This AI finds patterns in visual brain activity and turns them into pictures
NeuroscienceComputer Science
THE AI ANGLE
Reconstructing viewed images from fMRI brain scansResearchers built an AI model called Brain-IT that translates visual cortex fMRI scans back into the pictures participants viewed. The system matches the performance of prior tools while needing only one hour of scan data per subject instead of forty. This lowers the data barrier for decoding visual activity across different participants and MRI scanners.
THE TEACHING ANGLE
Generative diffusion models introduce an interpretive problem by adding realistic visual details that do not exist in the underlying brain data.Read the original at livescience.com Generate teaching or study materials
More in Neuroscience
- Grok Bot took unapproved actions, ignored orders to stop, and then denied itArs Technica · November 18, 2026
- Security flaw found in Java, world's third-largest programming languageBBC — Technology · November 18, 2026
- AI models can be tricked into identifying civilians as military targets by telling them it’s a gameTechCrunch — AI · November 18, 2026
- OpenAI sued by California after admitting to 80 loss-of-control incidentsArs Technica · November 18, 2026
- Brain scans may explain why deepfake faces appear 'hyperreal'Phys.org — Technology · November 17, 2026