ML4Jets 2026

Session

Parallel Talks

C1

14 Sept 2026, 11:00

C1 (Hörsaalzentrum University of Vienna)

Conveners

Parallel Talks

• Lisa Benato (Austrian Academy of Sciences (AT))

Parallel Talks: Jet Tagging

• Lisa Benato (Austrian Academy of Sciences (AT))

Parallel Talks: Jet Tagging

• Vinicius Massami Mikuni (Lawrence Berkeley National Lab. (US))

Parallel Talks: Reconstruction / Calibration

• Felix Weiglhofer (CERN)

Parallel Talks: Reconstruction / Calibration

• Robert Schoefbeck (Austrian Academy of Sciences (AT))

Parallel Talks: Reconstruction / Calibration

• Huilin Qu (CERN)

Parallel Talks: Foundation Models

• Anna Hallin (University of Hamburg)

Parallel Talks: Foundation Models / Agentic Workflows

• Eric Anton Moreno (Massachusetts Inst. of Technology (US))

Parallel Talks: Agentic Workflows

• Eric Anton Moreno (Massachusetts Inst. of Technology (US))

Parallel Talks: Fast AI / Trigger

• Felix Weiglhofer (CERN)

Parallel Talks: Simulation Based Inference

• Theo Heimel (UCLouvain)

Parallel Talks: Simulation Based Inference

• Jay Ajitbhai Sandesara

Parallel Talks: Quantum Machine Learning

• Daohan Wang (HEPHY ÖAW)

Parallel Talks: Large Language Models

• Jaco ter Hoeve (The University of Edinburgh)

53. b-hive: a CMS wide Machine Learning Framework

Ulrich Willemsen (Rheinisch Westfaelische Tech. Hoch. (DE))

14/09/2026, 11:00

b-hive is a general-purpose machine learning framework developed for the CMS experiment. Every stage of the workflow, from dataset construction and training to inference and evaluation, is encapsulated in a self-contained Law task, while physics-specific choices such as architecture, input features, truth definitions, and kinematic selections are injected through YAML configuration files and...

6. Machine Learning Tools for JetMET Data Certification in CMS

Jawaher Altork (Universita e INFN, Firenze (IT))

14/09/2026, 11:20

The CMS experiment at CERN relies on Data Quality Monitoring (DQM) and data certification to ensure that only high-quality data are used for physics analyses. For the JetMET subsystem, this process is traditionally based on the manual inspection of a large number of DQM histograms by detector experts, making it a time-consuming task that can make subtle detector or reconstruction issues...

29. Improving particle identification in the Belle II TOP detector using machine learning

Cecilia Antonioli (INFN & Universita' di Padova)

14/09/2026, 11:40

The Time Of Propagation (TOP) detector at the Belle II experiment is a ring-imaging Cherenkov detector designed to identify charged hadrons in electron-positron collisions at the SuperKEKB accelerator. It consists of 16 quartz radiator modules arranged around the barrel region of the Belle II detector. When a charged particle crosses a module, Cherenkov photons are emitted. A fraction of these...

58. Transforming Flavour Tagging with the ATLAS Detector: ML tools and calibration techniques for small-R jets and boosted objects

Alexander Gavin (University of London (GB))

14/09/2026, 13:30

The identification of jets containing b-hadrons is essential for many physics analyses at the LHC, including precision measurements of Higgs boson and top-quark processes, as well as searches for physics beyond the Standard Model. We present recent improvements in the discrimination of b-jets from jets originating from lighter quarks using the ATLAS detector. These advances are driven by...

138. Deep Learning Methods for Jet Tagging and Process Classification Using Image Processing

Jhoão Gabriel Martins Campos de Almeida Arneiro (Universidade de São Paulo (USP))

14/09/2026, 13:50

This study explores a convolutional neural network (CNN) approach to classify events produced in high-energy collisions by the presence of heavy (charm and bottom), light (up, down, strange) and gluon jets, with the main characteristic being that jets are not reconstructed in our approach. The method constructs image-like representations based on the kinematics of charged decay products using...

62. An ML-based 4-prong Tagger for hadronic decays of highly boosted heavy scalars in ATLAS

Jae Jin Hong (Indiana University (US))

14/09/2026, 14:10

Discriminating highly boosted jets from the decays of heavy scalar particles that do not involve b-quarks from background is a very challenging problem. We describe a novel "4-Prong Tagger" that uses a graph neural network based on the Lund Jet Planes of a large radius jet to distinguish high energy scalar particle decays, S->WW->4q, from backgrounds such as QCD, hadronic vector-boson decays,...

