arXiv subjects

Tilman Plehn

Publications and source records attributed to Tilman Plehn.

At least 37 records · Page 2Linked to original sources

arXiv2026

MadNIS at NLO

We combine fast amplitude surrogates with neural importance sampling to accelerate NLO calculations. For virtual corrections, a learned ratio to the Born matrix element with calibrated uncertainties guarantees reliable precision across phase space. For real emission, we stick to the standard FKS subtraction and train sector-conditioned surrogates of the regularized integrands away from divergences. MadNIS then uses multi-channel mappings and FKS sectors as conditions. We validate our approach for electron-positron scattering to three and four jets and find significant speed-ups and variance reduction in the integration.

hep-ph↗

arXiv2026

The Physics Behind ML-based Quark-Gluon Taggers

Jet taggers provide an ideal testbed for applying explainability techniques to powerful ML tools. For theoretically and experimentally challenging quark-gluon tagging, we first identify the leading latent features that correlate strongly with physics observables, both in a linear and a non-linear approach. Next, we show how Shapley values can assess feature importance, although the standard implementation assumes independent inputs and can lead to distorted attributions in the presence of correlations. Finally, we use symbolic regression to derive compact formulas to approximate the tagger output.

hep-ph↗

arXiv2026

Amplitude Uncertainties Everywhere All at Once

Ultra-fast, precise, and controlled amplitude surrogates are essential for future LHC event generation. First, we investigate the noise reduction and biases of network ensembles and outline a new method to learn well-calibrated systematic uncertainties for them. We also establish evidential regression as a sampling-free method for uncertainty quantification. In a second part, we tackle localized disturbances for amplitude regression and demonstrate that learned uncertainties from Bayesian networks, ensembles, and evidential regression all identify numerical noise or gaps in the training data.

hep-ph↗

arXiv2026

Large Language Models -- the Future of Fundamental Physics?

For many fundamental physics applications, transformers, as the state of the art in learning complex correlations, benefit from pretraining on quasi-out-of-domain data. The obvious question is whether we can exploit Large Language Models, requiring proper out-of-domain transfer learning. We show how the Qwen2.5 LLM can be used to analyze and generate SKA data, specifically 3D maps of the cosmological large-scale structure for a large part of the observable Universe. We combine the LLM with connector networks and show, for cosmological parameter regression and lightcone generation, that this Lightcone LLM (L3M) with Qwen2.5 weights outperforms standard initialization and compares favorably with dedicated networks of matching size.

astro-ph.CO↗

arXiv2026

Iterative HOMER with uncertainties

We present iHOMER, an iterative version of the HOMER method to extract Lund fragmentation functions from experimental data. Through iterations, we address the information gap between latent and observable phase spaces and systematically remove bias. To quantify uncertainties on the inferred weights, we use a combination of Bayesian neural networks and uncertainty-aware regression. We find that the combination of iterations and uncertainty quantification produces well-calibrated weights that accurately reproduce the data distribution. A parametric closure test shows that the iteratively learned fragmentation function is compatible with the true fragmentation function.

hep-ph↗

arXiv2026

Economical Jet Taggers -- Equivariant, Slim, and Quantized

Modern machine learning is transforming jet tagging at the LHC, but the leading transformer architectures are large, not particularly fast, and training-intensive. We present a slim version of the L-GATr tagger, reduce the number of parameters of jet-tagging transformers, and quantize them. We compare different quantization methods for standard and Lorentz-equivariant transformers and estimate their gains in resource efficiency. We find an order-of-magnitude reduction in energy cost for an moderate performance decrease, down to 1000-parameter taggers. This might be a step towards trigger-level jet tagging with small and quantized versions of the leading equivariant transformer architectures.

hep-ph↗

arXiv2025

Extrapolating Jet Radiation with Autoregressive Transformers

Generative networks are an exciting tool for fast LHC event fixed number of particles. Autoregressive transformers allow us to generate events containing variable numbers of particles, very much in line with the physics of QCD jet radiation, and offer the possibility to generalize to higher multiplicities. We show how transformers can learn a factorized likelihood for jet radiation and extrapolate in terms of the number of generated jets. For this extrapolation, bootstrapping training data and training with modifications of the likelihood loss can be used.

hep-ph↗

arXiv2025

CaloChallenge 2022: A Community Challenge for Fast Calorimeter Simulation

We present the results of the "Fast Calorimeter Simulation Challenge 2022" - the CaloChallenge. We study state-of-the-art generative models on four calorimeter shower datasets of increasing dimensionality, ranging from a few hundred voxels to a few tens of thousand voxels. The 31 individual submissions span a wide range of current popular generative architectures, including Variational AutoEncoders (VAEs), Generative Adversarial Networks (GANs), Normalizing Flows, Diffusion models, and models based on Conditional Flow Matching. We compare all submissions in terms of quality of generated calorimeter showers, as well as shower generation time and model size. To assess the quality we use a broad range of different metrics including differences in 1-dimensional histograms of observables, KPD/FPD scores, AUCs of binary classifiers, and the log-posterior of a multiclass classifier. The results of the CaloChallenge provide the most complete and comprehensive survey of cutting-edge approaches to calorimeter fast simulation to date. In addition, our work provides a uniquely detailed perspective on the important problem of how to evaluate generative models. As such, the results presented here should be applicable for other domains that use generative AI and require fast and faithful generation of samples in a large phase space.

physics.ins-det↗

arXiv2025

Lorentz-Equivariance without Limitations

Lorentz Local Canonicalization (LLoCa) ensures exact Lorentz-equivariance for arbitrary neural networks with minimal computational overhead. For the LHC, it equivariantly predicts local reference frames for each particle and propagates any-order tensorial information between them. We apply it to graph networks and transformers. We showcase its cutting-edge performance on amplitude regression, end-to-end event generation, and jet tagging. For jet tagging, we introduce a large top tagging dataset to benchmark LLoCa versions of a range of established benchmark architectures and highlight the importance of symmetry breaking.

