Research focus
About the research
How can human creators and generative models collaborate so creators control outputs more easily and tell visual stories?
Read the full research overview
The group develops interfaces and algorithms that let creators steer controllable visual synthesis of images, videos, 3D content, and combined visual and tactile data. Another question is how creators can adapt existing models to new tasks, concepts, and styles, and even rewrite the rules those models follow. Researchers also ask how creators could opt into or out of generative systems whenever they choose, and how contributors of training data should be credited. Generative models are also used to produce synthetic data that improves computer vision and robotics systems.
Selected publications
3 listedSDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations
arXiv (Cornell University)
One-Step Image Translation with Text-to-Image Models
arXiv (Cornell University)
SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
arXiv (Cornell University)
People & alumni
Team details haven’t been added. See the lab’s website for its current members.
Alumni details haven’t been added. Check the lab’s official website.
Sources & listing information
Find Research Labs maintains this page using public sources. The faculty member, lab, and university have not claimed or approved this listing. Listing a lab does not indicate endorsement, partnership, or a recruiting opportunity.
Request a correction or removal ↗ · About directory listings