The paper presents the first machine learning models for fast generation of beam‑induced background (BIB) in tracking detectors at a future Muon Collider. Two architectures are explored: a high‑fidelity tabular diffusion model and a faster circular spline flow model. Both produce BIB hits and tracks that closely match full simulation results, achieving over an order of magnitude speed‑up while requiring far less computational resources.
By Radha Mastandrea, Shiyu Peng, Benjamin Rosser, Matt LeBlanc
The paper systematically compares four classical machine learning models—SVM, ANN, CNN, and LSTM—with their quantum equivalents—QSVM, QNN, QCNN, and QLSTM—on simulated proton‑proton collision data from CERN Open Data. Classical models, especially CNN and LSTM, slightly outperform the quantum models under current hardware and dataset constraints, but quantum models achieve comparable accuracy with far fewer trainable parameters; for example, the QCNN matches a deep classical CNN using only four qubits and a depth‑three circuit. The study also shows that the regression task is non‑trivial for shallow polynomial fits, underscoring the relevance of the architectural comparison.
whyItMatters":"The work provides a realistic benchmark of classical versus quantum machine learning performance on high‑energy physics data, highlighting parameter‑efficiency advantages of quantum models for near‑term devices."
By Tariq Mahmood, Zain ul Abidin, Itzel Luviano Soto, Alfredo Raya
arXiv:2604. 07520v2 Announce Type: replace-cross Abstract: These lecture notes provide a comprehensive framework for performing global statistical fits in high-energy physics using modern Machine Learning (ML) surrogates.
By Jorge Alda
arXiv:2606. 14373v1 Announce Type: cross Abstract: The workflow from particle collision to physics analysis passes through a series of reconstruction steps that are traditionally modular and disconnected, with no shared representation linking low-level detector data to high-level analysis tasks.
By Farouk Mokhtar, Joosep Pata, Michael Kagan, Javier Duarte
The paper presents NuCLR, a multi-task neural network that learns nuclear data representations to predict charge radii and electric‑quadrupole transition strengths across hundreds of nuclides. Using held‑out ensembles, the model achieves a charge‑radius RMS deviation of 0.0147 fm and a B(E2) RMS deviation of 0.192 e²b², comparable to leading nuclear models. The authors provide error bars indicating where additional experimental data could improve predictions, positioning NuCLR as a data‑driven surveyor of nuclear structure.
By Giuliano Giacalone, Sokratis Trifinopoulos, Mike Williams
arXiv:2608. 14278v1 Announce Type: cross Abstract: We present Pairton, an iterative framework for reconstructing short-lived particles in high-energy collision events.
By Andreas Hermansen, Chris Scheulen, Tobias Golling
arXiv:2609.08463v1 Announce Type: cross
Abstract: We apply transfer learning (TL) to construct data-driven models of inclusive electron-nucleus cross sections. Starting from an ensemble of deep neura...
By Krzysztof M. Graczyk, Beata E. Kowal, Rwik Dharmapal Banerjee, Jose Luis Bonilla, Hemant Prasad, Jan T. Sobczyk
The paper introduces a conditional diffusion model that learns to map raw semi‑inclusive deep inelastic scattering (SIDIS) event kinematics directly to transverse momentum dependent parton distribution functions (TMD PDFs), eliminating the need for explicit functional forms. On simulated CLAS12 data, the model accurately recovers the underlying TMD and provides informative uncertainties that improve with larger event samples, even when only about 1,000 events are available.
By Jitao Xu, Christopher Cocuzza, Kevin Braga, Daniel Lersch, Nobuo Sato, Yaohang Li
arXiv:2607. 01372v1 Announce Type: cross Abstract: Gravitational Waves (GWs) represent the newest window of astronomy, furthering our understanding of compact objects like black holes and neutron stars in the Universe.
By Bhavya Gupta, Deep Chatterjee, William Benoit, Ethan Marx, Christina Reissel, Seiya Tsukamoto, Kyungseop Yoon, Michael W. Coughlin, Philip Harris, Erik Katsavounidis
Precise knowledge of nuclear structure is essential across fundamental physics, yet probing these structures is notoriously difficult. To address this challenge, ultra-peripheral collisions (UPCs) provide a femtoscopic tomography for imaging the atomic nucleus.
The paper introduces a Deep Sets surrogate for optimal transport (OT) that respects key metric properties—non-negativity, exchange symmetry, and zero self-distance—while leaving the triangle inequality unconstrained. Applied to the Energy Mover's Distance between collider events, the Metric-Aware Particle Flow Network achieves percent‑level mean absolute percentage error and markedly higher inference throughput compared to other exact and approximate methods. The architectural constraints also dramatically reduce triangle‑inequality violations, improving geometric fidelity across a large set of held‑out event triplets.
By Lauren Hay, Rishabh Jain, Matt LeBlanc, Jennifer Roloff
VyPER is a new geometric learning framework that reconstructs particle collider events by representing them as hypergraphs with a physics-inspired topology. It tackles two key tasks: assigning measured jets and leptons to their parent particles through supervised hyperedge classification, and predicting neutrino kinematics using a diffusion model, all optimized jointly with a shared loss function. The authors evaluate VyPER on various proton‑proton collision processes, showing improved performance over existing analytical and machine‑learning methods and enabling more precise measurements in Higgs, electroweak, and top‑quark studies.
By Lining Mao, Yvonne Peters, Ethan Simpson, Zihan Zhang