44. Simplex Demixing: Disentangling Multiple Light-Flavor Jets at Colliders

Gregorio de la Fuente Simarro (Massachusetts Institute of Technology)

14/09/2026, 14:30

Providing a practical and hadron-level definition of multiple jet flavors has been a long-standing challenge in collider physics. Previous work has introduced a data-driven, operational definition of quark and gluon jets, but no robust generalization beyond two jet categories presently exists. To address this, we introduce a machine-learning framework called "simplex demixing'' to extract $T$...

2. "Hadron-in-fat-jet'' AI Tagging to Detect Rare Decays

Mr Zixun Kou (Peking University), Zixun Kou (Peking University (CN))

14/09/2026, 14:50

We investigate a novel class of boosted-object signatures at the LHC, where a high-pT fat-jet contains an identifiable hadron or quarkonium state originating from rare or semi-exclusive decays. Unlike conventional boosted jet studies, which focus on multi-prong partonic substructure, our approach probes hybrid configurations such as W±→π±γ, where a localized hadronic or quarkonium signal is...

129. Instance-Level b-Hadron Tagging with DELPHI Open Data

Sitian Qian (NU FNAL)

14/09/2026, 16:00

The release of LEP open data provides a clean test bed for developing machine-learning methods relevant to future lepton colliders. We present an effort to identify individual b hadrons in DELPHI $Z\to b\bar{b}$ events using an approach inspired by panoptic segmentation. Rather than assigning a single flavour label to a jet, the model classifies reconstructed particles and associates them with...

111. Domain Adaptation in Colliders: Reconcile Simulation and Data

Shang-Fu Wei (The University of Tokyo)

14/09/2026, 16:20

1

Multivariate classifiers in collider physics increasingly use low-level detector information to maximize sensitivity, but this often amplifies systematic uncertainties arising from mismodelling in simulation. To address this, we apply unsupervised domain adaptation (UDA), allowing the classifier to learn with both simulated and unlabeled real data during training, thereby reducing sensitivity...

72. Classifying hadronic objects in ATLAS with machine learning

Robert Les (Michigan State University (US))

14/09/2026, 16:40

Hadronic object reconstruction & classification is one of the most promising settings for cutting-edge machine learning and artificial intelligence algorithms at the LHC. In this contribution, recent highlights of ML applications by ATLAS for boosted-object identification will be presented. This covers results of constituent-based transformers for quark-gluon, top-quark, and W boson...

120. (ZOOM) PanopTag: Simultaneously Tagging All Jets in a Particle Collision Event

Umar Sohail Qureshi (Vanderbilt University)

14/09/2026, 17:00

Jet tagging, identifying the origin of jets produced in particle collisions, is a critical classification task in high-energy physics. Despite the revolutionary impact of deep learning on jet tagging over the past decade, the paradigm has remained unchanged. In particular, jets within the same collision event are classified independently, one at a time. This single-jet approach ignores...

87. Physics Aware Modifications to Particle Transformers (Mod-ParT) for Jet Tagging

Mr Osman Bayraktar (Istanbul University (TR))

14/09/2026, 17:20

1

Particle Transformer ( ParT) has achieved state of the art performance in jet tagging by modeling particle level information through attention. In this work, we introduce Mod-ParT, a physics aware extension of ParT that incorporates relational information into particle representations, enriches pairwise attention biases with additional physics motivated features and replaces the class token...

10. Multiclass classification without labels (multiCWoLa)

Johann Michael Ioannou-Nikolaides (University of Copenhagen (DK))

14/09/2026, 17:40

2

In many classification problems, reliable instance-level labels are unavailable. However, it is often possible to construct weakly enriched unlabeled samples: datasets selected by different cuts, sources, populations, or experimental conditions that change latent class proportions without revealing them. Classification without Labels (CWoLa) shows that, in the binary case ($K=2$), a classifier...

78. Amber: Self-Attention Muon Track Reconstruction in JUNO

Xiaoying Lu

15/09/2026, 11:00

Large-volume liquid scintillator detectors produce variable-size sets of PMT(photomultiplier tube) hits with rich timing, charge, and spatial correlations, making track reconstruction a natural application for attention-based architectures. This talk presents Amber (Attention Mechanism Based Event Reconstructor), a self-attention-based framework for cosmic-muon track reconstruction in the...

