ML4Jets 2026

Session

Parallel Talks

C2

14 Sept 2026, 11:00

C2 (Hörsaalzentrum University of Vienna)

Conveners

Parallel Talks: Uncertainty Quantification

• Ben Assi

Parallel Talks: Phenomenology

• Ben Assi

Parallel Talks: Reinterpretation & Theory

• Theo Heimel (UCLouvain)

Parallel Talks: Generative Models

• Michał Mazurek (National Centre for Nuclear Research (PL))

Parallel Talks: Generative Models

• Jay Ajitbhai Sandesara (University of Wisconsin (US))

Parallel Talks: Generative Models

• Manuel Szewc

Parallel Talks: Fast Simulation

• Sascha Cassandra Diefenbacher (Heidelberg University (DE))

Parallel Talks: Fast Simulation / Explainable AI

• Michał Mazurek (National Centre for Nuclear Research (PL))

Parallel Talks: Explainable AI

• Marie Hein (RWTH Aachen University)

Parallel Talks: Anomaly Detection

• Barry Dillon (b.dillon@ulster.ac.uk)

Parallel Talks: Anomaly Detection

• Marie Hein (RWTH Aachen University)

Parallel Talks: Scaling Laws

• Anna Hallin (University of Hamburg)

Parallel Talks: Equivariant NN

• Manuel Szewc

Parallel Talks

• There are no conveners in this block

3. Model Uncertainty in the Measurement of the Gluon-Jet Fraction

Siarhei Shulha (Joint Institute for Nuclear Research (RU))

14/09/2026, 11:00

The measurement of quark- and gluon-jet properties requires the determination of their fractions in experimental jet samples. This is commonly achieved by fitting data with quark- and gluon-jet templates derived from Monte Carlo simulations. Because the template shapes depend on the underlying model, the extracted jet fractions are intrinsically model-dependent. This talk reviews the main...

16. Local Conformal Predictions for Calibrated Surrogates

Suprio Dubey (Heidelberg University)

14/09/2026, 11:20

Neural network surrogates for LHC scattering amplitudes require trustworthy uncertainty estimates, a challenging task given the non-Gaussian systematics. We target it
using conformal prediction, a distribution-free post-processing to complement trained
surrogates with calibrated uncertainties. We find that standard conformal predictions
struggle to provide locally calibrated uncertainties....

97. Know What You Don't Flow

Lorenz Vogel (Institute for Theoretical Physics, Heidelberg University)

14/09/2026, 11:40

1

Calibrated learned uncertainties are a key requirement also for generative neural networks in LHC physics. For a toy model with an explicit likelihood we show how a heteroscedastic and a Bayesian normalizing flow learn the systematic and statistical uncertainties on the underlying phase space density. Without an explicit likelihood we train the heteroscedastic loss on a classifier-reweighted...

5. Mass-unspecific classifiers for mass-dependent searches

SERGIO RODRIGUEZ BENITEZ (Instituto de Física Teórica IFT-UAM/CSIC)

14/09/2026, 13:30

Searches for new particles often span a wide mass range, where both signal and SM background shapes vary significantly. We introduce a multivariate method that fully exploits the correlation between signal and background features and the explored mass scale. The classifiers—either a neural network or boosted decision tree—produce continuous outputs across the full mass range, achieving...

82. (ZOOM) A Machine-Learning Analysis of the Higgs Boson in the H → ZZ∗ →4ℓ Channel

Mane Papoyan (American University of Armenia (AUA))

14/09/2026, 13:50

The H → ZZ → 4ℓ channel remains one of the cleanest probes of Higgs boson properties at the LHC, owing to its fully reconstructable final state and well-understood background composition. This work addresses the problem of identifying an optimal machine-learning classifier for extracting the H → ZZ → 4ℓ signal from the ATLAS Open Data 2025 release (√s = 13 TeV, 36.6 fb⁻¹), comparing seven...

