Understanding Visual Generative Models for Precise Control

Despite remarkable progress in image and video generation, translating user intent into precise and consistent visual outputs remains a challenge. This talk explores how understanding the representations within generative models can enable finer control over what they create. It connects semantic image editing with compositional generation, examining how visual concepts can be isolated, manipulated, and combined while preserving their identity and surrounding content. Building on these insights, structured visual inputs provide a way to express complex intent through subject references, poses, and spatial layouts. The discussion then extends from images to video, where representations must evolve to preserve scene continuity while accommodating motion and change. Together, these directions establish a unified perspective on how visual representations can support controllable editing, composition, and coherent generation across space and time. Yusuf Dalva is a Ph.D. candidate at Virginia Tech, advised by Pinar Yanardag and affiliated with the Sanghani Center for Artificial Intelligence and Data Analytics. His research focuses on understanding and controlling visual generative models, with an emphasis on image editing, compositional generation, and coherent video synthesis. His work has appeared at CVPR, NeurIPS, ECCV, and SIGGRAPH, including oral and spotlight presentations. He has conducted research at Adobe Research, Snap Research, and Google Research, and holds B.Sc. and M.Sc. degrees in Computer Engineering from Bilkent University.