21. Learning pairwise associations for event slicing in ProtoDUNE-SP

Christina Karagianni (University and INFN Ferrara (IT))

15/09/2026, 11:20

Event reconstruction in liquid argon time projection chambers (LArTPCs) requires separating detector activity from overlapping beam particles and cosmic rays into physically meaningful particle hierarchies. In the Pandora event reconstruction chain, event slicing groups particle-flow particles (PFPs) into candidate hierarchies using topological association criteria. We investigate whether this...

114. Optimizing Optimal Transport-based Pileup Mitigation

Nathan Suri Jr. (Yale University (US))

15/09/2026, 11:40

The current run of the Large Hadron Collider (LHC) yields on average 30-50 simultaneous pileup vertices per event, consisting of both charged and neutral showers. This number is expected to only increase at the High Luminosity LHC with predicted averages on the order of 140 pileup vertices. Pileup presents a salient problem that, if not checked, hinders the search for new physics and Standard...

35. Learning to Reconstruct Muon Detector Showers from Raw Detector Readout

Asu Guvenli (University of Hamburg (DE))

15/09/2026, 13:30

Long-lived particles decaying within the CMS muon system can deposit dense showers of hits in the endcap Cathode Strip Chambers (CSCs), called muon detector showers (MDS), whose hit multiplicity is the primary handle for their identification. Standard CSC reconstruction, built for isolated muon tracks, breaks down here: overlapping detector signals inflate and smear the hit count where the...

45. Probabilistic, Structure-Intrinsic Clustering with an Hierarchical Embedding (PSICHE) in Time and Space Applied In Particle Physics Jet Reconstruction

Margaret Rose Lazarovits (The University of Kansas (US))

15/09/2026, 13:50

Jet reconstruction is an active and open area of particle physics research, with challenges and questions related to jet size, multiplicity, substructure, and experimental performance in the presence of pileup and noise. A new algorithm, Probabilistic, Structure-Intrinsic Clustering with an Hierarchical Embedding (PSICHE, arxiv:2608.xxxx), introduces a variety novel features to the domains of...

42. Transformer-based machine learning using low-level calorimeter signals for collimated photon identification

Gabriel Matos (Columbia University (US))

15/09/2026, 14:10

Electromagnetic calorimeters provide essential information for reconstructing and selecting both Standard Model (SM) and potential beyond the SM physics events at high-energy particle colliders. The fine-grained segmentation of modern calorimeters captures rich information about the internal structure of particle showers, much of which is discarded by conventional high-level reconstruction...

34. Transformer-based reconstruction of electromagnetic showers in CMS

Yuliia Maidannyk (IRFU-CEA, Université Paris-Saclay (FR))

15/09/2026, 14:30

The reconstruction of electrons and photons in the CMS Electromagnetic Calorimeter (ECAL) currently relies on a geometrical clustering algorithm called PFClustering. While it is efficient for isolated particles, it has a limited ability to resolve close-by showers and mitigate detector noise, which reduces the sensitivity of physics analyses and will worsen with detector ageing. We present...

66. Reconstruction of Tracker Material with Information Field Theory

Alexander Pesch Berrocal (Rheinisch Westfaelische Tech. Hoch. (DE))

15/09/2026, 14:50

1

Accurate knowledge of tracker material is essential for particle reconstruction and detector simulation in high energy physics. Photon conversions and secondary nuclear interactions provide localized probes of detector structures, but inferring a material map from their sparse and noisy vertex distributions is an ill-posed inverse problem. We present a Bayesian field-inference approach in...

54. Curvature-Adaptive Graph Neural Networks for Low-pT Charged-Particle Track Reconstruction at the HL-LHC

Mr Syed Haider Ali (Institute of Physics, Faculty of Science and Technology, University of Debrecen, Egyetem tér 1, H-4032 Debrecen, Hungary)

15/09/2026, 15:10

Charged-particle track reconstruction is a central challenge for the High-Luminosity Large Hadron Collider (HL-LHC), where high detector occupancy and the strongly curved trajectories of low-$p_T$ particles create severe combinatorial ambiguities. Although Graph Neural Networks (GNNs) have emerged as a promising approach for graph-based tracking, their performance is often limited by the...

26. Graph Neural Networks for Calorimeter-Based Cluster Calibration at the ATLAS Experiment

Matthew Green (Adelaide University (AU))

15/09/2026, 16:00

The ATLAS calorimeter system measures the energy of particles. These are large volumes segmented into many individual cells, each recording a small deposit of energy as a particle passes through. The cell-by-cell structure has a natural geometric and topological form well suited to graph neural networks (GNNs), a class of machine learning models designed to learn from data with irregular,...

