Searcharxiv⌕ Search

arXiv subjects

Benedikt Maier

Publications and source records attributed to Benedikt Maier.

At least 19 recordsLinked to original sources
arXiv2026

Machine Learning on Heterogeneous, Edge, and Quantum Hardware for Particle Physics (ML-HEQUPP)

The next generation of particle physics experiments will face a new era of challenges in data acquisition, due to unprecedented data rates and volumes along with extreme environments and operational constraints. Harnessing this data for scientific discovery demands real-time inference and decision-making, intelligent data reduction, and efficient processing architectures beyond current capabilities. Crucial to the success of this experimental paradigm are several emerging technologies, such as artificial intelligence and machine learning (AI/ML), silicon microelectronics, and the advent of quantum algorithms and processing. Their intersection includes areas of research such as low-power and low-latency devices for edge computing, heterogeneous accelerator systems, reconfigurable hardware, novel codesign and synthesis strategies, readout for cryogenic or high-radiation environments, and analog computing. This white paper presents a community-driven vision to identify and prioritize research and development opportunities in hardware-based ML systems and corresponding physics applications, contributing towards a successful transition to the new data frontier of fundamental science.

physics.ins-det↗
arXiv2026

Continuous-variable photonic quantum extreme learning machines for fast collider-data selection

We study continuous-variable photonic quantum extreme learning machines as fast, low-overhead front-ends for collider data processing. Data is encoded in photonic modes through quadrature displacements and propagated through a fixed-time Gaussian quantum substrate. The final readout occurs through Gaussian-compatible measurements to produce a high-dimensional random feature map. Only a linear classifier is trained, using a single logistic regression, so retraining is fast, and the optical path and detector response set the analytical and inference latency. We evaluate this architecture on two representative classification tasks, top-jet tagging and Higgs-boson identification, with parameter-matched multi-layer perceptron (MLP) baselines. Using standard public datasets and identical train, validation, and test splits, the photonic Quantum Extreme Learning Machine (QELM) outperforms an MLP with two hidden units for all considered training sizes, and matches or exceeds an MLP with ten hidden units at large sample sizes, while training only the linear readout. These results indicate that Gaussian photonic extreme-learning machines can provide compact and expressive random features at fixed latency. The combination of deterministic timing, rapid retraining, low optical power, and room temperature operation makes photonic QELMs a credible building block for online data selection and even first-stage trigger integration at future collider experiments.

quant-ph↗
arXiv2026

D$e^+e^-$ffusion: Capturing the Beam-Beam Physics of $e^+e^-$ Collisions with Diffusion Models

Beam-induced backgrounds at high-luminosity $e^+e^-$ colliders, such as the FCC-ee, are dominated by incoherent pair creation (IPC), and require computationally expensive simulations with dedicated Monte Carlo (MC) event generators. Reliable detector and machine-detector interface studies necessitate event samples that are several orders of magnitude larger than what is practically attainable with existing MC. To alleviate this bottleneck, we present D$e^+e^-$ffusion, a denoising diffusion probabilistic model that operates as a permutation-equivariant, set-valued surrogate for fast IPC simulation. Trained on a small GuineaPig++ sample, D$e^+e^-$ffusion faithfully reproduces the marginal and joint kinematic, angular, and positional distributions of all three IPC production processes. In addition, we assess the fidelity at the detector level by propagating both Geant4 and D$e^+e^-$ffusion events through a Geant4 simulation of the CLD vertex detector and by training a transformer-based two-sample classifier; the classifier achieves an area under the ROC curve of $0.553 \pm 0.016$. The trained model generates events nearly four orders of magnitude faster than Geant4, paving the way for a fast-simulation surrogate for FCC-ee design studies.

