IN2P3/IRFU Machine Learning workshop 2026

Liste des Contributions

223. Welcome address by the LPSC director

Laurent Derome (LPSC)

16/11/2026 13:30

Welcome address

224. Welcome address by local organization committee

16/11/2026 13:50

Welcome address

184. Multi-Parameter Calibration and Uncertainty Propagation in LArTPCs Using Differentiable Simulation

Pierre Granger (CERN)

16/11/2026 14:10

Signal Processing, Calibration and Reconstruction

Standard talks

Signal Processing, Calibration and Reconstruction

Precision measurements in Liquid Argon Time Projection Chambers (LArTPCs) rely on accurate modeling of detector response. In standard calibration workflows, effects such as space charge, recombination, electron lifetime, and electronics response are usually measured independently. This segmented approach ignores correlations among parameters and can introduce systematic biases into the...

198. Deep Learning for Extracting Spectra form JWST Spectrograms

Soorya Narayan Rajeshkumar (Aix Marseille Univ, CNRS/IN2P3, CPPM, Marseille, France)

16/11/2026 14:30

Signal Processing, Calibration and Reconstruction

Standard talks

Signal Processing, Calibration and Reconstruction

With telescopes like the Euclid in orbit and CSST in the works, we are looking at an emerging era of astronomy with surveys producing millions and millions of slitless spectrograms. While the analytical extraction techniques are sufficient for the current amount of data, the community will require faster pipelines for future data releases. Added to the large amount of expected data, slitless...

196. A plug-and-play approach for tomographic weak-lensing mass mapping

Hubert Leterme (CEA IRFU/DAp)

16/11/2026 14:50

Signal Processing, Calibration and Reconstruction

Standard talks

Signal Processing, Calibration and Reconstruction

Upcoming surveys such as Euclid and Rubin will probe the matter distribution through weak lensing with unprecedented precision. However, reconstructing mass maps from noisy shear measurements is fundamentally an ill-posed inverse problem. While current deep-learning approaches achieve high reconstruction accuracy, they either must require retraining for each new sky region (due to varying mask...

203. R&T Think2

Sebastien Viret (IPN Lyon)

16/11/2026 15:10

Real-Time AI, Trigger and Edge Computing

Standard talks

Real-Time AI, Trigger and Edge Computing

We will present the status of the IN2P3 R&T THINK2, whose objective was to develop tools to embed machine learning algorithms in FPGAs for realtime applications (DAQ, trigger,...)

194. Physical and ML models for simulating spectroscopy instruments

Julien Zoubian (Aix Marseille Univ, CNRS/IN2P3, CPPM, Marseille, France)

16/11/2026 16:00

AI for Scientific Instruments and Accelerators

Standard talks

AI for Scientific Instruments and Accelerators

In the ANR DISPERS project, we use a physics-first approach to simulate spectroscopy instruments. Each physical stage of the instrument, such as optics, source catalogs, detector response, and calibration, is modeled based on physical principles wherever possible. Machine learning is only used to complement these models where physics alone is insufficient or too expensive. These model...

209. Unsupervised Machine Learning for Anomaly Detection in Beam Position Monitors Data

Quentin Bruant (CEA/IRFU/DACM)

16/11/2026 16:20

AI for Scientific Instruments and Accelerators

Standard talks

AI for Scientific Instruments and Accelerators

Turn-by-turn beam position monitors (TbT-BPMs) are the primary
diagnostic for optics measurement and correction in high-luminosity colliders.
Reliable identification of faulty sensors is essential to any optics
reconstruction pipeline, yet manual inspection does not scale to the hundreds
of monitors in current rings or the thousands expected in future machines such
as the FCC. We apply...

186. ARTIFACT network

Dr Adnan Ghribi ({CNRS}UPR3266)

16/11/2026 16:40

AI for Scientific Instruments and Accelerators

Standard talks

AI for Scientific Instruments and Accelerators

The ARTificial Intelligence For Accelerators, user Communities and associated Technologies (ARTIFACT) network—a collaborative, open-science network connecting research infrastructures, institutes, and universities— addresses these challenges by coordinating a concerted strategy for AI in accelerator science. Beyond accelerator physics, ARTIFACT establishes bridges with adjacent disciplines,...

187. The iRIS project : intelligent research infrastructures

Dr Adnan Ghribi ({CNRS}UPR3266)

16/11/2026 17:00

AI for Scientific Instruments and Accelerators

Standard talks

AI for Scientific Instruments and Accelerators

iRIS positions Research Infrastructures as testbeds and innovation engines for the green and digital transitions . Motivated by the Future Circular Collider and the Einstein Telescope, this project aims at demonstrating AI-powered environmental technologies and sustainability-by-design across the infrastructure lifecycle. Its relevance extends beyond fundamental-science RIs: AI approaches...