32. Calibration of signatures from simulated electromagnetic showers in the CMS calorimeter with machine learning

Caio Cesar Daumann (Rheinisch Westfaelische Tech. Hoch. (DE))

15/09/2026, 16:20

Monte Carlo simulations are used extensively in high-energy particle physics analyses. However, imperfections in the configuration of detector simulation can lead to significant discrepancies between simulated events and collision data. Such mismodelling is often addressed using scale factors, which can be accompanied by large systematic uncertainties that compromise the sensitivity of...

71. Latest machine learning techniques for reconstructing and calibrating hadronic objects in ATLAS

Matthew Green (Adelaide University (AU))

15/09/2026, 16:40

The precision and reach of physics analyses at the LHC is often tied to the performance of hadronic object reconstruction & calibration, with any incremental gains in understanding & reduced uncertainties being impactful on ATLAS results. Recent improvements from machine learning methods include the calibration & pileup tagging or calorimeter clusters, regressions of b-jet and boosted jet...

159. 4D Particle Tracking in the NA62 GigaTracker with Transformer-Based Architectures

Gemma Tinti (INFN e Laboratori Nazionali di Frascati (IT))

15/09/2026, 17:00

Accurate particle tracking using the GigaTracker (GTK) silicon pixel detector represents
a mission-critical stage in the data processing pipeline of the NA62 experiment at CERN,
which is dedicated to the precision measurement of the ultra-rare decay K+ → π+ν ¯ν.
Operating in a high-intensity environment with a beam rate of up to 750 MHz, the GTK
provides the momentum and direction...

131. LI-JEPA: Self-supervised pretraining of Lorentz Invariant Models

Andreas Hermansen (Universite de Geneve (CH))

16/09/2026, 10:30

Deep learning classifiers for high-energy physics have recently advanced along two largely separate tracks: self-supervised pretraining on large unlabelled datasets, and architectures that respect Lorentz symmetry by construction. How these directions combine has not been shown.

To address this, we integrate Lorentz-invariant models into the LeJEPA pretraining framework, in which the...

55. To Mask, Predict, or Classify? Comparative Analysis of Pre-Training Strategies for Jet Foundation Models

Anuranjan Sarkar (DESY)

16/09/2026, 10:50

In recent years, several pre-training strategies have been proposed for foundation models in jet physics. These approaches range from self-supervised generative tasks like next-token prediction (NTP) and masked particle modeling (MPM), to standard supervised classification. Inputs to foundation models are often tokenized, but this leads to a loss of information. Recent work has shown that...

17. Performance of Tabular Foundation Models for analysis of 4-vectors LHC final states with the FAIR Universe HiggsML Dataset

David Rousseau (IJCLab-Orsay)

16/09/2026, 11:10

In collider-based particle physics experiments, proton collision events are commonly represented as tabular datasets for specific final states, features being four-vectors of final state particles or higher-level variables (invariant masses).
Inspired by the success of foundation models in language and vision, recent developments have introduced tabular foundation models such as TabPFN and...

74. What can representation geometry reveal about collider foundation models? Towards Scientific AI as a New Microscope

Tianji Cai

16/09/2026, 11:30

1

Foundation models have demonstrated remarkable performance in collider physics, yet little is understood about the geometric principles underlying their neural representations. We propose representation geometry as a new direction for Scientific AI, where machine learning models serve not only as powerful predictors but also as “microscopes” for revealing the intrinsic structure of the...

137. Top quark spin and CP studies with L-GATr

Marco Menen (TU Dortmund)

16/09/2026, 11:50

The top quark is well suited for precision tests of the Standard Model and also provides a unique window into physics beyond the SM, especially via probing of its spin state. Its spin information is encoded in its decay products and is needed for the construction of genuine CP-odd observables, making an accurate polarization reconstruction essential. In this work, we employ L-GATr to study the...

83. Preference-Optimized Generative Models for Underconstrained Inference in Particle Physics

Mr Ting-Hsiang Hsu

16/09/2026, 14:00

Precise reconstruction of event kinematics in the presence of invisible particles constitutes a fundamental underconstrained inference problem in particle physics. In processes such as dileptonic $t\bar{t}$ production, multiple undetected neutrinos lead to a multimodal solution space, where several kinematically consistent configurations can explain a single observed event.

We present a...

