- arxiv/cs.LG · 4 dk
Retrieval-Augmented Set Completion for Clinical Code Authoring
A two-stage approach retrieves similar clinical value sets then classifies candidates, outperforming direct LLM generation on standardized medical vocabularies.
17 Nisan 2026 Oku → → - arxiv/cs.LG · 4 dk
Retrieval beats memorization for clinical code selection
A two-stage retrieval-then-classify method outperforms direct LLM generation for assembling clinical value sets from large standardized vocabularies.
17 Nisan 2026 Oku → → - arxiv/cs.LG · 8 dk
Machine Learning Maps Drug Binding to Viral RNA Pseudoknot
Spectral map analysis reveals how small-molecule inhibitors distort SARS-CoV-2 RNA structure in topology-dependent ways, with protonation state determining mechanism.
17 Nisan 2026 Oku → → - arxiv/cs.LG · 8 dk
Action Aliasing Breaks Safe RL Differently Depending on Filter Placement
A formal comparison of two projection-based safety strategies reveals that embedding safeguards in the policy creates gradient rank deficiency, while environment-level filters distribute the problem to the critic.
17 Nisan 2026 Oku → → - arxiv/cs.LG · 3 dk
Transformer models outperform CNNs in prostate MRI segmentation
SwinUNETR achieves 5-point Dice improvement over standard UNet when trained on mixed-reader datasets, suggesting transformer attention handles annotation variability better.
17 Nisan 2026 Oku → → - arxiv/cs.LG · 8 dk
Quantum kernel inference cuts query cost by removing data-size dependence
New algorithm reduces quantum machine learning inference complexity from O(N) to O(1) in data size, achieving query-optimal bounds via amplitude estimation.
17 Nisan 2026 Oku → → - arxiv/cs.LG · 8 dk
Formalizing How Much Data Proves a Learning Model Right
Researchers formalize identifying information—the bits needed to confirm or reject a hypothesis—bridging information theory with practical sample complexity.
17 Nisan 2026 Oku → → - arxiv/cs.LG · 8 dk
Estimating classification ceiling without perfect labels
Ushio et al. show how to measure the theoretical best-case error rate in binary classification using imperfect soft labels and calibration techniques.
17 Nisan 2026 Oku → →