Search papers, labs, and topics across Lattice.
4
0
6
7
A single foundation model can effectively leverage heterogeneous cardiac signals to achieve superior performance across multiple tasks, defying the limitations of modality-specific training.
Achieving 71.6% accuracy in diagnosing unseen medical conditions with just two labeled examples showcases the power of federated learning in low-resource clinical settings.
Adaptive compute allocation in zero-shot learning can match or exceed supervised performance while halving compute costs, even in complex domains like respiratory audio classification.
Unlock vast troves of legacy ECG image data for automated cardiovascular diagnostics with a self-supervised framework that rivals signal-based analysis.
