Developing probabilistic machine learning that quantifies uncertainty for robust scientific computing. Creating algorithms that deliver predictions with confidence estimates, empowering scientists to make informed decisions at the intersection of models and data.
The accepted ICML 2026 paper introduces RAMBO, a Bayesian optimization framework that uses Dirichlet process mixtures of Gaussian processes to adapt to heterogeneous objective regimes and improve uncertainty-aware search across scientific design tasks. Congrats to Yan Zhang .
The accepted IJCNN 2026 paper presents COMPOL, a unified neural operator framework that models interactions among coupled physical processes with recurrent and attention-based feature aggregation for scalable multi-physics simulations. Congrats to Junqi Qu .
ATOM: A Framework of Detecting Query-Based Model Extraction Attacks for Graph Neural Networks was published at KDD 2025, presenting a real-time detection framework for graph neural network model extraction attacks.
