Over the past years, computer scientists have introduced increasingly sophisticated generative AI models that can produce personalized content following specific inputs or instructions. While image generation models are now widely used, many of them are unpredictable and precisely controlling the images they create remains a challenge.

In a recent paper presented at this year’s Conference on Computer Vision and Pattern Recognition (CVPR 2025), held in Nashville, June 11–15, researchers at NVIDIA introduced DiffusionRenderer, a new machine learning approach that could advance the generation and editing of images, allowing users to precisely adjust specific image attributes.

“Generative AI has made huge strides in visual creation, but it introduces an entirely new creative workflow that differs from classic graphics and still struggles with controllability,” Sanja Fidler, VP of AI Research at NVIDIA and head of the Spatial Intelligence lab, told Tech Xplore.

For the first time, researchers at the Netherlands Institute for Neuroscience and Amsterdam UMC have identified what happens in neural networks deep within the brain during obsessive thoughts and compulsive behaviors. Using electrodes implanted in the brain, they observed how specific brain waves became active. These brain waves serve as a biomarker for obsessive-compulsive disorder (OCD) and are an important step towards more targeted treatments.

OCD is a psychiatric disorder in which people suffer from obsessive thoughts (obsessions) and compulsive behaviors (compulsions). A well-known example is fear of contamination: someone is constantly afraid of becoming infected (the obsession) and feels compelled to wash their hands over and over again (the compulsion).

In OCD, communication appears to be disrupted between the cerebral cortex, the striatum, and the thalamus, areas of the brain that together form the CSTC circuit. Normally, this circuit mainly coordinates movement and motivation.