Latest AI and machine learning research in medicare for healthcare professionals.
Large vision-language models such as CLIP struggle with long captions because they align images and texts as undifferentiated wholes. Fine-grained vision-language understanding requires hierarchical semantics capturing both global context and localized details across visual and textual domains. Yet linguistic hierarchies from syntax or semantics rarely match visual organization, and purely visual ...
Large Language Models (LLMs) trained for average correctness often exhibit mode collapse, producing narrow decision behaviors on tasks where multiple responses may be reasonable. This limitation is particularly problematic in ordinal decision settings such as clinical triage, where standard alignment removes the ability to trade off specificity and sensitivity (the ROC operating point) based on co...
Large-scale video generative models have shown emerging capabilities as zero-shot visual planners, yet video-generated plans often violate temporal co...
Prediction sets can wrap around any ML model to cover unknown test outcomes with a guaranteed probability. Yet, it remains unclear how to use them opt...
Background Patients with repaired tetralogy of Fallot (rTOF) require lifelong surveillance with cardiovascular magnetic resonance (CMR) and cardiopulm...
Graph neural networks (GNNs) have become the standard tool for encoding data and their complex relationships into continuous representations, improvin...
Data science agents promise to accelerate discovery and insight-generation by turning data into executable analyses and findings. Yet existing data sc...
Robust machine learning for regulatory genomics is studied under biologically and technically induced distribution shifts. Deep convolutional and atte...
Total-body PET/CT enables system-wide molecular imaging, but heterogeneous anatomical and metabolic signals, approximately 2 m axial coverage, and str...
1Reconstructing genomes from metagenomic assemblies is foundational to microbiome research, yet metagenome binning remains constrained by a persistent...
Deep neural networks have achieved remarkable success across a variety of tasks, yet they often suffer from unreliable probability estimates. As a res...
UNLABELLED: This study aims to develop an exploratory classification model for Juvenile Myoclonic Epilepsy (JME) based on electroencephalogram (EEG) m...
Neural networks' insufficient interpretability can lead to unguaranteed Safety of the Intended Functionality (SOTIF) issues when perceptual results ar...
We introduce a full-stack framework that scales up reasoning in vision-language models (VLMs) to long videos, leveraging reinforcement learning. We ...
Conformal prediction methods are statistical tools designed to quantify uncertainty and generate predictive sets with guaranteed coverage probabilit...
Instruction tuning has become a foundation for unlocking the capabilities of large-scale pretrained models and improving their performance on comple...
Many real-world classification problems, such as plant identification, have extremely long-tailed class distributions. In order for prediction sets ...
Unlike classification, whose goal is to estimate the class of each data point in a dataset, prevalence estimation or quantification is a task that a...
Uniform and excessive herbicide application in modern agriculture contributes to increased input costs, environmental pollution, and the emergence o...
Diffusion policy has demonstrated promising performance in the field of robotic manipulation. However, its effectiveness has been primarily limited ...