84. Measurement of Spin and Quantum Correlations in $Z \to \tau^+\tau^-$ Decays at LEP with DELPHI

Mr Chen-Hua Hsu

16/09/2026, 14:20

Precision studies of $\tau^+\tau^-$ production at the Z pole provide a clean environment for investigating electroweak spin correlations and quantum information observables. Using archived LEP-1 data collected by the DELPHI experiment, the process $e^+e^- \to Z \to \tau^+\tau^-$ is well measured, but the presence of multiple neutrinos in $\tau$ decays limits reconstruction of the $\tau$-pair...

36. Searching For Anomalies with Foundation Models

Vinicius Massami Mikuni (Lawrence Berkeley National Lab. (US))

16/09/2026, 14:40

1

Foundation models have the potential to expand the discovery reach for new physics searches. In this paper, a full physics analysis using CMS Open Data is carried out to search for new physics in dijet events using the OmniLearned foundation model. We find that the background estimation describes the data well in validation regions, but is unable to accurately model the signal region where a...

94. Foundation Models for Jet Anomaly Detection: Optimization and Generalization

Dr Humberto Reyes-González (RWTH Aachen), Soumya Shaw (CISPA, Saarland University)

16/09/2026, 15:00

Foundation models have recently emerged as a promising approach for learning transferable representations from low-level particle physics data. In this work, we investigate the application of the OmniJet-α foundation model, to jet anomaly detection, focusing on how pretraining strategies and downstream optimization affect performance on the LHC Olympics (LHCO) benchmark. We systematically...

85. Agentic AI for Automated Foundation Model Analysis in HEP

Yue Xu (University of Washington (US))

16/09/2026, 15:20

Agentic AI frameworks offer a promising path toward automated HEP analyses, but current approaches rely on iterative prompting and accumulated context, leading to limitations in reproducibility and generality. We try to address these limitations by designing a structured agentic framework that drives a physics foundation model (FM) as its engine, replacing ad-hoc prompt engineering with...

123. ColliderBench: Benchmarking AI Agents with Particle Physics Analysis Reproduction

Sofia Palacios Schweitzer (Rutgers University)

16/09/2026, 15:40

Autonomous language-model agents are increasingly evaluated on long-horizon tool-use tasks, but existing benchmarks rarely capture the complexity and nuance of real scientific work. To address this gap, we introduce ColliderBench, a benchmark for evaluating whether LLM agents can reproduce parts of experimental analyses from the Large Hadron Collider (LHC) using only public papers and open...

22. MadAgents

Daniel Schiller (Institute for Theoretical Physics, Heidelberg University)

16/09/2026, 16:30

1

We present MadAgents, an effective and communicative set of agents for working with MadGraph. Agentic installation, learning-by-doing training, user support, and autonomous simulation campaigns provide easy access to state-of-the-art simulations and accelerate LHC research. We show how MadAgents interact with inexperienced and advanced users, support a range of simulation tasks, and analyze...

113. Ariadne: Agentic Automation of Collider-Physics Workflows

Aman Upadhyay (Rutgers University)

16/09/2026, 16:50

1

LLM agents increasingly assist with coding, but still struggle with long, tool-heavy, multi-step tasks common in high-energy physics. We present Ariadne, an autonomous multi-role LLM agent that, given a natural-language task, is designed to plan, divide, and execute this workflow step by step.
Ariadne's orchestration is based on a LangGraph state that organizes the workflow context into...

127. Agentic AI applications to particle theory and collider phenomenology

Konstantin Matchev (University of Alabama (US))

16/09/2026, 17:10

I will review the first generation of agentic AI tools for high-energy theory and simulations, including HEPTAPOD for orchestrating collider phenomenology workflows and Diagrammatica for autonomous symbolic Feynman-diagram calculations. I will also describe the ongoing community efforts for creating an ecosystem-level infrastructure for deployability, reproducibility, community uptake, and...

70. ORBIT: Online Real-time Bandwidth reduction via Information Tokens

Philipp Wagner (ETH Zürich), Younes Malek Elberkennou (ETH Zürich)

17/09/2026, 10:30

The CMS 40 MHz Scouting program at the High-Luminosity LHC requires aggressive real-time compression of particle-flow event information to operate within stringent bandwidth constraints. We investigate the use of quantized autoencoders for converting Level-1 event representations into compact sequences of discrete tokens. We explore vector quantization, finite scalar quantization, and...

