EuCAIFCon 2026

Session

🔀 Patterns & Anomalies

24 Aug 2026, 16:00

3.404

Conveners

🔀 Patterns & Anomalies

• Ramon Winterhalder (University of Milan)

🔀 Patterns & Anomalies

• Sebastian Dittmeier (PI)

🔀 Patterns & Anomalies

• Dennis Noll

🔀 Patterns & Anomalies

• Nicole Hartman (TUM)

111. Unsupervised Machine Learning for Model-Independent Searches at the LHC

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))

24/08/2026, 16:00

Patterns & Anomalies

Since the discovery of the Higgs boson, no experimental evidence for physics beyond the Standard Model has been observed at the LHC. While most searches rely on specific signal hypotheses, anomaly detection aims at identifying potential new-physics signatures without assuming a particular BSM model.

In recent years, unsupervised machine learning has become an active area of research in...

103. Searching Everything, Everywhere, All at Once

Theresa Reisch (University of Geneva)

24/08/2026, 16:10

Patterns & Anomalies

The LHC search programme remains largely model-driven, probing one final state and one model hypothesis at a time, complemented by occasional model-agnostic searches such as those in dijet spectra. We aim to take the next step: probing many final states at once, in an automatic and robust way, using limited resources efficiently to cover large regions of phase space. This combines reusing our...

159. Anomaly detection for multi-jet resonances

Chitrakshee Yede (Universität Hamburg)

24/08/2026, 16:20

Patterns & Anomalies

The search for physics beyond the standard model is one of the prime focuses in high-energy physics. Conventional searches at the LHC, though comprehensive, have not yet shown signs for new physics. Machine learning based anomaly detection has emerged offering a model-agnostic way to enhance the sensitivity of generic searches as compared to those targeting specific signal model. CATHODE...

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

Rafał Masełek (Jozef Stefan Institute)

24/08/2026, 16:30

Patterns & Anomalies

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...

188. HAXAD: Anomaly Detection in the Higgs Peak

Dennis Noll

24/08/2026, 16:50

Patterns & Anomalies

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...

142. Towards a Statistical Interpretation of the Normalized Autoencoder

Jonathan Ostertag-Henning (ITP Heidelberg)

24/08/2026, 17:00

Patterns & Anomalies

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...

61. Unsupervised Anomaly Detection for LHC Collision Data Using a Transformer-Based Autoencoder.

ASRITH KRISHNA RADHAKRISHNAN (University of Bologna (IT))

24/08/2026, 17:10

Patterns & Anomalies

An unsupervised machine learning framework is developed for searching for anomalous events in proton-proton collisions at √s=13 TeV using ATLAS Open Data. The analysis utilizes an object-based Masked Transformer autoencoder trained exclusively on Standard Model Run 2 data to learn complex correlations among reconstructed physics objects and identify events that deviate from expected Standard...

88. Kitchen Sink Anomaly Detection

Lukas Lang (RWTH Aachen University)

24/08/2026, 17:20

Patterns & Anomalies

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...

92. 4D particle tracking in the NA62 GigaTracker with transformer-based architectures

Leonardo Plini (INFN-LNF)

25/08/2026, 11:00

Patterns & Anomalies

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 $K^{+} \rightarrow \pi^{+} \nu \bar{\nu}$. Operating in a high-intensity environment with a beam rate of up to 750 MHz, the GTK provides the...

7. Machine Learning-Based Suppression of Secondary Hit Background in Low-Resistive RPCs

Dr Zubayer Ahammed (Variable Energy Cyclotron Centre, India)

25/08/2026, 11:10

Patterns & Anomalies

Resistive Plate Chambers (RPCs) are widely used as tracking detectors in high-energy physics experiments due to their simplicity, robustness, and excellent timing performance. However, low-resistive bakelite RPC prototypes often exhibit secondary hit components that degrade time and position resolution and introduce background, complicating track reconstruction. In this work, we present a...