hep-ph↗
arXiv2026

QUIVER: Quantum-Informed Views for Enhanced Representations in Large ML Models

Large machine learning models benefit substantially from multimodal inputs that provide a complementary view of the same example. We introduce QUIVER (QUantum-Informed Views for Enhanced Representations, a paradigm that enriches classical data-driven features with a quantum Fisher view: a geometrically motivated, basis-independent summary of higher-order correlations captured by a variational quantum circuit (VQC) trained to perform the same task. Unlike classical feature augmentation, the quantum Fisher information matrix encodes the intrinsic geometry of the learned quantum state manifold. While this feature map, motivated by quantum information theory, is ordinarily non-trivial to model classically, it can surface statistical structure that additional classical data or model capacity finds difficult to learn. This makes the quantum Fisher view a genuinely complementary modality rather than a redundant one. We demonstrate that QUIVER improves standard performance metrics on two benchmark datasets from very different fields: QM9 for predicting molecule properties, and JetClass for predicting jet flavor at the Large Hadron Collider (LHC). The core contribution, however, is domain-agnostic: the quantum Fisher view can be fused into a broad class of model architectures via targeted modifications to the base architecture, to incorporate information about the quantum geometry of the problem. These results demonstrate that quantum-geometric features, extracted from simulated variational circuits, can deliver measurable value for standard machine learning tasks, well before the advent of fault-tolerant quantum hardware.

cs.LG↗
arXiv2026

Particle-Lund Multimodality in Jet Taggers

The Lund plane offers a physics-motivated, hierarchical representation of QCD radiation within jets, while transformer-based taggers have reached state-of-the-art performance by learning directly from raw particle constituents and their pairwise relations. We investigate whether transformers implicitly capture hierarchical QCD structure from constituent-level inputs, or whether explicit physics representations remain complementary. To test this, we introduce PLuM, a multimodal architecture that projects particle constituents and Lund plane splittings into a shared latent space, processing both jointly with a unified transformer. Cross-attention allows the model to probe whether structured QCD information provides discriminating power beyond what particles alone encode. We observe systematic gains for top-quark and $\mathrm{H}\to\mathrm{b}\bar{\mathrm{b}}$ tagging, while finding no comparable improvement for $\mathrm{H}\to\mathrm{c}\bar{\mathrm{c}}$ or $\mathrm{H}\to 4\mathrm{q}$ topologies. This selective enhancement suggests that explicit hierarchical information about b-jet formation remains complementary to raw particle representations even in highly expressive architectures, while other topologies are already well-captured at constituent level. For high-impact LHC analyses such as Lorentz-boosted di-Higgs searches in the four $\mathrm{b}$ quark final state ($\mathrm{H}\mathrm{H}(4\mathrm{b})$), the gains are substantial: at a $25\%$ di-Higgs efficiency working point, PLuM achieves $25\%$ higher background rejection than the baseline. Our results indicate that physically structured representations of QCD radiation retain discriminating value in the transformer era, motivating further study into how different aspects of jet dynamics are encoded by deep learning algorithms.

hep-ph↗
arXiv2026

From Information Geometry to Jet Substructure: A Triality of Cumulant Tensors, Energy Correlators, and Hypergraphs

Pairwise Fisher graphs capture local covariance information, but they cannot distinguish an irreducible multi-observable radiation pattern from a collection of ordinary pairwise correlations. We show that this missing structure is naturally supplied by higher-order Fisher tensors. In a finite basis of binned EECs, ECFs, or EFPs, and in the natural exponential-family coordinates generated by that basis, the same local tensor has three equivalent interpretations: a coefficient in the local Kullback-Leibler expansion, a connected cumulant of the chosen correlator observables, and a signed weight on a hyperedge linking those observables. This gives an exact Fisher-correlator-hypergraph triality in the local exponential-family embedding. The triality provides a direct construction of physics-informed hypergraphs from correlator data. Extending the quadratic Fisher matrix to the first non-trivial higher tensor identifies genuinely connected multi-observable radiation patterns, supplies hyperedge weights for higher-order Laplacians and message passing, and gives a principled criterion for compressing observable bases beyond pairwise information. We develop these constructions and spell out why the exact cumulant interpretation is special to natural exponential-family coordinates. We illustrate the framework in four applications. In a minimal local-KL study, the cubic Fisher tensor reduces the KL truncation error and isolates the dominant triplet structure. In a two-versus-three prong jet substructure benchmark, the hypergraph selector improves compressed-basis classification. In a 33-observable basis-design problem, the Fisher hypergraph retains more third-order local response at twelve observables. A low-capacity learning benchmark then shows how the same Fisher hyperedges can be used as an interpretable inductive bias for message passing on correlator observables.