193. Machine learning surrogate models for collective effects studies in the FCC-ee High-Energy Booster

Keon Hee Kim (CNRS/GANIL)

16/11/2026 17:20

AI for Scientific Instruments and Accelerators

Lightning talks

AI for Scientific Instruments and Accelerators

Accurate beam dynamics simulations including collective effects are essential for the design of future particle accelerators, but high-fidelity macroparticle tracking can become computationally expensive, especially when large parameter scans are required. We investigate machine learning surrogate models for the evolution of beam distributions in the FCC-ee High-Energy Booster.

Rather than...

206. Jean Zay for AI in Physics: Resources, Access and Getting Started

Stéphane Ilic (IDRIS)

17/11/2026 09:00

AI Ecosystem: Infrastructure, Open Science and Community

Invited talk

AI Ecosystem: Infrastructure, Open Science and Community

Jean Zay, hosted at IDRIS, provides large-scale computing resources for AI research. This talk will offer a practical introduction for the IN2P3 and CEA-IRFU communities, focusing on the resources available and the steps required to access and use them effectively.

I will present the computing resources and software environment, together with an outlook on future capabilities. The...

226. LLM and agents

François Portet (IMAG), Maxime Calka (UGA)

17/11/2026 09:30

Invited talk

AI Ecosystem: Infrastructure, Open Science and Community

216. Lightcone Research: an open ecosystem for reproducible, composable and verifiable physics analyses in the age of AI agents

Alexandre Boucaud (APC / IN2P3)

17/11/2026 10:00

AI Ecosystem: Infrastructure, Open Science and Community

Standard talks

AI Ecosystem: Infrastructure, Open Science and Community

Nowadays, AI agents that can write and run scientific code on their own. From coding assistants such as Claude Code, Cursor and Codex to integrated research systems such as Kosmos and Gemini Co-Scientist or Claude Science, they all are rapidly changing how analyses are built in physics. This speed also makes an existing problem worse. Methodological choices, assumptions and scientific...

217. French tokens for everyone : partnering with the ILaaS Federation

Alexandre Boucaud (APC / IN2P3)

17/11/2026 10:20

AI Ecosystem: Infrastructure, Open Science and Community

Lightning talks

AI Ecosystem: Infrastructure, Open Science and Community

Large language models are quickly becoming everyday tools for physicists and software developers, whether for coding help, documentation, data exploration or agentic workflows. Yet access is uneven, and most usage goes through shadow IT with commercial frontier APIs, which raises concerns about cost, data sovereignty and environmental footprint. Many research needs, however, do not require a...

219. Accelerating Weather Forecasts with Artificial Intelligence

Dr Mikaël Jacquemont (Bull SAS)

17/11/2026 10:55

AI for Physics Analysis, Inference and Discovery

Invited talk

AI for Physics Analysis, Inference and Discovery

Until very recently, weather forecasting almost only relied on solving physical equations using numerical solvers called numerical weather prediction (NWP) models. Modelling the atmosphere faster and at higher precision was made possible thanks to access to more computing power through the evolution of High-Performance Computing (HPC) clusters.
The rise of Artificial Intelligence (AI), more...

185. emulating accurately and consistently the cosmological power spectrum and the halo mass function

johan comparat

17/11/2026 11:25

AI for Physics Analysis, Inference and Discovery

Standard talks

AI for Physics Analysis, Inference and Discovery

Cosmological forecasts and likelihood analyses increasingly need two ingredients at once: the linear matter power spectrum, and the abundance of dark matter haloes. Computing them exactly is far too slow for parameter inference, and computing them from unrelated approximations quietly introduces inconsistencies between the two.

In this presentation, I will introduce two emulators built to...

192. Speeding-up the search for anomalies in ZTF time series with interpretable machine learning

Emmanuel Gangler (LPC)

17/11/2026 11:45

AI for Physics Analysis, Inference and Discovery

Standard talks

AI for Physics Analysis, Inference and Discovery

Machine learning is often viewed as a black box when it comes to understanding its output, be it a decision or a score. Automatic anomaly detection is no exception to this rule, and quite often the astronomer is left to independently analyze the data in order to understand why a given event is tagged as an anomaly. Interpretable AI on the other hand provides clues to the analyst, often in the...

