Skip to main content

Adam Klivans

Artificial Intelligence Trained to Draw Inspiration From Images, Not Copy Them

Three rows of similarly themed illustrations—earnest dogs, scientist pandas and robot graffiti—differ in each of five iterations per row.

05/17/2024 - Researchers are using corrupted data to help generative AI models avoid the misuse of images under copyright. Powerful new artificial intelligence models sometimes, quite famously, get things wrong — whether hallucinating false information or memorizing others’ work and offering it up as their own. To address the latter, researchers led by a team at The University of Texas at Austin have developed a framework to train AI models on images corrupted beyond recognition.