hep-ph↗

arXiv2025

Generative Unfolding of Jets and Their Substructure

Unfolding, for example of distortions imparted by detectors, provides suitable and publishable representations of LHC data. Many methods for unbinned and high-dimensional unfolding using machine learning have been proposed, but no generative method scales to the several hundred dimensions necessary to fully characterize LHC collisions. This paper proposes a 3-stage generative unfolding framework that is capable of unfolding several hundred dimensions. It is effective to unfold the jet-level kinematics as well as the full substructure of light-flavor jets and of top jets, and is the first generative unfolding study to achieve high precision on high-dimensional jet substructure.

hep-ph↗

arXiv2025

Lorentz Local Canonicalization: How to Make Any Network Lorentz-Equivariant

Lorentz-equivariant neural networks are becoming the leading architectures for high-energy physics. Current implementations rely on specialized layers, limiting architectural choices. We introduce Lorentz Local Canonicalization (LLoCa), a general framework that renders any backbone network exactly Lorentz-equivariant. Using equivariantly predicted local reference frames, we construct LLoCa-transformers and graph networks. We adapt a recent approach for geometric message passing to the non-compact Lorentz group, allowing propagation of space-time tensorial features. Data augmentation emerges from LLoCa as a special choice of reference frame. Our models achieve competitive and state-of-the-art accuracy on relevant particle physics tasks, while being $4\times$ faster and using $10\times$ fewer FLOPs.

stat.ML↗

arXiv2025

Accurate Surrogate Amplitudes with Calibrated Uncertainties

Neural networks for LHC physics have to be accurate, reliable, and controlled. Using neural surrogates for the prediction of loop amplitudes as a use case, we first show how activation functions are systematically tested with Kolmogorov-Arnold Networks. Then, we train neural surrogates to simultaneously predict the target amplitude and an uncertainty for the prediction. We disentangle systematic uncertainties, learned by a well-defined likelihood loss, from statistical uncertainties, which require the introduction of Bayesian neural networks or repulsive ensembles. We test the coverage of the learned uncertainties using pull distributions to quantify the calibration of cutting-edge neural surrogates.

hep-ph↗

arXiv2025

Advancing Tools for Simulation-Based Inference

We study the benefit of modern simulation-based inference to constrain particle interactions at the LHC. We explore ways to incorporate known physics structures into likelihood estimation, specifically morphing-aware estimation and derivative learning. Technically, we introduce a new and more efficient smearing algorithm, illustrate how uncertainties can be approximated through repulsive ensembles, and show how equivariant networks can improve likelihood estimation. After illustrating these aspects for a toy model, we target di-boson production at the LHC and find that our improvements significantly increase numerical control and stability.

hep-ph↗

arXiv2025

A Lorentz-Equivariant Transformer for All of the LHC

We show that the Lorentz-Equivariant Geometric Algebra Transformer (L-GATr) yields state-of-the-art performance for a wide range of machine learning tasks at the Large Hadron Collider. L-GATr represents data in a geometric algebra over space-time and is equivariant under Lorentz transformations. The underlying architecture is a versatile and scalable transformer, which is able to break symmetries if needed. We demonstrate the power of L-GATr for amplitude regression and jet classification, and then benchmark it as the first Lorentz-equivariant generative network. For all three LHC tasks, we find significant improvements over previous architectures.

hep-ph↗

arXiv2025

Towards Precise Simulations and Inference for the Neutron EDM

Precision measurements of neutron properties, like its permanent electric dipole moment, rely on understanding complex experimental setups in detail. We show how the properties of stored and transported ultracold neutron ensembles can be simulated reliably. In a second step, we illustrate how they can be used for simulation-based inference of the parameters associated with underlying physics processes such as neutron capture or beta decay. Our proof of principle for simulation-based inference confronts a longstanding challenge with ultracold neutrons: low measurement statistics coupled with a complex apparatus.

nucl-th↗

arXiv2025

How to Unfold Top Decays

Using unfolded top-quark decay data we can measure the top quark mass, as well as search for unexpected kinematic effects. We present a new generative unfolding method for the two tasks and show how they both benefit from unbinned, high-dimensional unfolding. Unlike weight-based or iterative generative methods we include a targeted unbiasing with respect to the training data. This shows significant advantages over standard, iterative methods, in terms of applicability, flexibility and accuracy.

hep-ph↗

arXiv2025

Simulation-Prior Independent Neural Unfolding Procedure

Machine learning allows unfolding high-dimensional spaces without binning at the LHC. The new SPINUP method extracts the unfolded distribution based on a neural network encoding the forward mapping, making it independent of the prior from the simulated training data. It is made efficient through neural importance sampling, and ensembling can be used to estimate the effect of information loss in the forward process. We showcase SPINUP for unfolding detector effects on jet substructure observables and for unfolding to parton level of associated Higgs and single-top production.

hep-ph↗

arXiv2025

$\mathcal{CP}$-Analyses with Symbolic Regression

Searching for $\mathcal{CP}$ violation in Higgs interactions at the LHC is as challenging as it is important. Although modern machine learning outperforms traditional methods, its results are difficult to control and interpret, which is especially important if an unambiguous probe of a fundamental symmetry is required. We propose solving this problem by learning analytic formulas with symbolic regression. Using the complementary PySR and SymbolNet approaches, we learn $\mathcal{CP}$-sensitive observables at the detector level for WBF Higgs production and top-associated Higgs production. We find that they offer advantages in interpretability and performance.

hep-ph↗