Healthcare

CIMSleepNet: a novel framework for robust sleep staging from incomplete multimodal physiological signals using contrastive imagination.

Reaction-GFlowNet (RGFN) revolutionizes small molecule discovery by generating synthesizable molecules directly within the chemical reaction space, dramatically expanding the search space for drug dis…

AI-powered dual-target drug design is revolutionized by repurposing pretrained diffusion models, achieving zero-shot transfer learning and outperforming existing methods.

ReMAP repurposes able-bodied motion prediction models for limb-impaired patients using network inversion and retrieval-augmented mapping, significantly improving motion forecasting.

realSEUDO: Real-time calcium imaging analysis now possible at speeds exceeding 30 Hz, enabling sophisticated closed-loop neuroscience experiments.

Randomized sparse matrix compression boosts large-scale cancer radiotherapy optimization, improving treatment quality without sacrificing speed.

SpatioTemporal Video Diffusion (STVD) revolutionizes precipitation downscaling using a novel diffusion model, achieving state-of-the-art accuracy in super-resolution while capturing crucial distributi…

Physics-regularized multi-modal image assimilation improves brain tumor localization by integrating data-driven and physics-based cost functions, achieving state-of-the-art performance in capturing tu…

This paper introduces a novel, robust online control framework for managing evolving populations, achieving near-optimal control even in complex, noisy systems.

Newton Informed Neural Operator efficiently solves nonlinear PDEs with multiple solutions by learning the Newton solver, enabling faster computation and the discovery of new solutions with limited dat…

MotionTTT: Deep learning enables accurate 3D motion-corrected MRI by cleverly estimating motion parameters during test-time training, significantly improving image reconstruction.

MeLLoC: Mechanism Learning for Lossless Compression, a novel approach that combines high-order mechanism learning with classical encoding, significantly improves lossless compression for scientific da…

Medformer: A novel multi-granularity patching transformer achieves state-of-the-art performance in medical time series classification, excelling in challenging subject-independent settings.

Med-Real2Sim uses physics-informed self-supervised learning to build non-invasive medical digital twins, enabling in-silico clinical trials and unsupervised disease detection.

ALTER, a novel brain graph transformer, leverages long-range dependencies to achieve state-of-the-art accuracy in neurological disease diagnosis.

ProtoSurv uses heterogeneous graph representation learning to predict cancer survival more accurately by incorporating tumor heterogeneity and tissue spatial relationships from WSIs.

BeatDiff, a lightweight diffusion model, reconstructs ECG morphology from indirect signals, enabling noise removal, artifact reduction, missing-lead recovery, and anomaly detection.

Conformal Prediction with Length Optimization (CPL) achieves shorter, conditionally valid prediction sets by optimizing length while ensuring coverage across various covariate shifts.

KEDGN, a novel graph neural network, leverages medical knowledge to model variable-specific temporal dependencies and dynamic inter-variable correlations in irregularly sampled medical time series, si…

KFNN dynamically determines optimal neighborhood sizes for label integration in crowdsourcing, significantly boosting accuracy and robustness, especially with limited noisy labels.