33. Machine learning for jets for the CMS Phase-2 Update of the L1 Trigger

Stella Felice Schaefer (Hamburg University (DE))

17/09/2026, 10:50

At the Phase-2 Upgrade of the CMS Level-1 Trigger (L1T), particles will be reconstructed by linking charged particle tracks with clusters in the calorimeters and muon tracks from the muon stations. The 200 pileup interactions will be mitigated using primary vertex reconstruction for charged particles and a weighting for neutral particles based on the distribution of energy in a small area....

116. Do BitNet Gains Survive FPGA Synthesis? An Implementation-Aware Benchmark of Low-Precision Jet Classification

Dorian Sloot (Austrian Academy of Sciences (AT))

17/09/2026, 11:10

Real-time jet classification in high-energy physics requires high predictive performance under strict latency, throughput, and FPGA-resource constraints. Although aggressive weight quantisation promises simpler arithmetic, reductions in numerical precision and theoretical operation count do not necessarily translate into more efficient synthesised implementations. This study investigates...

77. High-performance and portable ML Inference using SOFIE

Sanjiban Sengupta (The University of Manchester (GB))

17/09/2026, 11:30

SOFIE (System for Optimized Fast Inference code Emit), being developed by the ML4EP Project at CERN, translates trained machine learning models into self-contained, low-latency C++ code that is portable, hardware-agnostic, and highly optimized while depending only on BLAS libraries.

SOFIE achieves portability across heterogeneous computing architectures by leveraging the abstract buffer...

101. FlashJet: exact jet clustering and jet substructure reconstruction at the GPU era

Chirayu Gupta (Vrije Universiteit Brussel (BE))

17/09/2026, 11:50

Jet clustering remains one of the few steps in modern analysis and reconstruction chains that is still bound to the CPU. Machine learning workflows that wish to recluster jets inside the training loop, scan the jet radius, or access substructure dynamically must pay for repeated transfers between host and device, and reconstruction itself is steadily moving toward heterogeneous environments in...

14. Application of Machine Learning to Collision Parameter Tuning in the SuperKEKB Accelerator

Riku Takizawa (UTokyo)

17/09/2026, 12:10

SuperKEKB is an electron–positron collider operating at a center-of-mass energy of 10.58 GeV and has achieved the world’s highest instantaneous luminosity. At present, collision parameters are optimized manually through a procedure known as an interaction-point (IP) knob tuning. This study aims to improve the efficiency and reproducibility of IP knob tuning, and ultimately automate the process...

12. Proton Structure from Neural Simulation-Based Inference at the LHC

Jaco ter Hoeve (The University of Edinburgh)

17/09/2026, 14:00

1

The precise determination of the parton distribution functions (PDFs) of the proton is an essential ingredient for LHC analyses, including for those at the upcoming High-Luminosity LHC. So far, PDFs are determined from global fits to binned low-dimensional data obtained from unfolded hard-scattering cross section measurements. In this talk, we demonstrate the feasibility of neural...

133. Reliable Likelihood Ratios for Neural Simulation Based Inference in HEP

Nino Kovacic (University of Zagreb (HR))

17/09/2026, 14:20

1

Neural Simulation Based Inference (NSBI) is a collection of statistical machine learning methods that learn the likelihood or posterior based on high-dimensional input data. One flavor of NSBI, Neural Likelihood Ratio Estimation (NLRE), has emerged as a powerful method in the domain of High Energy Physics (HEP), having recently been used in Higgs-boson measurement [1] at the Large Hadron...

134. Iterative Simulation-Based Inference for the LHC

Ranit Das (Heidelberg University)

17/09/2026, 14:40

1

Simulation-based inference (SBI) is a powerful tool for likelihood-free parameter estimation, but often requires large numbers of simulated events. At the LHC, where event generation can be computationally expensive, particularly with restrictive generator-level cuts and detector simulation, this can become a major bottleneck. We demonstrate sequential SBI for the inference of resonance masses...

23. Trusting Generative Unfolding

Sebastian Pitz (LPNHE Paris)

17/09/2026, 15:00

Machine learning enables unbinned unfolding with per-event posteriors, but a measurement is only as good as its error bars. We dissect the uncertainty budget of conditional flow matching unfolding for WZ production. Bootstraps propagate the statistics of the training sample and, by reweighting, of the data. We show how weight sampling from a Bayesian neural network relates to the spread of...

