Teaching large language models how to absorb new knowledge
Reports and Proceedings
Updates every hour. Last Updated: 23-Nov-2025 13:11 ET (23-Nov-2025 18:11 GMT/UTC)
MIT researchers developed a technique that enables LLMs to permanently absorb new knowledge by generating study sheets based on data the model uses to memorize important information.
A new heart monitoring system combining 3D printing and artificial intelligence could transform the way doctors measure and diagnose patients' heart health.
Developed at SFU’s School of Mechatronic Systems Engineering, the system features reusable dry 3D-printed electrodes embedded in a soft chest belt – the folding origami-shaped design uses gentle suction to stick to the skin.
Carbon-based ink printed on the suction cup replaces electrolyte gel, conducting the heart’s electrical signals through to a wearable device with built-in AI software to pre-diagnose of up to 10 types of arrhythmias, or irregular heart rhythms.
A new MIT system identifies the smallest possible dataset that can be used to optimally solve a complex problem with many potential solutions. This technique could help engineers or scientists solve problems faster and with less expense.
A mouse study led by University of California, Riverside biomedical scientists suggests that everyday exposure to microplastics — tiny fragments shed from packaging, clothing, and countless plastic products — may accelerate the development of atherosclerosis, the artery-clogging process that leads to heart attacks and strokes. The harmful effects were seen only in male mice, offering new clues about how microplastics may affect cardiovascular health in humans.