Pinar Yanardag

Modern generative models can synthesize nearly any image or video — yet steering them precisely, efficiently, and faithfully is still hard. Making these systems controllable, interpretable, and accessible is the key focus of my research.

I am a tenure-track Assistant Professor at Virginia Tech, in the Department of Computer Science, where I lead 💎 GEMLAB. I am also a member of the Sanghani Center for AI and Data Analytics.

Prior to joining Virginia Tech, I was a postdoctoral researcher at MIT. I received my Ph.D. in Computer Science from Purdue University, where I was advised by S.V.N. Vishwanathan. I completed my M.S. under the supervision of Ethem Alpaydın at Boğaziçi.

Beyond academia, I was CEO of AI Fiction, a creative design studio specializing in AI, and I co-founded GLITCH — the world's first generative-AI clothing line. At MIT, I launched the How to Generate (Almost) Anything project and Nightmare Machine.

In a past life — long before I worked on making models behave — I was a security researcher who broke software on purpose, and a core developer of a GNU/Linux distribution.