41. PID Reconstruction in Gaseous Detectors for Future e+e- Experiments

Guang Zhao (Institute of High Energy Physics (CAS))

25/08/2026, 11:20

Patterns & Anomalies

PID is essential in high energy physics experiments, particularly for future e+e- colliders. The tera-z samples at FCC or CEPC offers vast flavor physics opportunities, necessitating robust hadron identification over a broad momentum range. Moreover, there is growing recognition of the performance gains that PID provides for jet flavor tagging. A key breakthrough in PID is cluster counting...

125. GBDT based unified PID scheme for the CBM experiment

Pavish Subramani (University of Wuppertal)

25/08/2026, 11:30

Patterns & Anomalies

The Compressed Baryonic Matter (CBM) experiment is a fixed target heavy-ion collision experiment currently being built at the Facility for Antiproton and Ion Research (FAIR), Darmstadt, Germany.
The CBM experiment is designed to probe the QCD phase diagram at moderate temperatures and high net-baryon density via different physical observables, including flow, fluctuations, and correlations of...

154. Generative and geometric learning for comprehensive collider event reconstruction

Ethan Simpson (The University of Manchester (GB))

25/08/2026, 11:50

Patterns & Anomalies

In particle collider experiments, event reconstruction is the task of inferring the kinematics of the short-lived, 'interesting' particles of the hard scatter from the stable final states recorded by detectors. We decompose event reconstruction into two tasks: assigning measured jets and leptons to parent particles, and regressing unmeasured neutrino kinematics. We present a novel geometric...

146. Encoding locality and geometry in a Transformer encoder for muon triggers

Nadezhda Dobreva

25/08/2026, 12:00

Patterns & Anomalies

Muon reconstruction in high-energy physics experiments relies on identifying detector hits originating from muons and fitting trajectories through them to extract track parameters. This process currently consists of separating signal hits from background before the track reconstruction can be performed. In this work, we present a deep learning solution for discriminating between background and...

48. Can multi-modality improve IACTs event reconstruction in heterogeneous observing conditions?

Thomas Vuillaume (LAPP, CNRS, USMB)

25/08/2026, 12:10

Patterns & Anomalies

Deep learning methods have emerged as a powerful alternative to reconstruct physical properties directly from images of atmospheric events acquired by Imaging Atmospheric Cherenkov Telescopes (IACTs). In the context of the Cherenkov Telescope Array Observatory (CTAO) first Large-Sized Telescope (LST-1), the specialized architecture gamma-PhysNet has demonstrated strong performances on...

199. Recent Results from Anomaly Detection Searches on CMS

Jovin Drews (Universität Hamburg)

25/08/2026, 12:20

Patterns & Anomalies

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.

35. Anomaly-detection of gravitational waves through the 4th observing run of the LIGO detectors

Gianluca Inguglia (MBI Vienna), Huw Haigh (MBI Vienna), Ulyana Dupletsa (MBI Vienna)

26/08/2026, 16:00

Patterns & Anomalies

We present an anomaly detection algorithm based on a deep convolutional autoencoder. The algorithm, initially developed with a focus on the Einstein Telescope, was adjusted to the higher noise levels of the LIGO detectors, implementing coherence, trained and validated using O3 data, and tested on publicly available O4 data. We achieve an excellent recovery rate for short, loud signals and...

164. Anomaly detection for generic-transient gravitational waves

Prof. Elena Cuoco (Unversity of Bologna)

26/08/2026, 16:10

Patterns & Anomalies

All gravitational wave detections thus far have been from binary compact object coalescences. These detections rely on analyses that exploit the well-modelled nature of the sources. Generic-transient (burst) gravitational waves, on the other hand, do not have well-modelled gravitational wave signals. Therefore, searches for burst gravitational waves must efficiently scan a broad parameter...

147. DeepExtractor: Glitch Mitigation and Template Free Searches with Model-Agnostic Reconstruction using Deep Learning

Tom Dooney (Nikhef / Utrecht University)

26/08/2026, 16:20

Patterns & Anomalies

Gravitational-wave detectors such as LIGO, Virgo, and KAGRA, detect faint signals from distant astrophysical events. However, their high sensitivity also exposes them to noise artifacts — including unmodelled transients known as "glitches" — that can mimic or mask genuine signals. Last year we introduced DeepExtractor, a deep learning framework that reconstructs arbitrary signals or glitches...

