|
Maryam AlipourHajiagha I am a graduate research assistant at Mila - Quebec AI Institute and Polytechnique Montréal doing my Master's in Applied Mathematics supervised by Julie Carreau. My current research focuses on the intersection of deep learning, computer vision and climate science/modeling. I am also a visiting AI researcher at Ouranos working on super resolution tasks in climate world. I obtained my Bachelor's in Applied Mathematics with a minor in Computer Science from Amirkabir University of Technology, one of the top three universities in Iran. My research is about leveraging probabilistic deep learning and generative models to model uncertainty and improve the physical coherence of scientific applications, such as climate modeling. Beyond this, I am deeply interested in advancing research at generative AI, multi-modal learning, reinforcement learning. I am actively seeking research opportunities and collaborations in these areas to further explore the theoretical foundations of AI systems. |
|
|
I'm actively looking for research internship positions for Summer 2026. Please get in touch if you have opportunities! |
Publications |
|
A Probabilistic U-Net Approach to Downscaling Climate Simulations
Maryam AlipourHajiagha, Pierre-Louis Lemaire, Youssef Diouane, Julie Carreau, NeurIPS 2025 AI4Science Repo / arXiv A Probabilistic U-Net to downscale climate data and compare different training losses. Results show MS-SSIM best captures extremes, while afCRPS best models uncertainty and fine-scale details. |
Teaching
|