hep-ph↗
arXiv2026

Contrastive Metric Learning for Point Cloud Segmentation in Highly Granular Detectors

We propose a novel clustering approach for point-cloud segmentation based on supervised contrastive metric learning (CML). Rather than predicting cluster assignments or object-centric variables, the method learns a latent representation in which points belonging to the same object are embedded nearby while unrelated points are separated. Clusters are then reconstructed using a density-based readout in the learned metric space, decoupling representation learning from cluster formation and enabling flexible inference. The approach is evaluated on simulated data from a highly granular calorimeter, where the task is to separate highly overlapping particle showers represented as sets of calorimeter hits. A direct comparison with object condensation (OC) is performed using identical graph neural network backbones and equal latent dimensionality, isolating the effect of the learning objective. The CML method produces a more stable and separable embedding geometry for both electromagnetic and hadronic particle showers, leading to improved local neighbourhood consistency, a more reliable separation of overlapping showers, and better generalization when extrapolating to unseen multiplicities and energies. This translates directly into higher reconstruction efficiency and purity, particularly in high-multiplicity regimes, as well as improved energy resolution. In mixed-particle environments, CML maintains strong performance, suggesting robust learning of the shower topology, while OC exhibits significant degradation. These results demonstrate that similarity-based representation learning combined with density-based aggregation is a promising alternative to object-centric approaches for point cloud segmentation in highly granular detectors.

hep-ex↗
arXiv2026

Search for additional scalar bosons within the Inert Doublet Model in a final state with two leptons at the FCC-ee

We present a search for new scalar bosons predicted by the Inert Doublet Model at an $e^+e^-$ machine with centre-of-mass energies of 240 and 365 GeV. Within this model, four additional scalar bosons ($H,\, A,\, H^+$ and $H^-$) are predicted. Due to an additional symmetry, the lightest new scalar, here chosen to be $H$, is stable and provides an adequate dark matter candidate. The search for pair production of the new scalars is investigated in final states with two electrons or two muons, in the context of the future circular collider proposal, FCC-ee. Building on previous studies in the context of the CLIC proposal, this analysis extends the search to detector-level objects, using a parametric neural network to enhance the signal contributions over the Standard Model backgrounds, and sets projected exclusion and discovery contours in the $M_A-M_H$ vs. $M_H$ plane. With a total integrated luminosity of 10.8 (2.7) ab$^{-1}$ for $\sqrt{s}=240$ (365) GeV, the discovery reach for the model goes up to $m_H= 108$ (157) GeV for $M_A-M_H=15$ GeV. For exclusion, almost the entire phase-space available in the $M_A-M_H$ vs. $M_H$ plane is expected to be ruled out at 95\% CL, reaching up to $M_H=110$ (165) GeV.

hep-ph↗
arXiv2026

JetFormer: A Scalable and Efficient Transformer for Jet Tagging from Offline Analysis to FPGA Triggers

We present JetFormer, a versatile and scalable encoder-only Transformer architecture for particle jet tagging at the Large Hadron Collider (LHC). Unlike prior approaches that are often tailored to specific deployment regimes, JetFormer is designed to operate effectively across the full spectrum of jet tagging scenarios, from high-accuracy offline analysis to ultra-low-latency online triggering. The model processes variable-length sets of particle features without relying on input of explicit pairwise interactions, yet achieves competitive or superior performance compared to state-of-the-art methods. On the large-scale JetClass dataset, a large-scale JetFormer matches the accuracy of the interaction-rich ParT model (within 0.7%) while using 37.4% fewer FLOPs, demonstrating its computational efficiency and strong generalization. On benchmark HLS4ML 150P datasets, JetFormer consistently outperforms existing models such as MLPs, Deep Sets, and Interaction Networks by 3-4% in accuracy. To bridge the gap to hardware deployment, we further introduce a hardware-aware optimization pipeline based on multi-objective hyperparameter search, yielding compact variants like JetFormer-tiny suitable for FPGA-based trigger systems with sub-microsecond latency requirements. Through structured pruning and quantization, we show that JetFormer can be aggressively compressed with minimal accuracy loss. By unifying high-performance modeling and deployability within a single architectural framework, JetFormer provides a practical pathway for deploying Transformer-based jet taggers in both offline and online environments at the LHC. Code is available at https://github.com/walkieq/JetFormer.