227. AI/ML for large galaxy survey analyses

Agnès Ferté (LPNHE)

17/11/2026 12:05

Standard talks

AI for Physics Analysis, Inference and Discovery

Large galaxy surveys such as the Dark Energy Survey (DES) or the new LSST from the Vera C. Rubin Observatory offer several cosmological probes to test dark energy and gravity. The combination of galaxy clustering and weak lensing has proven to be a powerful probe, especially in combination with complementary probes such as galaxy clusters, supernovae and the baryonic acoustic oscillation peak....

213. Revisiting Nuclear Cross Sections for Cosmic Rays with Gaussian Processes

Anthony Correia (LPSC,IN2P3/CNRS/UGA)

17/11/2026 12:25

AI for Physics Analysis, Inference and Discovery

Lightning talks

AI for Physics Analysis, Inference and Discovery

Inelastic and production cross sections are crucial inputs for predicting nuclear cosmic-ray fluxes in the Galaxy. Deuterium (²H) and helium-3 (³He) are both expected to be produced solely by interactions of heavier nuclei with the interstellar gas, yet recent AMS-02 and Voyager data are in tension with this picture. In this context, it is natural to revisit the relevant nuclear cross...

191. Physics-informed impedance-model-agnostic reconstruction of point-charge wakefields from finite bunch electromagnetic simulations

Keon Hee Kim (CNRS/GANIL)

17/11/2026 12:30

AI for Physics Analysis, Inference and Discovery

Lightning talks

AI for Physics Analysis, Inference and Discovery

Electromagnetic wakefield simulations generally provide wake potentials excited by finite length bunches, whereas beam dynamics studies require the underlying point-charge wake and broadband impedance. Direct access to the THz impedance regime in full 3D electromagnetic simulations typically requires extremely short drive bunches and very fine numerical resolution. The resulting simulations...

222. Beyond efficiency: Frugal AI

Dr Sophie CERF (INRIA)

17/11/2026 14:00

Invited talk

AI Ecosystem: Infrastructure, Open Science and Community

The adoption of AI is accelerating and its ecological impacts are soaring, despite tremendous improvements of technologies efficiency. Indeed, such improvements have historically consistently led to increased usage and thus overall impacts of AI technologies. Yet, frugality of AI is a major preoccupation, e.g. at the national (AFNOR reference document), and European (AI act) levels. In this...

225. MIAI Cluster: the Grenoble Alpes AI cluster and what it offers to physics

Cyrille Doux (LPSC)

17/11/2026 14:30

Invited talk

AI Ecosystem: Infrastructure, Open Science and Community

MIAI Grenoble Alpes is one of the nine French AI clusters, built on the 3IA institute created in 2019 and coordinated by Université Grenoble Alpes with UCA and USMB. It brings together about 600 researchers from more than 100 laboratories, from machine learning, generative AI and explainable or frugal AI to vision, robotics, health, environment and industry. This talk presents the cluster's...

215. Hybrid Latent-Space Inference for Galaxy Deblending

Anna Preto

17/11/2026 14:50

AI for Physics Analysis, Inference and Discovery

Standard talks

AI for Physics Analysis, Inference and Discovery

In the absence of systematic errors, weak lensing is among the most constraining probes of dark energy. Blending is a major source of systematic uncertainty for weak-lensing analyses, affecting both galaxy shape measurements and photometric redshifts. At LSST depth, blending is estimated to affect about 62% of detectable galaxies. Deblending therefore requires assigning the observed flux among...

201. Accurate and efficient simulation-based inference for massive black-hole binaries with LISA

Alice Spadaro (L2I Toulouse, CNRS/IN2P3, Université de Toulouse)

17/11/2026 15:10

AI for Physics Analysis, Inference and Discovery

Standard talks

AI for Physics Analysis, Inference and Discovery

The Laser Interferometer Space Antenna (LISA) is a future space-based gravitational-wave observatory designed to detect low-frequency gravitational waves, including those produced by massive black-hole binaries. I will present a machine-learning framework based on normalizing flows for rapid Bayesian parameter estimation of these sources. The method is trained on simulated LISA signals and can...

205. MODULARITY: A Modular Architecture for Distributed Autonomous Scientific Discovery

Hayg Guler (IJCLAB)

17/11/2026 15:30

AI for Physics Analysis, Inference and Discovery

Standard talks

AI for Physics Analysis, Inference and Discovery

Modern scientific facilities increasingly combine complex instrumentation, simulations, heterogeneous diagnostics, and machine-learning-based control. We propose MODULARITY, a domain-agnostic architecture for distributed closed-loop experimentation, where complex systems are decomposed into interoperable autonomous modules. Each module combines observations, control variables, constraints,...