75. Hunting the Unseen: Parameter-Agnostic Deep Learning for Semi Visible Jet Tagging

Mr Miguel Angel Avendano Bernal (University of Southampton)

14/09/2026, 14:10

In the study of DM detection at colliders, novel candidates have emerged to bridge between experimental data and theoretical models. Dark Showers (DS) are being studied as an extension of the Standard Model (SM), containing both invisible and visible particles that allow us to predict scenarios involving collider observables. Among these, Semi-Visible Jets (SVJs), represent a novel promising...

79. Understanding the Performance Gains of a full-event HH→4b Search

Yipin Wang (Peking University (CN))

14/09/2026, 14:30

A calibratable full-event (jet-free) HH→4b framework based on full-event particle-flow (PF) candidates was presented at ML4Jets 2025 and in Refs. [[1]][1] and [[2]][2], demonstrating a dramatic >5× improvement in search sensitivity over conventional approaches. In this talk, I will present a series of controlled ablation studies that progressively enhance the event representation, providing a...

60. Enhancing the Sensitivity for Triple Higgs Boson Searches with Deep Learning Techniques

Feng-Yang Hsieh (National Taiwan University)

14/09/2026, 14:50

1

Using two benchmark models containing extended scalar sectors beyond the Standard Model, we investigate deep learning techniques to enhance the sensitivity of resonant triple Higgs boson ($HHH$) searches in the fully hadronic $6b$ channel, which suffers from severe combinatorial background and jet-pairing ambiguities. Specifically, we employ the Symmetry Preserving Attention Network (SPA-Net),...

86. Measurement of the Energy Dependence of Strong Isospin Violation in $\Upsilon(4S)$ Decays Using a Neural Network Event Classifier

Lena Nowatzki

14/09/2026, 15:10

Precise measurements of $B$ meson branching fractions are essential both for testing Standard Model predictions and for many measurements that rely on accurate modeling of data composition in flavor-physics analyses. At Belle II, $B$ mesons are produced via the process $e^+e^- \to \Upsilon(4S) \to B\bar{B}$. The total number of such events can be determined with high precision, yet using this...

81. Open library of learned likelihoods from LHC experiments

Humberto Reyes-Gonzalez (RWTH Aachen University), Dr Humberto Reyes-González (RWTH Aachen)

14/09/2026, 16:00

1

Open statistical models released by the LHC experiments are transforming the reinterpretation of collider searches by providing access to the full likelihood information of experimental analyses. However, evaluating these likelihoods remains computationally expensive, particularly for analyses with many signal and control regions, limiting their use in large-scale phenomenological studies. In...

39. Learning to bin: differentiable approach for multi-dimensional discriminants in high-energy physics

Nitish Kumar Kasaraguppe Veerappa Gowda (Rheinisch Westfaelische Tech. Hoch. (DE))

14/09/2026, 16:20

1

Categorizing events using discriminant observables is central to many high-energy physics analyses. Yet, bin boundaries are often chosen manually. A simple, popular choice in multi-classification tasks is to assign events according to the largest per-class score (”argmax”) and to apply equidistant binning to the resulting one-dimensional discriminants. We propose a binning optimization for...

28. Resummed Distribution Functions: Making Perturbation Theory Positive and Normalized

Radha Mastandrea

14/09/2026, 16:40

Fixed-order perturbative calculations for differential cross sections can suffer from non-physical artifacts: they can be non-positive, non-normalizable, and non-finite, none of which occur in experimental measurements. We propose a framework, the Resummed Distribution Function (RDF), that, given a perturbative calculation for an observable to some finite order in $\alpha_S$, will ``resum''...

119. Theory-informed neural networks for particle physics

Barry Dillon (b.dillon@ulster.ac.uk)

14/09/2026, 17:00

2

We present a theory-informed reinforcement-learning framework that recasts the combinatorial assignment of final-state particles in hadron collider events as a Markov decision process. A transformer-based deep Q-network, rewarded at each step by the logarithmic change in the magnitude of the tree-level matrix element, learns to map final-state particles to partons. Because the reward derives...

