publications

A Hierarchical Conformal Framework for Uncertainty-Aware Length of Stay Prediction in Multi-Hospital Settings

Blending Optimism and Pessimism via Wasserstein Barycenters for Continuous Control

Efficient Counterexample Generation for Control Systems Using Multi-Fidelity Bayesian Optimization

Fairness Without Discrimination: Individually Fair Outcomes in the Kidney Exchange Problem

Federated Distributional Reinforcement Learning with Distributional Critic Regularization

Hospital and Regional Effects on Length of Stay: A Multilevel Modeling Approach

How Much Do Your Models Disagree? Adaptive MPC Safety from Ensemble Uncertainty

Adaptive Conformal Prediction via Bayesian Uncertainty Weighting for Hierarchical Healthcare Data

Can Optimal Transport Improve Federated Inverse Reinforcement Learning?

Density-Ratio Weighted Behavioral Cloning: Learning Control Policies from Corrupted Datasets

Flow-Corrected Thompson Sampling for Non-Stationary Contextual Bandits

Geometry-Aware Decentralized Sinkhorn for Wasserstein Barycenters

Geometry-Aware Uncertainty Quantification via Conformal Prediction on Manifolds

Geometry-Grounded Flow Matching on Compact Manifolds

Logic-Guided Vector Fields for Constrained Generative Modeling

Metriplectic Conditional Flow Matching for Structure-Preserving Dynamics Learning

Wasserstein Stability of Contracting Flows: Effective Rates, Euler Self-Correction, and Noise Tightening

What Does a Neural PDE Solver Really Learn? A Residual-Spectrum Diagnostic

When Distance Matters: Wasserstein Trust Regions for Multi-Agent Coordination

When Does Multi-Agent Language-Model Debate Converge? A Bifurcation on the Probability Simplex

Conformal Prediction Across Scales: Finite-Sample Coverage with Hierarchical Efficiency

Distributionally Robust Lyapunov-Barrier Networks for Safe and Stable Control Under Uncertainty

Multi-Fidelity Temporal Reasoning: A Stratified Logic for Cross-Scale System Specifications

Multilevel Constrained Bandits: A Hierarchical Upper Confidence Bound Approach with Safety Guarantees

Geometry-Aware Backdoor Attacks: Leveraging Curvature in Hyperbolic Embeddings

Hierarchical Neuro-Symbolic Decision Transformer

Implicit Constraint-Aware Off-Policy Correction for Offline Reinforcement Learning

Metriplectic Conditional Flow Matching for Dissipative Dynamics

WAVE: Wasserstein Adaptive Value Estimation for Actor-Critic Reinforcement Learning

Wasserstein-Barycenter Consensus for Cooperative Multi-Agent Reinforcement Learning

A Survey on Reinforcement Learning in Aviation Applications

BEACON: A Bayesian Evolutionary Approach for Counterexample Generation of Control Systems

Concurrent Learning of Control Policy and Unknown Safety Specifications in Reinforcement Learning

Forward Variable Selection Enables Fast and Accurate Dynamic System Identification with Karhunen-Loève Decomposed Gaussian Processes

The Synergy Between Optimal Transport Theory and Multi-Agent Reinforcement Learning

Optimal Transport-Assisted Risk-Sensitive Q-Learning

Exploring the Role of Simulator Fidelity in the Safety Validation of Learning-Enabled Autonomous Systems

Joint Falsification and Fidelity Settings Optimization for Validation of Safety-Critical Systems: A Theoretical Analysis

Falsification of Learning-Based Controllers through Multi-Fidelity Bayesian Optimization

Joint Learning of Policy with Unknown Temporal Constraints for Safe Reinforcement Learning

LLMs-Augmented Contextual Bandit

Policy Refinement with Human Feedback for Safe Reinforcement Learning

Risk-Aware Reinforcement Learning Through Optimal Transport Theory

Safety Validation of Learning-Based Autonomous Systems: A Multi-Fidelity Approach

Understanding Reward Ambiguity Through Optimal Transport Theory in Inverse Reinforcement Learning