126. Unfolding without Iterations, Adversaries, or Surrogates

Ayodele Ore

17/09/2026, 15:20

Correcting measurements for detector effects is a pressing inverse problem in LHC physics. Current methods solve this problem by relying on iterative refinement, minimax optimization, or a surrogate forward mapping. In this talk, I present Adversary-free Unfolding SanS Iteration or Emulation (AUSSIE), which dispenses with these mechanisms while remaining asymptotically correct. AUSSIE unfolds...

124. A fully-differential charged particle phase space measurement of $Z$+jets production in $pp$ collisions at $\sqrt{s} = 13$ TeV with the ATLAS detector

Kevin Thomas Greif (University of California Irvine (US))

17/09/2026, 16:30

The production of a $Z$ boson decaying to muons in association with hadronic jets is a benchmark process in proton--proton collisions at the Large Hadron Collider. It provides a clean experimental signature with high selection efficiency and purity while probing a wide range of Standard Model dynamics. Measurements of this process are typically reported as binned differential cross sections in...

122. Learning the latent structure of background distributions

Santiago Tanco

17/09/2026, 16:50

1

Topic modeling techniques allow to learn robust representations of a data in terms of latent themes or topics. In this talk, I will present an application of Latent Dirichlet Allocation that exploits information from multiple Monte Carlo simulation setups of known processes to learn the shapes of observable distributions directly from data. This approach provides a general framework to infer...

68. Exploring data-driven likelihood estimation with normalizing flows for CRESST

Danae Danielle Valdenaire (Austrian Academy of Sciences (AT))

17/09/2026, 17:10

CRESST (Cryogenic Rare Event Search with Superconducting Thermometers) is a direct dark matter detection experiment located at the Laboratori Nazionali del Gran Sasso (LNGS) in Italy. It searches for dark matter–nucleus interactions using scintillating cryogenic calorimeters, pushing its energy threshold ever lower to improve sensitivity to low‑mass dark matter. At these thresholds, however,...

92. Neural-network quantum states for exotic hadrons and nuclei

weilin wu (Peking University)

18/09/2026, 10:30

Neural-network quantum states provide a flexible representation of high-dimensional many-body wave functions, offering a promising approach to quantum systems that remain challenging for conventional numerical methods. In this talk, I will present their applications to exotic hadrons and nuclei. By combining expressive neural-network wave functions with variational Monte Carlo and...

109. (ZOOM) Variational Quantum Classification Heads for Particle Transformer-Based in Jet Tagging

Nadia Sharna (Bursa Technical University)

18/09/2026, 10:50

1

In collider physics, jet tagging is a key classification task in which models must identify the initiating particle from a reconstructed jet's internal structure. Though their final predictions are often produced by classical neural-network heads, Particle Transformer architectures achieve strong performance by learning interactions among jet constituents. In this paper, the usefulness of a...

125. Normalising Flow-Assisted Neural Quantum States for Ground-State Estimation

Timur Sypchenko (IPPP)

18/09/2026, 11:10

Neural quantum states provide expressive variational representations of quantum many-body wavefunctions.
However, their practical performance depends on how well they can sample the relevant configurations from
an exponentially large Hilbert space. Conventional Markov chain Monte Carlo methods can mix slowly between separated high-probability regions, particularly in frustrated and strongly...

110. Continuous-Variable Photonic Quantum Machine Learning for High-Energy Physics: The 1-Particle 1-Qumode Framework

Louis Choron (Imperial College (GB))

18/09/2026, 11:30

As next-generation colliders reach unprecedented energies and luminosities, novel computing techniques become essential to meet the resulting computational challenges. One area of promise is quantum machine learning (QML), which combines the quantum effects of superposition and entanglement with classical optimisation techniques. Within QML, photonic devices are of particular interest due to...

104. Information-theoretic and quantum-informed approaches for jets at the LHC

Aritra Bal (KIT - Karlsruhe Institute of Technology (DE))

18/09/2026, 11:50

1

Jet substructure studies at the LHC often rely on observables that do not fully capture all possible correlations between constituents, especially at higher irreducible orders. We present two approaches for modelling this structure, based on information theory and quantum information geometry. Both methods use the Fisher Information Matrix, the first being constructed classically using the...

128. Lund Plane to Bloch (LP2B) encoding for object and polarization tagging with quantum jet substructure

Luca Della Penna (Universita e INFN, Perugia (IT))

18/09/2026, 12:10

The application of quantum algorithms to jet substructure analysis is of growing interest as Noisy Intermediate-Scale Quantum (NISQ) hardware continues to mature in qubit count and gate depth. Jet substructure remains essential for addressing challenges at the LHC and beyond, notably object classification and polarization tagging. However, existing quantum machine learning approaches typically...