49. Scaling Particle-Level Foundation Models on Real Heavy-Ion Collision Data

João A. Gonçalves (University of Bonn, B-IT, Lamarr Institute)

14/09/2026, 17:20

Foundation models for collider physics have so far been trained predominantly on simulated events or proton–proton collision data, leaving their behaviour in the high-occupancy heavy-ion regime largely unexplored. We present, to our knowledge, the first particle-level foundation model pretrained directly on experimentally recorded heavy-ion collisions released through the CERN Open Data...

47. (ZOOM) Forecasting Generative Amplification

Sascha Cassandra Diefenbacher (Heidelberg University (DE))

15/09/2026, 11:00

Generative networks are perfect tools to enhance the speed and precision of LHC simulations. It is important to understand their statistical precision, especially when generating events beyond the size of the training dataset. We present two complementary methods to estimate the amplification factor without large holdout datasets. Averaging amplification uses Bayesian networks or ensembling to...

98. Generative Amplification with Surrogate Monte Carlo

Rebecca Revelli (Heidelberg University)

15/09/2026, 11:20

Amplitude surrogates speed up one of the most computationally expensive steps in the LHC simulation chain. We adapt the generative amplification framework to amplitude surrogates evaluated by reweighting and apply it to uncertainty-aware surrogates. We show that amplitude surrogates, like generative event generators, can exhibit generative amplification when trained on a limited set of...

95. Neural Control Variates at LO and NLO

Sophia Vent (Institute for theoretical physics Heidelberg)

15/09/2026, 11:40

We employ neural control variates to minimize the range of event weights and avoid negative weights for phase-space integration and event generation. A signed control variate, built from two normalizing flows, fulfills both tasks. Combined with neural importance sampling, it significantly reduces the computational cost of LO and NLO predictions. For the NLO case, our conditional neural control...

1. Efficient Event Generation for High-Multiplicity LHC Processes: An End-to-End GPU Workflow with Normalizing Flows

Daohan Wang (HEPHY ÖAW)

15/09/2026, 13:30

Producing very large unweighted event samples for high-multiplicity processes is limited by expensive matrix-element evaluations and low unweighting efficiencies. We present the first end-to-end GPU-resident event-generation workflow that integrates normalizing-flow proposals with the parton-level event generator Pepper. Helicity-conditioned coupling flows are trained using online updates...

50. Too good to go: Upcycling Phase-Space Points for Multijet Processes

Konrad Helms (Georg August University of Göttingen)

15/09/2026, 13:50

1

Accurate sampling of multi-particle phase spaces is a major bottleneck in
high-energy-physics simulations at the LHC, especially for processes with
many final-state particles where matrix-element evaluations become
prohibitively expensive. We introduce a stacked training strategy for
phase-space point generators that cuts the training cost dramatically while
delivering improved...

31. MadNIS at NLO

Giovanni De Crescenzo

15/09/2026, 14:10

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...

64. Sampling NNLO QCD phase space with normalizing flows

Timo Janßen (University of Göttingen)

15/09/2026, 14:30

Next-to-next-to-leading-order QCD calculations are essential for precision collider physics, but their computational cost is often dominated by inefficient phase-space integration. In this talk, I will present the application of neural importance sampling to all contributions entering an NNLO QCD calculation of gluonic top-quark pair production within the STRIPPER subtraction framework. The...

121. Re-Ranking the CaloChallenge 2022

Agni Purani (Rutgers University)

15/09/2026, 14:50

We present a new way of measuring the performance of generative models and use it to rerank all CaloChallenge submissions. This method reorders some submissions and provides a new perspective on how the generative models differ from the reference samples.

