DARK distillation lets a 75M-parameter student model match or exceed a 427M-parameter teacher on fetal ultrasound benchmarks by transitioning from imitating to repelling non-target similarities.
et al.: BEHRT: Transformer for electronic health records
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
A new framework for spatial quantum sensing constructs non-local estimators for field properties using quantum sensor networks, with algebraic geometry for exact placements, entanglement for maximal precision, and error-free subspaces to cut sensor requirements.
In the Dicke model, multiparameter critical metrology achieves square-root divergent scaling for two parameters via higher-order QFIM contributions, while a Dicke dimer with triple point restores quadratic scaling for specific pairs.
Disease trajectory embeddings from longitudinal EHR data serve as structural priors to enhance multi-organ IDP representation learning, improving AUC and MAE for disease prediction across 159 conditions in UK Biobank.
Systematic benchmarking shows existing transcriptomic predictors for immune checkpoint inhibitor response have limited cross-cohort generalisability and inconsistent biomarker signals.
citing papers explorer
-
DARK: Diagonal-Anchored Repulsive Knowledge Distillation for Vision-Language Models under Extreme Compression
DARK distillation lets a 75M-parameter student model match or exceed a 427M-parameter teacher on fetal ultrasound benchmarks by transitioning from imitating to repelling non-target similarities.
-
A Framework for Spatial Quantum Sensing
A new framework for spatial quantum sensing constructs non-local estimators for field properties using quantum sensor networks, with algebraic geometry for exact placements, entanglement for maximal precision, and error-free subspaces to cut sensor requirements.
-
Multi-Parameter Multi-Critical Metrology of the Dicke Model
In the Dicke model, multiparameter critical metrology achieves square-root divergent scaling for two parameters via higher-order QFIM contributions, while a Dicke dimer with triple point restores quadratic scaling for specific pairs.
-
From Trajectories to Phenotypes: Disease Progression as Structural Priors for Multi-organ Imaging Representation Learning
Disease trajectory embeddings from longitudinal EHR data serve as structural priors to enhance multi-organ IDP representation learning, improving AUC and MAE for disease prediction across 159 conditions in UK Biobank.
-
Transcriptomic Models for Immunotherapy Response Prediction Show Limited Cross-cohort Generalisability
Systematic benchmarking shows existing transcriptomic predictors for immune checkpoint inhibitor response have limited cross-cohort generalisability and inconsistent biomarker signals.