A new brain-computer interface (BCI) has enabled a paralyzed man to control a robotic arm by simply imagining movements. Unlike previous BCIs, which lasted only a few days, this AI-enhanced device worked reliably for seven months ..read more

A new AI model can measure how fast a person’s brain is aging using MRI scans, providing a powerful tool for detecting cognitive decline. Unlike previous methods, this model tracks brain aging over time, identifying regions most affected and correlating changes with cognitive function ..read more

Researchers have developed a geometric deep learning approach to uncover shared brain activity patterns across individuals. The method, called MARBLE, learns dynamic motifs from neural recordings and identifies common strategies used by different brains to solve the same task ..read more

Researchers have mapped over 70,000 synaptic connections in rat neurons using a silicon chip with 4,096 microhole electrodes, significantly advancing neuronal recording technology. Unlike traditional electron microscopy, which only visualizes synapses, this method also measures connection strength, providing deeper insight into brain network function. The chip mimics patch-clamp electrodes but at a massive scale, enabling highly sensitive intracellular recordings from thousands of neurons simultaneously ..read more

A new study reveals how AI-driven deep learning models can decode the genetic regulatory switches that define brain cell types across species. By analyzing human, mouse, and chicken brains, researchers found that some brain cell types remain highly conserved over 320 million years, while others have evolved uniquely ..read more

A new study suggests that ChatGPT’s responses in psychotherapy scenarios are often rated higher than those written by human therapists. Researchers found that participants struggled to distinguish between AI-generated and therapist-written responses in couple’s therapy vignettes ..read more

A new AI model, based on the PV-RNN framework, learns to generalize language and actions in a manner similar to toddlers by integrating vision, proprioception, and language instructions. Unlike large language models (LLMs) that rely on vast datasets, this system uses embodied interactions to achieve compositionality while requiring less data and computational power ..read more

A study reveals that London taxi drivers prioritize complex and distant junctions during their initial "offline thinking" phase when planning routes, rather than sequentially considering streets. This efficient, intuitive strategy leverages spatial awareness and contrasts with AI algorithms, which typically follow step-by-step approaches ..read more

Researchers have developed an AI model that accurately predicts gene activity in any human cell, providing insights into cellular functions and disease mechanisms. Trained on data from over 1.3 million cells, the model can predict gene expression in unseen cell types with high accuracy. It has already uncovered mechanisms driving a pediatric leukemia and may help explore the genome's "dark matter," where most cancer mutations occur ..read more

Researchers have developed a Genetic Progression Score (GPS) using artificial intelligence to predict the progression of autoimmune diseases from preclinical symptoms to full disease. The GPS model integrates genetic data and electronic health records to provide personalized risk scores, improving prediction accuracy by 25% to 1,000% over existing models ..read more