4 papers
Learning Multiple Timescales for Goal-Conditioned Reinforcement Learning
Pedro Robles Dutenhefner, Dikshant Shehmar, Wagner Meira +1
Existing approaches to offline goal-conditioned reinforcement learning (GCRL) struggle with long-horizon tasks. Discounting shrinks value differences between distant states until t…
Inference-Time Decision Calibration for Temporal Classification
Arthur Chagas, Arthur Buzelin, Yan Aquino +4
Temporal classification errors are often treated as representation failures, but they can also arise from how available evidence is converted into decisions. This paper proposes a…
Beyond Patient Invariance: Learning Cardiac Dynamics via Action-Conditioned JEPAs
Jose Geraldo Fernandes, Luiz Facury, Pedro Robles Dutenhefner +1
Self-supervised learning in healthcare has largely relied on invariance-based objectives, which maximize similarity between different views of the same patient. While effective for…
Transferring Clinical Knowledge into ECGs Representation
Jose Geraldo Fernandes, Luiz Facury de Souza, Pedro Robles Dutenhefner +2
Deep learning models have shown high accuracy in classifying electrocardiograms (ECGs), but their black box nature hinders clinical adoption due to a lack of trust and interpretabi…