About me

I am a Ph.D. student at École de technologie supérieure in Montreal, Quebec, Canada, conducting research at LIVIA under the supervision of Professors Jose Dolz and Ismail Ben Ayed.

My current research focuses on enhancing the pre-training of ViT-based approaches on large-scale datasets, such as ImageNet. Prior to this, I concentrated on low-supervision techniques in computer vision and the application of pre-trained vision-language and foundation models. During my Ph.D., I addressed challenges in generalized few-shot semantic segmentation, few-shot adaptation of vision-language models for classification, and open-vocabulary semantic segmentation.

I hold a master’s degree in artificial intelligence from Sharif University of Technology. During my master’s program, I worked on feature disentanglement in Variational Autoencoders (VAEs), under the supervision of Professor Mahdieh Soleymani Baghshah. My academic journey began at the same institution, where I completed my bachelor’s degree.

In addition to my academic background, I have practical experience as a software engineer at Divar, a prominent classified ads website in my home country.