Hidir Yesiltepe

I am a PhD student at Virginia Tech, affiliated with the Sanghani Center for Artificial Intelligence and Data Analytics, where I am advised by Pinar Yanardag. My research specializes in controllable video generation where I have explored broad spectrum of topics including Motion Transfer, Semantic Video Editing, Video Super-Resolution, Autoregressive Video Distillation, and Novel View Synthesis. Previously, I was a Research Intern at Meta, Adobe and an Applied Scientist Intern at Amazon.

Prior to my PhD, I graduated from METU Computer Engineering. During my Bachelor's, I had the opportunity to conduct generative modeling research at KTH Royal Institute of Technology in Sweden and University of Edinburgh in UK.