A new study reveals that the human brain processes spoken language in a sequence that closely mirrors the layered architecture of advanced AI language models. Using electrocorticography data from participants listening to a narrative, the research shows that deeper AI layers align with later brain responses in key language regions such as Broca’s area. The findings challenge traditional rule-based theories of language comprehension and introduce a publicly available neural dataset that sets a new benchmark for studying how the brain constructs meaning.

Rising sea levels along coastlines not only threaten populations, but also pose a danger to agricultural crops, which may be damaged by surging amounts of saltwater. Researchers have, in response, sought to improve salt-tolerance in plants. An international team of scientists now reports the identification of cell traits that are critical to tolerating saltwater inundation—a finding that potentially offers new pathways for creating plants that can survive in harsh environments.

Researchers at Thomas Jefferson University have developed a groundbreaking automated machine learning (AutoML) model that can accurately differentiate between two common types of brain tumors using preoperative MRI scans, potentially improving surgical planning and patient outcomes.

The study, published in the December 2025 issue of Otolaryngology–Head and Neck Surgery, represents the first application of AutoML technology specifically trained to classify pituitary macroadenomas and parasellar meningiomas—two benign but challenging-to-distinguish brain tumors that require different treatment approaches.