Related papers: pyTRAIN -- a modern TRAIN implementation
When exoplanets pass in front of their stars, they imprint a transit signature on the stellar light curve which to date has been assumed to be symmetric in time, owing to the planet being modelled as a circular area occulting the stellar…
Spectral line observations are an indispensable tool to remotely probe the physical and chemical conditions throughout the universe. Modelling their behaviour is a computational challenge that requires dedicated software. In this paper, we…
We introduce a new open-source Python x-ray tracing code for modelling Bragg diffracting mosaic crystal spectrometers: High Energy Applications Ray Tracer (HEART). HEART's high modularity enables customizable workflows as well as efficient…
With the advancements in open-source models, training (or finetuning) models on custom datasets has become a crucial part of developing solutions which are tailored to specific industrial or open-source applications. Yet, there is no single…
PINT is a pure-Python framework for high-precision pulsar timing developed on top of widely used and well-tested Python libraries, supporting both interactive and programmatic data analysis workflows. We present a new frequentist framework…
We proposed the boundary-integral type neural networks (BINN) for the boundary value problems in computational mechanics. The boundary integral equations are employed to transfer all the unknowns to the boundary, then the unknowns are…
Thermal infrared (TIR) tracking is pivotal in computer vision tasks due to its all-weather imaging capability. Traditional tracking methods predominantly rely on hand-crafted features, and while deep learning has introduced correlation…
Large Reasoning Models (LRMs) have recently achieved strong mathematical and code reasoning performance through Reinforcement Learning (RL) post-training. However, we show that modern reasoning post-training induces an unintended…
In order to meet the challenges of new accelerator and space projects and further improve modelling of radiation effects in microscopic objects, heavy-ion interaction and transport physics have been recently incorporated into the MARS15…
Machine learning (ML) techniques have recently enabled enormous gains in sensitivity to new phenomena across the sciences. In particle physics, much of this progress has relied on excellent simulations of a wide range of physical processes.…
The study of beam transport is of central importance to the design and performance assessment of modern particle accelerators. In this paper, we benchmark two contemporary codes, DIMAD and BDSIM, the latter being a relatively new tracking…
TIM (The Interactive METATOY) is a ray-tracing program specifically tailored towards our research in METATOYs, which are optical components that appear to be able to create wave-optically forbidden light-ray fields. For this reason, TIM…
Physics-Informed Neural Networks (PINN) are neural networks (NNs) that encode model equations, like Partial Differential Equations (PDE), as a component of the neural network itself. PINNs are nowadays used to solve PDEs, fractional…
Spatiotemporal trajectories are sequences of timestamped locations, which enable a variety of analyses that in turn enable important real-world applications. It is common to map trajectories to vectors, called embeddings, before subsequent…
We develop improved physics-informed neural networks (PINNs) for high-order and high-dimensional power system models described by nonlinear ordinary differential equations. We propose some novel enhancements to improve PINN training and…
High-energy physics experiments require fast and efficient methods for reconstructing the tracks of charged particles. The commonly used algorithms are sequential, and the required CPU power increases rapidly with the number of tracks.…
In solving partial differential equations (PDEs), machine learning utilizing physical laws has received considerable attention owing to advantages such as mesh-free solutions, unsupervised learning, and feasibility for solving…
Physics-informed neural networks (PINNs) are a new tool for solving boundary value problems by defining loss functions of neural networks based on governing equations, boundary conditions, and initial conditions. Recent investigations have…
Trajectory representation learning (TRL) maps trajectories to vectors that can then be used for various downstream tasks, including trajectory similarity computation, trajectory classification, and travel-time estimation. However, existing…
Physics-informed machine learning (PIML) is an emerging framework that integrates physical knowledge into machine learning models. This physical prior often takes the form of a partial differential equation (PDE) system that the regression…