.

News

  • Our paper bridging long-tailed recognition and continual learning was accepted to NeurIPS 2026.
  • PRISM was accepted to ICCV 2025.
  • Joined Captura as a Senior Machine Learning Research Scientist.
  • Completed my PhD at Queen's University.

Selected publications

Generalization under imbalance

  • A Theoretical Bridge Between Long-Tailed Recognition and Continual Learning Mahdiyar Molahasani, Michael Greenspan, Ali Etemad NeurIPS 2026 [arXiv, Interactive note, Workshop’23]

Bias and fairness in vision-language models

  • PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Mahdiyar Molahasani*, Azadeh Motamedi*, Michael Greenspan, Il-Min Kim, Ali Etemad ICCV 2025 [Paper, arXiv, Code, Interactive note]

Privacy-preserving generalization

  • Federated Unsupervised Domain Generalization using Global and Local Alignment of Gradients Farhad Pourpanah*, Mahdiyar Molahasani*, Milad Soltany*, Michael Greenspan, Ali Etemad AAAI 2025 [Paper, arXiv, Code, Interactive note]
  • A Theoretical Framework for Federated Domain Generalization with Gradient Alignment Mahdiyar Molahasani*, Milad Soltany*, Farhad Pourpanah*, Michael Greenspan, Ali Etemad NeurIPS 2024 Workshop on Mathematics of Modern Machine Learning [Paper]

* Equal contribution

All publications →

Experience & Education

  • Senior Machine Learning Research Scientist, Captura Efficient inference and adaptation for vision-language models (2025–)
  • Graduate Research Assistant, Ingenuity Labs Research Institute Queen's University (2021–2025)
  • Ph.D., Electrical and Computer Engineering, Queen's University With Ali Etemad and Michael Greenspan; thesis on generalization in deep representation learning (2021–2025)
  • M.Sc., Electrical and Computer Engineering, University of Saskatchewan (2019–2021)
  • B.Sc., Electrical Engineering, Iran University of Science and Technology (2013–2018)

Service

  • Gold Reviewer Award, ICML 2026; Top Reviewer, NeurIPS 2024.
  • Reviewer for NeurIPS, ICML, ICLR, AAAI, AISTATS, TMLR, and IEEE journals (40+ reviews).