I’m a Ph.D. candidate in the Vision and Image Understanding Lab at Johns Hopkins University, working under Prof. Vishal M. Patel. My research explores a wide spectrum of neural network architectures—including structured state space models, vision-language mdodels, and diffusion-based models—to tackle challenges in computer vision and medical imaging.

Before joining Johns Hopkins, I earned both my B.Sc. and M.Sc. with High Honors from Bilkent University where I worked under supervision of Prof. Tolga Cukur, focusing on deep unsupervised learning for accelerated MRI reconstruction. From there, I branched out to multi-modal vision-language models, change detection, unsupervised image translation, and self-supervised learning methods.

Feel free to reach out if you’d like to discuss research or potential collaborations!

Google Scholar: https://scholar.google.com/citations?user=JqK7g60AAAAJ&hl=en