51. FastSimu: Constraint-Preserving Generative Fast Simulation of Optical-Photon Response at Wavelength-Shifting-Fiber Entry

Mr Jiacheng Wu (Shanghai Jiao Tong University)

15/09/2026, 15:10

Optical-photon tracking is a major computational bottleneck in segmented plastic-scintillator detectors, where a single particle crossing can produce tens of thousands of photons. We present FastSimu, a conditional generative surrogate for the response of a 25-mm scintillator voxel at the first entry of photons into three orthogonal wavelength-shifting fibers. Conditioned on a multidimensional...

59. Toward Complete ML-Based Simulation for CMS with FlashSim

Prabhat Solanki (Universita & INFN Pisa (IT))

15/09/2026, 16:00

FlashSim is an end-to-end machine-learning simulation in CMS that produces analysis-level events (NanoAOD) directly from generator-level input, at a small fraction of the cost of detailed simulation. Each reconstructed object is generated by its own model, continuous normalizing flows trained with flow matching, conditioned on generator-level information and the per-object models are combined...

139. To surrogate or to differentiate? A Delphes3 optimization study

Luigi Favaro (Universite Catholique de Louvain (UCL) (BE))

15/09/2026, 16:20

Fast parametric detector simulations transform generator-level particles into reconstructed physics objects through a chain of modules controlled by smearing functions. A smearing function contains closed-form resolution and efficiency formulae with numeric coefficients which are traditionally tuned by hand against full simulation or data. We study gradient-based optimization of Delphes3, a...

73. Parnassus for Detector Simulation with Legacy e⁺e⁻ Collider Data

Ya-Feng Lo (University of California Los Angeles (US))

15/09/2026, 16:40

Parnassus is a generative detector-simulation model that learns the mapping from generator-level particles to reconstructed particle-flow objects. We apply it to simulated hadronic Z-boson events from legacy e⁺e⁻ collider experiments. Using ALEPH simulation, we validate Parnassus across particle-, jet-, and event-level observables, including particle identification, reconstructed vertices, jet...

24. Simulating the CMS High-Granularity Calorimeter with Generative AI

Sitian Qian (Northwestern University and Fermilab)

16/09/2026, 10:30

In the upcoming High Luminosity LHC era, detector simulation will face computing resource constraints; at the same time CMS will be upgraded with the new High Granularity Calorimeter (HGCal), which is more intensive to simulate. This computing challenge motivates the use of generative machine learning models as surrogates to replace full physics-based simulation of particle showers in the...

27. Fast Calorimeter Simulation in ATLAS with Modern Generative Models

Florian Ernst (Heidelberg University (DE))

16/09/2026, 10:50

Simulating electromagnetic and hadronic showers accurately is among the most computationally demanding parts of the ATLAS detector simulation. To cut CPU consumption for Run 3, the collaboration deployed AtlFast3, a fast simulation tool that pairs traditional histogram-based parameterisations with GAN-based calorimeter models. For the upcoming  Run 4 of the LHC, work began on optimising the...

106. AllShowers: One model for all calorimeter showers

Thorsten Buss (RWTH Aachen)

16/09/2026, 11:10

To address the high computational demand of detector simulations in high-energy physics, various generative surrogate models have been developed. Traditionally, one generative model per incident particle type is trained, requiring separate trainings and model weights. This increases training and human effort, as well as memory footprint during inference, since multiple sets of weights must be...

52. Fast Point Cloud Generation via Latent Diffusion

Martina Mozzanica (University of Hamburg)

16/09/2026, 11:30

1

Fast, reliable surrogates for detector simulation are essential to support the physics program of the high-luminosity LHC (HL-LHC) and future collider experiments. We present a generative model for pion showers in the ECal and HCal of the International Large Detector (ILD), representing each shower as a high-granularity point cloud where every point encodes position, energy, and — for the...

