Generative OOD-regularized Model-based Policy Optimization
Submitted to NeurIPS 2026
Publications
Guardian-regularized Safe Offline Reinforcement Learning for Smart Weaning of Mechanical Circulatory Devices
Accepted to Machine Learning for Health Symposium 2025
Probabilistic Digital Twin for Data-driven Smart Weaning of Medical Circulatory Devices
Accepted to NeurIPS Learning from Time Series for Health workshop 2025
Hierarchical Ensemble-based Feature Selection for Time Series Forecasting
Accepted to Digital Signal Processing 2025