NTK-UQ produces 31-37% sharper 90% prediction intervals than split conformal prediction for extreme weather forecasts, with adaptive scaling via architecture-dependent eigenvalue truncation and ICA decomposition of last-layer features.
A systematic review of intermediate fusion in multimodal deep learning for biomedical applications , volume=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
A compact 0.09B model using hierarchical discrete tokenization and prompted latent translation outperforms larger baselines in cross-modal PPG-to-ECG synthesis and cross-frequency super-resolution.
Comparison of top-down and bottom-up approaches for collecting news on landslides from German sources reveals differences in event coverage that affect downstream studies.
In a private dataset of 353 patients, medical records and cardiac biomarkers outperform vascular biomarkers and GNNs on vascular graphs for PE risk stratification, suggesting vascular graphs hold no discriminative information.
citing papers explorer
-
The Course of News Events: A Comparison of Bottom-Up and Top-Down Approaches for Collecting Text-Based Data about Disasters
Comparison of top-down and bottom-up approaches for collecting news on landslides from German sources reveals differences in event coverage that affect downstream studies.