67. step2point: Optimising Point Cloud Representations for Fast Calorimeter Simulation

Peter McKeown (CERN)

16/09/2026, 11:50

The substantial computational burden associated with the use of traditional Monte Carlo simulation for the calorimeter systems of high energy physics experiments has driven the development of numerous deep generative models for fast calorimeter simulation. Recently, several models have been proposed which move away from the common image-like representation of a shower using a regular grid to a...

160. FASTColor – Full-color Amplitude Surrogate Toolkit for QCD

Javier Mariño Villadamigo (Institut für Theoretische Physik - University of Heidelberg)

16/09/2026, 12:10

High-multiplicity events remain a bottleneck for LHC simulations due to their computational cost. We present a ML-surrogate approach to accelerate matrix element reweighting from leading-color (LC) to full-color (FC) accuracy, building on recent advancements in LC event generation. Comparing a variety of modern network architectures for representative QCD processes, we achieve speed-up of...

103. SPADE: Split-and-Delay Embeddings for Autoregressive High-Granularity Calorimeter Simulation

Henning Rose (Uni Hamburg)

16/09/2026, 14:00

We introduce SPADE (SPlit And Delay Embeddings), which embeds each feature of a token independently and staggers the resulting streams along the sequence with progressively increasing delays. The vocabulary then scales additively rather than multiplicatively, while intra-token correlations are recovered by the ordinary causal self-attention mechanism: each feature is predicted at its own...

130. Improving neural generative models with density estimation and Monte-Carlo resampling

Dr Minh Tuan Pham (IJCLab, Université Paris-Saclay, CNRS/IN2P3)

16/09/2026, 14:20

Detector simulation is among the most resource-intensive components of modern collider experiments, currently consuming roughly half of the LHC computing budget and more still in the High-Luminosity phase. Normalizing flows are attractive surrogate models for fast simulation: they sit on the Pareto frontier between inference speed and accuracy compared with competing generators such as VAEs...

19. Information Geometry of Learned Latent Representations

Rebecca Maria Wolfgramm-Kuntz (Astronomisches Rechen-Institut, Zentrum für Astronomie, Universität Heidelberg)

16/09/2026, 14:40

1

Many classification and reconstruction tasks in physics rely on learned latent representations of the data. When networks are trained with a notion of locality, they encode task-specific similarity as closeness in the latent space. Differential geometry, particularly information geometry, is a powerful tool to uncover the learned information in these latent representations and thereby retrace...

18. Information Geometry of Latent Representations for Interpretable Jet Tagging

Benedikt Schosser

16/09/2026, 15:00

1

Latent representations are an important theme in modern machine learning. While information geometry provides a framework to analyze their structure, it also offers new insight into the physics learned by jet-tagging networks. We apply these methods to binary quark-gluon classification and three-fold fat-jet tagging and relate the learned latent representation to characteristic features of QCD...

90. Where Does the Particle Transformer Look Inside a Jet? A Jacobian-Lens Interpretation

Sitian Qian (Northwestern University and Fermilab)

16/09/2026, 15:20

1

Particle Transformers have achieved state-of-the-art performance in jet tagging, but the physical information underlying their decisions remains difficult to characterize. This limits our ability to assess their robustness, diagnose sensitivities to Monte Carlo mismodeling, and design effective pretraining strategies. We introduce a Jacobian-lens framework that resolves the response of a...

112. Do Jet Taggers Learn Physics? Probing and Steering Latent Directions in a Transformer Tagger

Savannah Thais (City University New York)

16/09/2026, 15:40

1

A growing body of work on large language models has focused on steering vectors, which are linear directions within a model’s latent space that correspond to interpretable language concepts the model has learned. However whether such interpretable directions exist in models trained on physics data, that correspond to physics concepts, remains underexplored. We investigate this in the context...

