Tech Xplore

Mistaken correlations: Why it's critical to move beyond overly aggregated machine-learning metrics

MIT researchers have identified significant examples of machine-learning model failure when those models are applied to data ...

New research decodes hidden bias in health care LLMs

Artificial intelligence is increasingly used as a tool in many health care settings, from writing physicians' notes to making ...
Frontiers

Advancing Deep Learning Frameworks for Enhanced Cervical Cancer Diagnosis, Staging and Treatment

Cervical cancer detection and diagnosis are undergoing a transformation with the integration of advanced deep learning (DL) technologies. Despite ...
InfoQ

MIT's Recursive Language Models Improve Performance on Long-Context Tasks

Researchers at MIT's CSAIL published a design for Recursive Language Models (RLM), a technique for improving LLM performance ...
Tech Xplore

Benchmarking framework reveals major safety risks of using AI in lab experiments

While artificial intelligence (AI) models have proved useful in some areas of science, like predicting 3D protein structures, ...

Machine learning can predict patients' responses to antidepressants—while disentangling drug and placebo effects

Depression is one of the most widespread mental health disorders worldwide, affecting approximately 4% of the global ...
Scientific Research Publishing

Implementing an Electrocardiogram Suite in the Emergency Department to Decrease Door-to-EKG Time ()

Implementing an Electrocardiogram Suite in the Emergency Department to Decrease Door-to-EKG Time ...

AI-Generated Mental Health Advice Must Shift From Discrete-Classifications To Continuous Multidimensional Psychological Analyses

Mental health is not to be reduced to simple discrete classifications, but that's what AI is doing to us. AI can be ...

Why reinforcement learning plateaus without representation depth (and other key takeaways from NeurIPS 2025)

Why reinforcement learning plateaus without representation depth (and other key takeaways from NeurIPS 2025) ...

Decoded rules of microRNA strand selection reveal conserved, programmable features

MicroRNAs, whose discovery was recognized with the 2025 Nobel Prize in Physiology or Medicine, are central regulators of gene ...
IEEE

Label Feature Co-Learning for Facial and EEG Emotion Recognition

Abstract: Recognizing human emotions through behavioral and physiological signals is fundamental to overall health. However, since emotion occurs transiently, a semantics mismatch exists between the ...
IEEE

A Nearly Hamiltonian Neural Network-Enhanced Multi-Machine Power System Excitation Control

Abstract: The generalized Hamiltonian system theory (GHST) is a powerful tool for excitation control in high-dimensional non-linear power systems, but relies on reduced-order dynamics, given the ...