cs.LG↗
arXiv2025

Physics Briefing Book: Input for the 2026 update of the European Strategy for Particle Physics

The European Strategy for Particle Physics (ESPP) reflects the vision and presents concrete plans of the European particle physics community for advancing human knowledge in fundamental physics. The ESPP is updated every five-to-six years through a community-driven process. It commences with the submission of specific proposals and other input from the community at large, outlining projects envisioned for the near-, mid-, and long-term future. All submitted contributions are evaluated by the Physics Preparatory Group (PPG), and a preliminary analysis is presented at a Symposium meant to foster a broad community discussion on the scientific value and feasibility of the various ideas proposed. The outcomes of the analysis and the deliberations at the Symposium are synthesized in the current Briefing Book, which provides an important input in the deliberations of the Strategy recommendations by the European Strategy Group (ESG).

hep-ex↗
arXiv2025

Sub-microsecond Transformers for Jet Tagging on FPGAs

We present the first sub-microsecond transformer implementation on an FPGA achieving competitive performance for state-of-the-art high-energy physics benchmarks. Transformers have shown exceptional performance on multiple tasks in modern machine learning applications, including jet tagging at the CERN Large Hadron Collider (LHC). However, their computational complexity prohibits use in real-time applications, such as the hardware trigger system of the collider experiments up until now. In this work, we demonstrate the first application of transformers for jet tagging on FPGAs, achieving $\mathcal{O}(100)$ nanosecond latency with superior performance compared to alternative baseline models. We leverage high-granularity quantization and distributed arithmetic optimization to fit the entire transformer model on a single FPGA, achieving the required throughput and latency. Furthermore, we add multi-head attention and linear attention support to hls4ml, making our work accessible to the broader fast machine learning community. This work advances the next-generation trigger systems for the High Luminosity LHC, enabling the use of transformers for real-time applications in high-energy physics and beyond.

physics.ins-det↗
arXiv2025

QINNs: Quantum-Informed Neural Networks

Classical deep neural networks can learn rich multi-particle correlations in collider data, but their inductive biases are rarely anchored in physics structure. We propose quantum-informed neural networks (QINNs), a general framework that brings quantum information concepts and quantum observables into purely classical models. While the framework is broad, in this paper, we study one concrete realisation that encodes each particle as a qubit and uses the Quantum Fisher Information Matrix (QFIM) as a compact, basis-independent summary of particle correlations. Using jet tagging as a case study, QFIMs act as lightweight embeddings in graph neural networks, increasing model expressivity and plasticity. The QFIM reveals distinct patterns for QCD and hadronic top jets that align with physical expectations. Thus, QINNs offer a practical, interpretable, and scalable route to quantum-informed analyses, that is, tomography, of particle collisions, particularly by enhancing well-established deep learning approaches.

hep-ph↗
arXiv2025

1 Particle - 1 Qubit: Particle Physics Data Encoding for Quantum Machine Learning

We introduce 1P1Q, a novel quantum data encoding scheme for high-energy physics (HEP), where each particle is assigned to an individual qubit, enabling direct representation of collision events without classical compression. We demonstrate the effectiveness of 1P1Q in quantum machine learning (QML) through two applications: a Quantum Autoencoder (QAE) for unsupervised anomaly detection and a Variational Quantum Circuit (VQC) for supervised classification of top quark jets. Our results show that the QAE successfully distinguishes signal jets from background QCD jets, achieving superior performance compared to a classical autoencoder while utilizing significantly fewer trainable parameters. Similarly, the VQC achieves competitive classification performance, approaching state-of-the-art classical models despite its minimal computational complexity. Furthermore, we validate the QAE on real experimental data from the CMS detector, establishing the robustness of quantum algorithms in practical HEP applications. These results demonstrate that 1P1Q provides an effective and scalable quantum encoding strategy, offering new opportunities for applying quantum computing algorithms in collider data analysis.