7. Autoencoders for Symbolic Distillation of Black-Boxes

Alan Gu

16/09/2026, 16:30

1

Deep learning (DL) approaches to high-energy jet tagging achieve state-of-the-art performance over classical methods, but lack human interpretability. We propose a framework for constructing post-hoc interpretable symbolic surrogates of state-of-the-art DL jet taggers trained on particle cloud input representations. A Deep Sets variational autoencoder first learns fixed-size tabular...

4. Jet Taggers Rediscover the Energy Correlators: A Causal and Explainable-AI Dissection

Sanmay Ganguly (Indian Institute of Technology Kanpur (IN))

16/09/2026, 16:50

1

We open the black box of machine-learning jet taggers, asking how they compute their decisions and whether they rediscover QCD. Applying the causal mechanistic-interpretability toolkit (ablation, path patching, logit-lens, probing) to a Particle Transformer top-tagger, we isolate a sparse six-head source -> relay -> readout circuit that recovers 97.3% of full-model AUC, encodes the...

80. A Unified Geometric Framework for Understanding Collider Event Manifolds

Hancheng Li (Rutgers University)

16/09/2026, 17:10

1

As particle collider experiments produce increasingly large and complex datasets, a fundamental question arises: how should we quantify the similarity between two events? A variety of physically motivated metrics have been developed—from optimal transport to phase-space distances—yet the geometric structures induced by these metrics remain largely unexplored. We introduce the Multi-Reference...

9. Interpreting Parton Distributions with Shapley Values

Raphael Bonnet Guerrini (Computer Science Dep. University of Milan)

16/09/2026, 17:30

We show that Shapley values can be used to trace how individual parton distributions (PDFs) shape the theory predictions for high-energy observables computed from them.
This provides a tool for assessing the impact of data on PDFs when determining them, and the impact of PDF uncertainties when using the PDFs to compute collider observables.
The Shapley value is computed by treating the...

57. Data driven hadronization with HOMER

Susie Kim (ITP, Heidelberg University)

16/09/2026, 17:50

Due to the non-perturbative nature of hadronization, its simulation relies on a fragmentation function of a fixed parametric form. We present HOMER, a data-driven alternative based on neural networks that extracts the Lund string fragmentation function directly from data. HOMER addresses the information gap between the latent and observable phase spaces through an iterative reweighting...

30. Getting More Power from Anomaly Detectors for Free with Weights

Rikab Gambhir (University of Cincinnati)

17/09/2026, 10:30

1

Weakly-supervised anomaly searches, such as CWOLA and CATHODE, typically train a classifier to separate a signal region from a sideband-estimate background and then cut on the classifier output to create a signal-enriched dataset. We show that there is a more efficient use of the output: the same classifier output can be used instead as a per-event weight, This results in a more powerful...

38. Improving direct background estimation for resonant anomaly detection

Mark Fanselow (RWTH Aachen University)

17/09/2026, 10:50

Resonant anomaly detection is a promising strategy for extending the reach of bump-hunt searches at the LHC. In a weakly supervised setup, a high-quality background template is essential to produce an anomaly score but can serve a second purpose: It allows to directly estimate the background expectation in a simple cut and count setup, removing the problem of background sculpting. For...

13. Kitchen Sink Anomaly Detection

Lukas Lang (RWTH Aachen University)

17/09/2026, 11:10

Recent years have seen rapid progress in resonant anomaly detection for collider searches, but existing studies often rely on a limited set of signal benchmarks and face a trade-off between sensitive but model-dependent high-level observables and fully agnostic but less performant low-level representations. We address both limitations by introducing new simulated signal benchmarks, publicly...

11. Anomaly detection with normalizing flows for model-agnostic new physics searches

Rafal Maselek

17/09/2026, 11:30

Discovering new particles from beyond the Standard Model remains one of the main goals of present-day particle physics. Traditional searches for new physics at the Large Hadron Collider rely on specific theoretical scenarios and simulation-based background estimates, limiting their reach and introducing modeling uncertainties. We present an anomaly detection method that uses normalizing flows...