165. Anomaly Detection for Faint Galactic Substructure with EagleEye

Sven Põder (SISSA)

26/08/2026, 16:30

Patterns & Anomalies

Detecting faint stellar substructure in the Milky Way halo and its surroundings favours methods that remain sensitive to weak signals without restrictive assumptions about either the signal morphology or the Galactic background. We present recent applications of EagleEye, a model-independent anomaly detection framework that compares multidimensional data distributions to identify localized...

140. Exploiting the Latent Space of Convolutional Autoencoders to identify low-energy recoil signals in a dual-phase LAr TPC

Gioacchino Alex Anastasi (Università di Catania & INFN Catania)

26/08/2026, 16:40

Patterns & Anomalies

In this contribution, we propose a data-driven approach based on unsupervised learning, specifically using deep Convolutional AutoEncoders (CAE), to identify signals from low-energy nuclear recoils in the dual-phase Liquid Argon Time Projection Chamber (LAr TPC) of the Recoil Directionality (ReD) experiment. This is a challenging task for recoil energies $\sim$1 keV, since scintillation...

131. Multi-task, Multi-modal Transformers for Jet Flavour Tagging in ATLAS

Alexander Froch (Université de Genève)

27/08/2026, 11:00

Patterns & Anomalies

Identifying the flavour of hadronic jets is a cornerstone of the ATLAS physics programme, underpinning measurements of the Higgs boson and top quark as well as searches for di-Higgs production and physics beyond the Standard Model. We present the latest generation of ATLAS flavour-tagging algorithms, which have evolved from hybrid multi-stage approaches into unified transformer architectures...

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

Sebastian Pitz (LPNHE Paris)

27/08/2026, 11:10

Patterns & Anomalies

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...

167. Virtues and Vices of Equivariant Transformers

Jonas Spinner (IPPP, Durham University)

27/08/2026, 11:20

Patterns & Anomalies

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 all 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...

38. Gauge equivariant transformer for lattice gauge theories

Fracesco Passante (Sapienza Università di Roma and INFN)

27/08/2026, 11:30

Patterns & Anomalies

Gauge equivariant convolutional neural networks have shown that enforcing exact lattice gauge symmetry in a neural network significantly improves regression accuracy on gauge invariant observables. However, their convolutional kernels stay fixed after training and cannot adapt to configuration-dependent features. We introduce GELT (Gauge Equivariant Lattice Transformer), a gauge equivariant...

22. Towards a comprehensive high-z quasar selection: multimodal self-supervised learning on Euclid data

Tatsuyuki Sekine (University of Hamburg)

27/08/2026, 11:50

Patterns & Anomalies

Within the first billion years of cosmic time, galaxies and supermassive black holes (SMBHs) had already formed. Especially, rapidly growing billion solar mass black holes - shining as quasars - discovered at z > 7 challenge standard models of SMBH growth. To constrain their formation, expanding the quasar redshift frontier is critical.
The deep, wide-area photometry of the Euclid mission,...

168. SURFing to the Fundamental Limit of Jet Tagging

Ranit Das (Heidelberg University)

27/08/2026, 12:00

Patterns & Anomalies

Beyond the practical goal of improving search and measurement sensitivity through better jet tagging algorithms, there is a deeper question: what are their upper performance limits? Generative surrogate models with learned likelihood functions offer a new approach to this problem, provided the surrogate correctly captures the underlying data distribution. In this work, we introduce the...

82. Multiclass classification without labels (multiCWoLa)

Johann Ioannou-Nikolaides (Niels Bohr Institute), Raphaël Bonnet-Guerrini (Computer Science Dep. University of Milan)

27/08/2026, 12:10

Patterns & Anomalies

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...

151. A Machine-Learning Analysis of the Higgs Boson in the H → ZZ∗ →4ℓ Channel

Mane Papoyan (American University of Armenia (AUA))

27/08/2026, 12:20

Patterns & Anomalies

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...