Physicist working on machine learning for physics
I build physics-informed neural networks: models trained against the equations a system obeys, not only against data. I use them to solve and control physical systems, from relativistic fluids and black-hole oscillations to quantum control and sensing.
I am a Quantum Algorithm Engineer at Kipu Quantum and a PhD student at the Universitat de València, in the Intelligent Data Analysis Laboratory.
Three lines of work, each with a tutorial post and the papers behind it.
Physics-informed neural networks for differential equations, including systems with sharp transitions and coupled dynamics, and transformer-based particle tracking.
Neural approaches to counterdiabatic driving, which suppresses unwanted transitions during quantum evolution, and control protocols that raise the quantum Fisher information of a sensor.
Physics-informed learning for relativistic hydrodynamics, the gravitational collapse of a scalar field, and the oscillation frequencies of rotating black holes.
arXiv:2608.19774 (2026), preprint
arXiv:2604.18506 (2026), preprint
Machine Learning: Science and Technology (2026)
Gradient-annihilated PINNs for solving Riemann problems: Application to relativistic hydrodynamics
Computer Methods in Applied Mechanics and Engineering (2024)
Physics-informed neural networks for an optimal counterdiabatic quantum computation
Machine Learning: Science and Technology (2024)
From a magnetic-field sensor to learned controls: how PINNs use physics to guide training and improve quantum sensing protocols.
Density, pressure and velocity in a relativistic shock tube: explore the Euler equations in Minkowski space and how PINNs learn fluid evolution.
How PINNs learn counterdiabatic quantum controls: network outputs, physics-based losses, training and independent validation.
How physical knowledge shapes learning, how PINNs solve differential equations, and how to check whether a learned solution is reliable.
Write to me about physics-informed learning, quantum algorithms or a paper you are working on.