40. Unsupervised Machine Learning for Jet-Based Anomaly Detection in ATLAS

Antonio D'Avanzo (University Federico II and INFN, Naples (IT)), Elvira Rossi (University Federico II and INFN, Naples (IT)), Francesco Cirotto (University Federico II and INFN, Naples (IT)), Francesco Conventi (Università degli studi di Napoli "Parthenope" and INFN Sezione di Napoli (IT)), Graziella Russo (University of California,Santa Cruz (US))

17/09/2026, 11:50

Searches for physics beyond the Standard Model at the LHC are traditionally optimized for specific signal hypotheses. Anomaly detection provides a complementary approach by identifying events that deviate from the expected Standard Model background without relying on a particular new-physics model. In fully hadronic final states, these techniques exploit the rich information encoded in the...

37. Look Everywhere Effects in Anomaly Detection

Marie Hein (RWTH Aachen University)

17/09/2026, 12:10

1

Machine learning–based anomaly detection can search for new physics in high-dimensional data with minimal theory bias. However, because these methods scan many possibilities at once, they suffer from a look-elsewhere effect that weakens statistical significance. We study this in weakly supervised settings and find a key trade-off: training and testing on the same data gives high sensitivity...

91. Domain Adaptation Against Background Sculpting

Vincent Benne (RWTH Aachen University)

17/09/2026, 14:00

Weakly supervised anomaly detection has been shown to be an effective tool for model agnostic searches for new physics, especially in the context of resonance searches. However, to integrate weak supervision into standard resonance search analysis workflows, which rely on fits in the sidebands for the background estimation, anomaly scores need to be well behaved in the sidebands. In order to...

115. HAXAD: Anomaly Detection in the Higgs Peak

Dennis Noll (Stanford University)

17/09/2026, 14:20

The Higgs boson, with its universal coupling to mass, provides a broadly applicable portal to sectors beyond the Standard Model and is therefore a natural anchor for anomaly detection (AD) at collider experiments. The Higgs And X Anomaly Detection (HAXAD) strategy offers a principled approach to searching for anomalies occurring in association with a Higgs boson. In the kinematic region of the...

117. Recent Results from Anomaly Detection Searches on CMS

Tore Von Schwartz (Hamburg University (DE))

17/09/2026, 14:40

In the absence of direct evidence for new physics in targeted searches, model-independent strategies are becoming increasingly important. In this talk, we present recent results of model-agnostic searches that are facilitated by advanced machine learning techniques, opening a new avenue for unbiased detection of potential new physics signals.

96. Towards a Statistical Interpretation of the Normalized Autoencoder

Jonathan Ostertag-Henning (Institute for Theoretical Physics, Heidelberg University)

17/09/2026, 15:00

Unsupervised anomaly detection with autoencoders is a promising data-driven and model-agnostic approach for new physics searches at the LHC. However, current anomaly scores assigned by neural networks suffer from a lack of statistical interpretability. The normalized autoencoder (NAE) combines a standard bottleneck architecture with a well-defined probabilistic description. We show that the...

25. Multitask, Every Region, All at Once : Fine-Tunable Region-Conditioned Simulation-Based Inference for Collider Analysis

Yong Sheng Koay

17/09/2026, 15:20

1

Collider simulations simultaneously provide three sources of information: whether an event is signal or background, the physics parameters that generated each signal event, and the event kinematics from which signal regions are defined. Conventional pipelines use these sources in separate stages—training classifiers for signal discrimination, performing parameter inference for fixed analysis...

43. Scaling laws for amplitude surrogates

Joaquin Iturriza Ramirez (LPNHE - Sorbonne Université)

17/09/2026, 16:30

Fast and precise evaluations of scattering amplitudes even in the case of precision calculations is essential for event generation tools at the HL-LHC. We explore the scaling behavior of the achievable precision of neural networks in this regression problem for multiple architectures, including a Lorentz symmetry aware multilayer perceptron and a fully Lorentz equivariant transformer using...