hep-ph↗
arXiv2025

t-channel dark matter at the LHC -- a whitepaper

This report, summarising work achieved in the context of the LHC Dark Matter Working Group, investigates the phenomenology of $t$-channel dark matter models, spanning minimal setups with a single dark matter candidate and mediator to more complex constructions closer to UV-complete models. For each considered class of models, we examine collider, cosmological and astrophysical implications. In addition, we explore scenarios with either promptly decaying or long-lived particles, as well as featuring diverse dark matter production mechanisms in the early universe. By providing a unified analysis framework, numerical tools and guidelines, this work aims to support future experimental and theoretical efforts in exploring $t$-channel dark matter models at colliders and in cosmology.

hep-ph↗
arXiv2025

Re-Simulation-based Self-Supervised Learning for Pre-Training Foundation Models

Self-Supervised Learning (SSL) is at the core of training modern large machine learning models, providing a scheme for learning powerful representations that can be used in a variety of downstream tasks. However, SSL strategies must be adapted to the type of training data and downstream tasks required. We propose RS3L ("Re-simulation-based self-supervised representation learning"), a novel simulation-based SSL strategy that employs a method of re-simulation to drive data augmentation for contrastive learning in the physical sciences, particularly, in fields that rely on stochastic simulators. By intervening in the middle of the simulation process and re-running simulation components downstream of the intervention, we generate multiple realizations of an event, thus producing a set of augmentations covering all physics-driven variations available in the simulator. Using experiments from high-energy physics, we explore how this strategy may enable the development of a foundation model; we show how RS3L pre-training enables powerful performance in downstream tasks such as discrimination of a variety of objects and uncertainty mitigation. In addition to our results, we make the RS3L dataset publicly available for further studies on how to improve SSL strategies.

hep-ph↗
arXiv2025

Optimum filter-based analysis for the characterization of a high-resolution magnetic microcalorimeter towards the DELight experiment

Ultra-sensitive cryogenic calorimeters have become a favored technology with widespread application where eV-scale energy resolutions are needed. In this article, we characterize the performance of an X-ray magnetic microcalorimeter (MMC) using a Fe-55 source. Employing an optimum filter-based amplitude estimation and energy reconstruction, we demonstrate that an unprecedented FWHM resolution of $ΔE_\mathrm{FWHM} = \left(1.25\pm0.17\mathrm{\scriptsize{(stat)}}^{+0.05}_{-0.07}\mathrm{\scriptsize{(syst)}}\right)\,\text{eV}$ can be achieved. We also derive the best possible resolution and discuss limiting factors affecting the measurement. The analysis pipeline for the MMC data developed in this paper is furthermore an important step for the realization of the proposed superfluid helium-based experiment DELight, which will search for direct interaction of dark matter with masses below 100 MeV/c$^2$.

hep-ex↗
arXiv2025

A lightweight analysis farm for fundamental physics experiments

Scientific collaborations require a strong computing infrastructure to successfully process and analyze data. While large-scale collaborations have access to resources such as Analysis Facilities, small-scale collaborations often lack the resources to establish and maintain such an infrastructure and instead operate with fragmented analysis environments, resulting in inefficiencies, hindering reproducibility and thus creating additional challenges for the collaboration that are not related to the experiment itself. We present a scalable, lightweight and maintainable Analysis Facility developed for the DARWIN collaboration as an example study case. Grid computing and storage resources are integrated into the facility, allowing for distributed computing and a common entry point for storage. The authentication and authorization infrastructure for all services is token-based, using an Indigo IAM instance. We discuss the architecture of the facility, its provided services, the user experience, and how it can serve as a sustainable blueprint for small-scale collaborations.

hep-ex↗
arXiv2024

Signal partitioning in superfluid ${}^4$He: a Monte Carlo approach

Superfluid ${}^4$He is an ideal candidate for the direct detection of light dark matter via nuclear recoils thanks to its low nuclear mass and the possibility to reach a low detection energy threshold by exploiting the generated quasiparticles. The design of future detectors based on this target, such as the DELight experiment, requires a proper understanding of the formation and partitioning of the signal for different energy depositions from various sources. This work presents an overview of the physical processes involved in the energy deposition of recoiling electrons and ions, and describes a Monte Carlo approach to the partitioning of the signal into different channels. Despite an overall good agreement with existing literature, differences in the region of interest for light dark matter searches below 200 eV are observed.

hep-ex↗