212. Machine Learning-Based Event Categorisation for Higgs-to-Dimuon Analyses

Somanko Saha

17/11/2026 15:50

AI for Physics Analysis, Inference and Discovery

Lightning talks

AI for Physics Analysis, Inference and Discovery

The search for the Higgs boson decay to a pair of muons provides a direct probe of the Higgs coupling to second-generation fermions and represents an important test of the Standard Model. Due to the small branching fraction of this decay and the large backgrounds from Drell–Yan and other processes, achieving high sensitivity requires efficient exploitation of the kinematic and event-level...

218. Self Organised Randoms for correcting systematic effects in Euclid photometric galaxy clustering.

Dr Jérôme Odier (LPSC Grenoble)

17/11/2026 16:30

AI for Physics Analysis, Inference and Discovery

Standard talks

AI for Physics Analysis, Inference and Discovery

The Euclid satellite is designed to make accurate measurements of weak lensing and galaxy clustering for the purpose of probing structure formation over half of the age of the Universe. However, spatial variations in the Euclid survey and instrumental properties, as well as on the foreground sky emission, can affect photometric galaxy clustering and bias cosmological results. To correct for...

195. LIS² (Large Image Split Segmentation): A Modular Research Software Framework for Deep Learning on Large-Scale Scientific Images

Dr Dominique Benielli (Aix Marseille Univ, CNRS, LIS, Marseille, France)

17/11/2026 16:50

Event/Object Reconstruction and Identification

Standard talks

AI for Physics Analysis, Inference and Discovery

The automatic detection of interstellar filaments in large-scale astrophysical surveys is a challenging segmentation problem for deep learning methods. Observations cover large portions of the Galactic plane and exhibit a wide range of densities and contrasts, spatially varying noise, and a heterogeneous distribution of structures. In addition, available annotations are necessarily incomplete,...

221. Cosmology using topological data analysis with SBI

Cyrille Doux (LPSC)

17/11/2026 17:10

AI for Physics Analysis, Inference and Discovery

Standard talks

AI for Physics Analysis, Inference and Discovery

In this talk I will present a cosmological analysis of weak lensing data from the Dark Energy Survey using a topological descriptors, persistent homology, within a simulation-based inference framework. This analysis captures cosmological information from the field beyond Gaussian, complementing standard two-point correlation functions.

214. Lorentz-Equivariant Transformers for ttX multi-lepton final state at the LHC

JINU RAJ

17/11/2026 17:30

AI for Physics Analysis, Inference and Discovery

Lightning talks

AI for Physics Analysis, Inference and Discovery

Rare top-quark processes, ttW,ttH,tH,ttZ,tttt, are traditionally measured in separate analyses, despite substantial overlap among their multilepton final states. However, this strongly limits the overall physics understanding, as the correlations between the various measurements are large and poorly known. We propose a new approach to tackle these limitations by simultaneously reconstructing...

210. GammaLearn: deep-learning event reconstruction for the CTAO - Results and Lessons learned between 2017 and 2026

Dr Thomas Vuillaume (LAPP, Univ. Savoie Mont-Blanc, CNRS)

18/11/2026 09:00

Event/Object Reconstruction and Identification

Standard talks

Event/Object Reconstruction and Identification

Since 2017, GammaLearn has developed deep-learning event reconstruction for Imaging Atmospheric Cherenkov Telescopes. Our main target is LST-1, the first Large-Sized Telescope of CTAO. One multi-task convolutional network, γ-PhysNet, estimates the particle type, energy and arrival direction of each event from the calibrated camera image and pixel timing.

From indexed convolution on...

199. Machine Learning for event reconstruction with uncertainty quantification in the ClearMind ultra-fast detector

Dr Théo Kaprélian (Université Paris-Saclay, CEA, Service de Génie Logiciel pour la Simulation, Gif-surYvette, 91191, Franc)

18/11/2026 09:20

Event/Object Reconstruction and Identification

Standard talks

Event/Object Reconstruction and Identification

The ClearMind collaboration [1] aims to develop a gamma detector with a coincidence resolving time below 100 ps. The detector combines a large monolithic crystal with a photocathode deposited directly on its surface and coupled to a microchannel plate photomultiplier tube (MCP-PMT). The opposite face is instrumented with silicon photomultipliers (SiPMs) to improve depth of interaction (DOI)...

