Latest AI and machine learning research in medicare for healthcare professionals.
Standard evaluation of many recognition systems contains distribution shift by construction, since benchmarks place disjoint conditions in the training and test splits. Under such a shift, split conformal prediction keeps marginal coverage near the nominal level while per-class coverage fails silently: on a real cross-subject skeleton benchmark, marginal coverage stays near ninety percent, the wor...
This study focuses on the relationship between access to Advanced Neonatal Care (ANC) and fertility across the regions in Ghana between 1988 and 2022. It builds on previous studies focused on inequity in maternal health across subnational levels and incorporates spatial analytics, machine learning, and a welfare-adjusted fertility care metric. Nine waves of the Ghana Demographic and Health Survey ...
We present Audio-Visual Flamingo (AV-Flamingo), a fully open state-of-the-art audio-visual large language model (AV-LLM) for joint understanding and r...
Long-tailed label distributions reduce the reliability of deep learning for electrocardiogram (ECG) arrhythmia diagnosis, particularly for clinically ...
Text-to-image (T2I) models can synthesize realistic, prompt-aligned images, yet samples generated for the same prompt often cover only a small subset ...
Large language models achieve strong scores on medical benchmarks, yet these benchmarks evaluate each question in isolation, providing no measure of w...
Radiative Gaussian splatting has made sparse-view CT reconstruction fast, but existing methods output point estimates with no notion of where the reco...
Heavy-tailed data arise in many domains where rare events carry disproportionate importance, such as imbalanced image datasets, financial returns, and...
Large language model (LLM) agents can increasingly plan, use tools, maintain memory, and execute long-horizon tasks. These advances motivate two linke...
In operational 1:N face identification, a crucial question arises for each probe: is this person enrolled in the gallery or not? The stakes are high a...
Introduction: Climate change disproportionately affects disadvantaged communities, yet construction workforce education rarely addresses interconnecte...
Objectives: Explore the perspectives of primary caregivers towards pediatric tissue-based research participation. Design: Cross-sectional. Setting: Tw...
Radiomic features derived from medical images and segmentation masks are used to support decision making in clinical imaging pipelines. In practice, t...
Background: Emerging artificial intelligence and machine learning (AI/ML) tools can help generate robust knowledge to support precision rehabilitation...
Conformal prediction is being adopted in drug discovery to put an honest number on model reliability: pick an error rate alpha, and the method returns...
Learned optimization aims to improve upon hand-designed optimizers (e.g., Adam and Muon) by meta-learning small neural network optimizers over a distr...
We present HunyuanOCR-1.5, a lightweight end-to-end OCR-specialized vision-language model. HunyuanOCR unifies document parsing, text spotting, informa...
Modern GPU domain-specific languages (DSLs), such as Triton and TileLang, are increasingly used to implement specialized deep-learning kernels and as ...
Background: Despite advances in circulating tumor DNA analysis, reliable detection of oncological disease from ultra-low coverage whole genome sequenc...
Molecular docking is widely used in structure-based drug discovery, yet most approaches provide point estimates without rigorous uncertainty quantific...