63. Fine-tuning Small Language Models for Particle-Physics Lagrangian Generation

Paul Schmidt

18/09/2026, 14:00

2

Recent advances in language models have sparked growing interest in their use for specialized scientific applications. In this work, we apply supervised fine-tuning to adapt a small pretrained language model to a task in theoretical particle physics. We consider the generation of particle-physics Lagrangians from structured field descriptions. Given a set of fields, the model must generate the...

102. (ZOOM) Classification-Generative Supervised Fine-Tuning for Hierarchical Tagging of ML4HEP Literature

Ziyue Chen (IHEP)

18/09/2026, 14:20

We propose CG-SFT, a parameter-efficient framework that turns a causal large language model into a structured hierarchical multi-label classifier without adding a classification head. The label space is encoded as a fixed sequence where each label is followed by a <yes>/<no> decision token. Supervision is applied only to these decision positions using cross-entropy, binary cross-entropy, and...

89. Steering in Theory Space: Representation Engineering of a Lagrangian Transformer

Yong Sheng Koay

18/09/2026, 14:40

1

Foundation models embed not only their training examples but the space those examples were drawn from. A transformer trained to write Lagrangians symbolically (such as BART-L) thus embeds the space of theories itself. In this work, we investigate the navigation of this learned theory space using activation steering, adapted from interpretability work on LLMs. Using only small contrastive...

56. (ZOOM) Probing the Higgs Charge Parity at the LHC with Invertible Neural Networks

Nityaansh Parekh (Michigan State University (US))

CP-sensitive observables in H+2jet production, such as the azimuthal angle between the leading jets, are defined at parton level but measured at detector level, requiring unfolding to recover them. We present a conditional invertible neural network (cINN) that learns a full posterior over parton-level kinematics given detector-level observables trained jointly across multiple EFT coupling...

8. [CANCELED] AI for Rare Top-Higgs Processes at the LHC

Dr Adil Jueid (Korea Institute for Advanced Study)

The observation of flavor-changing neutral current (FCNC) interactions between the top quark and the Standard Model (SM) Higgs boson would constitute an unambiguous signal of physics beyond the SM. Searches for this process at the LHC are, however, extremely challenging due to the small signal rates and the strong kinematic resemblance between the signal and dominant SM backgrounds,...

93. Agentic Re-Casting using Agentic Re-Simulations

Nikita Schmal (Universität Heidelberg)

Analysis re-casting at the LHC is highly standardized and nevertheless requires resources, time, and expert physics input. Building on the newly developed MadAgents.v3 framework, we demonstrate how a global SMEFT analysis can be updated and improved through an agentic workflow with a physicist in the loop. Although demonstrated within the SFitter framework, the underlying technical aspects of...

135. Interpretable machine learning for dynamical dark energy models

Giulia Borghetto (University of Swansea)

Recent cosmological observations suggest possible deviations from a cosmological constant, pointing toward a dynamical nature of dark energy. Quintessence models, which assume a slowly rolling scalar field, provide a compelling theoretical framework to explain this late time evolution in the dark energy equation of state. However, identifying the correct form of the quintessence potential...

136. Optimizing local LLM agents for HEP

Darius Faroughy (Rutgers University)

LLM agents are beginning to take on real high-energy-physics workflows — tasks that demand orchestrating full toolchains of event generators, detector simulation, and analysis code rather than simply producing text. Making such agents reliable, auditable, and cheap enough to run on local hardware raises a distinct set of questions from those studied in general-purpose agent benchmarks.

This...

132. Scaling AllShowers: Sparse Attention and Fast Sampling for Universal Calorimeter Shower Simulation

Zlatan Dimitrov (GATE Institute; Sofia University St. Kliment Ohridski)

AllShowers (arXiv:2601.11716) marks a significant step towards a universal model for calorimeter shower simulations in collider experiments. Unlike traditional surrogate models that train separate networks for each particle species, AllShowers unifies shower generation across multiple particle types in a single continuous normalizing flow with a Transformer architecture, producing realistic...

65. Scaling tokenized models for full-event generation

Dan Godi (Weizmann Institute of Science)

Full simulation and reconstruction are projected to become major bottlenecks for computation at the High-Luminosity LHC, motivating the need for fast, ML-based surrogates. At the same time, LLMs have driven fast progress in generative discrete modeling: autoregressive transformers trained on tokenized data now represent the state of the art across a range of generative tasks. We extend the...