207. Transformers for reconstruction of electromagnetic showers in calorimeters

Yuliia Maidannyk (CEA-IRFU)

18/11/2026 09:40

Event/Object Reconstruction and Identification

Standard talks

Event/Object Reconstruction and Identification

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...

182. Upgrade II LHCb calorimeter real-time reconstruction with GNN

Aniol Lobo Salvia (CNRS - LAPP)

18/11/2026 10:00

Event/Object Reconstruction and Identification

Standard talks

Event/Object Reconstruction and Identification

Upgrade II constitutes a major leap forward at LHCb towards more and better data, driven by new hardware and software that will enable an ambitious increase of the current instant luminosity, thus, the experiment's physics reach. In particular, the calorimeter will be replaced by the new branded PicoCal, featuring better granularity and timing capabilities.
A significant challenge will be to...

204. SPINE for DUNE

Nived PUTHUMANA MELEPPATTU (IJCLab)

18/11/2026 10:20

Event/Object Reconstruction and Identification

Standard talks

Event/Object Reconstruction and Identification

SPINE (Scalable Particle Imaging with Neural Embeddings) is a transformative, ML-native approach to reconstruction and is rapidly becoming a common reconstruction pipeline across LArTPC experiments. Building on its strong performance in ICARUS, SBND and ND-LAr, we are extending SPINE to the DUNE Far Detector and its two large-scale prototypes at CERN. This is not a direct port of existing...

211. A machine learning approach to stellar stream detection in photometric surveys

Matthieu Pelissier (LPSC/UGA)

18/11/2026 10:40

Event/Object Reconstruction and Identification

Lightning talks

Event/Object Reconstruction and Identification

Stellar streams are faint remnants of disrupted dwarf galaxies or globular clusters, orbiting within our Galaxy's halo. These low-surface-brightness structures can be detected in photometric surveys such as DES and LSST, but detection has so far relied on visual inspection. We aim to automate this process using a machine learning approach, trained on simulated streams injected with the...

220. Stratégie IA à l'IN2P3 - vers un GDR

Julien DONINI (UBP/LPC/IN2P3)

18/11/2026 11:15

AI at IN2P3/CNRS and at CEA/Irfu

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

David Rousseau (IJCLab, Université Paris-Saclay)

18/11/2026 14:00

AI for Physics Analysis, Inference and Discovery

Standard talks

Foundation Models, Representation Learning and Generative AI

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...

208. CaloFound: towards a foundation model for calorimetry

Mehmet Ozgur Sahin (CEA-Saclay)

18/11/2026 14:20

Foundation Models, Representation Learning and Generative AI

Standard talks

Foundation Models, Representation Learning and Generative AI

CaloFound uses conditional shower generation to pretrain a reusable transformer representation in an unsupervised manner for calorimeter representation and reconstruction. Using GEANT4 simulations of a CMS-like electromagnetic calorimeter, it masks a ($9\times9$) crystal window around a photon impact, randomly placing its impact crystal within the central ($3\times3$) region. The encoder...

183. The Limits of Foundation Models for Jet Physics: Tagging, Generation, Scaling and Anomalies

Humberto Reyes-Gonzalez (RWTH Aachen)

18/11/2026 14:40

Foundation Models, Representation Learning and Generative AI

Standard talks

Foundation Models, Representation Learning and Generative AI

Jets are ubiquitous but highly complex objects at the LHC, and learning their substructure patterns provides information about the particles that produced them and, ultimately, the underlying physics. They are therefore paramount to the LHC physics program. Foundation models have emerged as a powerful new ML paradigm for modelling jets and harnessing the information encoded in their...

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

Tuan Pham (IJCLab - Paris Saclay)

18/11/2026 15:00

Foundation Models, Representation Learning and Generative AI

Standard talks

Foundation Models, Representation Learning and Generative AI

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...

197. FoSFor : Multiscale Graph Representations from Forest-Based Coarse-Graining

Dominique BENIELLI (Aix Marseille Université), Dr Sacha Duverger (Aix Marseille Univ, CNRS, I2M, Marseille, France)

18/11/2026 15:20

Foundation Models, Representation Learning and Generative AI

Lightning talks

Foundation Models, Representation Learning and Generative AI

Representing large and complex scientific data as graphs requires methods that capture their structure across different scales while remaining computationally tractable. In this context, the FoSFor (Forest Screening for Multiscales Network Processing) toolbox, a CNRS Innovation Open project, provides a forest-based coarse-graining framework for constructing compact and multiscale graph...

228. Closing

18/11/2026 15:25

Closing