Related papers: Towards Foundation Models for Experimental Readout…

Numerous phenomenological nuclear models have been proposed to describe specific observables within different regions of the nuclear chart. However, developing a unified model that describes the complex behavior of all nuclei remains an…

Nucleon decays are generic predictions of motivated theories, including those based on the unification of forces and supersymmetry. We demonstrate that non-canonical nucleon decays offer a unique opportunity to broadly probe light new…

We present a systematic evaluation of representation learning objectives for particle physics within a unified framework. Our study employs a shared transformer-based particle-cloud encoder with standardized preprocessing, matched sampling,…

Deep kernel learning is a promising combination of deep neural networks and nonparametric function learning. However, as a data driven approach, the performance of deep kernel learning can still be restricted by scarce or insufficient data,…

Despite advances in deep probabilistic models, learning discrete latent representations remains challenging. This work introduces a novel method to improve inference in discrete Variational Autoencoders by reframing the inference problem…

Accelerator-based neutrino physics is entering an energy-frontier regime in which interactions reach the TeV scale and produce exceptionally dense, overlapping detector signatures. In this regime, event interpretation becomes impractical…

The detection of high-energy tau neutrinos remains a critical challenge in neutrino astronomy, limited by inadequate angular resolution and sensitivity in current detectors like IceCube and KM3NeT. We present a modular water Cherenkov…

Dose reduction in computed tomography (CT) is essential for decreasing radiation risk in clinical applications. Iterative reconstruction is one of the most promising ways to compensate for the increased noise due to reduction of photon…

We present a machine-learning-based particle-identification study for the proximity-focusing Ring Imaging Cherenkov (pfRICH) detector of the ePIC experiment at the Electron-Ion Collider. Operating in the backward region ($-3.5 \lesssim \eta…

New deep learning techniques present promising new analysis methods for Imaging Atmospheric Cherenkov Telescopes (IACTs) such as the upcoming Cherenkov Telescope Array (CTA). In particular, the use of Convolutional Neural Networks (CNNs)…

Physics-informed neural networks (PINNs) have emerged as a promising numerical method based on deep learning for modeling boundary value problems, showcasing promising results in various fields. In this work, we use PINNs to discretize…

We present an approach to pose object recognition as next token prediction. The idea is to apply a language decoder that auto-regressively predicts the text tokens from image embeddings to form labels. To ground this prediction process in…

At high-energy collider experiments, generative models can be used for a wide range of tasks, including fast detector simulations, unfolding, searches of physics beyond the Standard Model, and inference tasks. In particular, it has been…

Recent inroads in Computer Vision (CV) and Machine Learning (ML) have motivated a new approach to the analysis of particle imaging detector data. Unlike previous efforts which tackled isolated CV tasks, this paper introduces an end-to-end,…

The Electron-Ion Collider (EIC) will be the next frontier project of nuclear physics in the United States. It is planned to be built in the Brookhaven National Laboratory (BNL) in close collaboration with Jefferson Lab. One of the key…

High-fidelity electron microscopy simulations required for quantitative crystal structure refinements face a fundamental challenge: while physical interactions are well-described theoretically, real-world experimental effects are…

Time series foundation models (TSFMs) have recently gained significant attention due to their strong zero-shot capabilities and widespread real-world applications. Such models typically require a computationally costly pre-training on…

A brief description of our improvements and refinements that led from the CEM95 version of the Cascade-Exciton Model (CEM) code to CEM97 and to CEM2k is given. The increased accuracy and predictive power of the code CEM2k are shown by…

We present a conditional generative model to learn variation in cell and nuclear morphology and the location of subcellular structures from microscopy images. Our model generalizes to a wide range of subcellular localization and allows for…

In this work, we present a novel direction to build an image tokenizer directly on top of a frozen vision foundation model, which is a largely underexplored area. Specifically, we employ a frozen vision foundation model as the encoder of…