Research across scientific machine learning, quantum dynamics and relativistic physics.
More on Google ScholarComputes the oscillation frequencies of rotating black holes with physics-informed neural networks. A two-dimensional solver preserves the coupled radial-angular structure without separating variables.
arXiv:2608.19774
Uses physics-informed neural networks to design control protocols that increase quantum Fisher information in driven spin systems. The work connects quantum dynamics and control with improved sensitivity for parameter estimation.
arXiv:2604.18506
Compares neural architectures for scalar-field dispersion and gravitational collapse, including the threshold of black-hole formation. The study examines how network design and adaptive sampling affect accuracy and stability.
Machine Learning: Science and Technology
Compares transformer-based methods for associating detector hits with particle tracks in simulations for the high-luminosity LHC. It examines reconstruction accuracy and computational cost for sequential and one-shot approaches.
The European Physical Journal C
Introduces a weighted physics loss that reduces the influence of steep gradients when learning discontinuous solutions. Tests on relativistic Riemann problems assess how well the method captures shocks and other fluid discontinuities.
Computer Methods in Applied Mechanics and Engineering
Learns counterdiabatic controls from physical constraints to suppress unwanted transitions during quantum computation. A two-qubit molecular example demonstrates the joint design of control schedules and adiabatic gauge potentials.
Machine Learning: Science and Technology
Investigates deep learning to estimate malignant transformation and high-risk dysplasia from photographs of oral leukoplakia. The pipeline combines lesion segmentation, classification and heatmaps to help interpret its predictions.
Oral Oncology
Selected bibliography · Updated October 2026. Preprints are labeled separately from journal articles.