76. Neural Scaling Laws for Jet Generation

Anna Kindsvater (University of Hamburg)

17/09/2026, 16:50

Scaling laws have become a central topic in modern machine learning, providing a quantitative understanding of how model performance improves with increasing model size, training data, and compute. They also offer insights into whether learning is approaching the information limits of a given dataset. In this contribution, we present the first study of neural scaling laws for generative jet...

100. Scaling Laws for the Unified Particle Transformer in Heavy-Flavour Tagging

Pavlo Kashko (Vrije Universiteit Brussel (BE))

17/09/2026, 17:10

Transformer-based taggers have become the workhorse of heavy-flavour identification at the LHC, with the Unified Particle Transformer (UParT) folding flavour classification, track-level auxiliary tasks and regression into a single architecture. Their development has nonetheless remained largely empirical: model capacity, training-sample size and input granularity are chosen by convention...

88. Virtues and Vices of Equivariant Transformers

Jonas Spinner (Durham University)

18/09/2026, 10:30

We study for the first time the benefit of Lorentz-equivariant transformers for large-size jet tagging and flavor tagging. To control their computing demands, we optimize their implementations for inference cost metrics. In our scaling studies, we find that Lorentz-equivariant networks outperform standard transformers provided geometric features are relevant. This holds true in an idealized...

20. Economical Jet Taggers -- Equivariant, Slim and Quantized

Antoine Petitjean (Heidelberg University)

18/09/2026, 10:50

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...

61. Group equivariance in infrared and collinear safe graph neural networks for jet classification

Vishal Singh Ngairangbam

18/09/2026, 11:10

Improving interpretability is essential for building robust
and trustworthy machine learning tools in collider physics. To address this challenge, we systematically investigate equivariant and IRC-safe graph neural networks for jet classification. Using simulated jet datasets, we compare IRC-safe architectures with inbuilt E(2) and O(2) equivariance in the rapidity-azimuth plane against...

144. (ZOOM) Enforcing IRC Safety and Lipschitz-Constrained Insensitivity to Non-Perturbative Effects in Transformers

Umar Sohail Qureshi (Vanderbilt University)

18/09/2026, 11:30

IRC safety has long guided the design of robust jet substructure observables, and this principle has increasingly been built into machine-learned taggers as well. For attention-based architectures such as the Particle Transformer (ParT), however, it is non-trivial to enforce IRC safety without discarding the pairwise, energy-dependent features that make these models powerful. In this work, we...

15. One Generator, Any Process: LLM-Conditioning for the LHC

Thanush Sivagnanalingam (University Heidelberg)

18/09/2026, 11:50

Neural network training for LHC event generation should, ideally, benefit from common high-level patterns in different processes. We propose novel conditioning schemes for continuous parameters, process labels, and Feynman diagrams. We employ pre-trained LLMs as multi-modal foundation models to provide descriptive embeddings for an autoregressive transformer. With such high-level...

99. Clustering for large-scale reinterpretation of new physics searches at the LHC

Judita Mamuzic (IFAE - Barcelona)

Beyond the Standard Model (BSM) searches show no statistically significant sign of new physics to date. However, several analyses reported small excesses, higher than 2σ SD beyond the SM expectation. In this work, clustering algorithms are used to extract more insight from existing searches and motivate a next round of BSM analyses. The flexible framework of the phenomenological Minimal...

107. Detecting and Adapting to Distribution Shift in Real-Time Anomaly Triggers

Amishi Agrawal (KJ Somaiya School of Engineering)

Learned anomaly triggers such as CMS AXOL1TL and CICADA are calibrated against a fixed background model, but there is no standard way to check in real time whether that calibration still holds as detector conditions change. I present two components that address this from different angles.

The first is a sequential change-point detector that monitors trigger calibration health online....