Generative Adversarial Networks (GANs) are powerful image synthesis models that have revolutionized generative modeling in computer vision. However, what knowledge GANs learn in latent representations and how these internal representations can be used to synthesize diverse and semantically meaningful images is still an ongoing research question. Exploring what kind of controls these models provide will not only allow us to design better models, but will also open up exciting possibilities for creative applications and human-AI collaboration. In this talk, I will present our recent work from CATLAB  on interpreting and manipulating the latent space of GANs (ICCV'21, WACV'21). I will also talk about generative models in creative contexts such as fashion and theater plays (Best Paper at CtrlGen Workshop at NeurIPS'21) and discuss human-AI collaborated designs as part of the How to Generate (Almost) Anything project. Finally, I will briefly discuss our recent efforts to address issues related to fairness and ethics in generative models, and conclude my talk with future work on generative models, creativity, and human-AI collaboration.

—

Pinar Yanardag Delul received her PhD in Computer Science from Purdue and completed her postdoctoral research at MIT Media Lab. She is currently a principal investigator at Bogazici University, Istanbul, Turkey, where she leads CATLAB (Creative AI Technologies Lab).  Her research interests are in the area of generative adversarial networks (GANs) and developing deep learning approaches to enable creativity and human-AI collaboration. Her research has been published at conferences such as NeurIPS, ICCV, and KDD, and featured in mainstream media (e.g., The Washington Post, BBC, CNN) and magazines (e.g., Motherboard, Rolling Stone). She is also CEO of AI Fiction, a creative design studio focused on the entertainment industry, for which she received a Creative Director nomination at the 72nd Primetime Emmy Awards for her work on the Westworld TV series. During her studies, she was supported by Fulbright Fellowship, and Google Anita Borg Scholarship.

Faculty Host:  Jim McCann

In Person and Zoom Participation. See announcement.