Conveners
🔀 Simulations & Generative Models
- Andreas Ipp (TU Wien)
🔀 Simulations & Generative Models
- Marco Letizia (Università di Genova)
🔀 Simulations & Generative Models
- Andre Scaffidi (SISSA)
🔀 Simulations & Generative Models
- Andrew Pilkington (University of Manchester)
-
Florian Ernst (Heidelberg University (DE), CERN)24/08/2026, 16:00Simulations & Generative Models
One of the costliest elements of the ATLAS detector simulation is the precise modelling of electromagnetic and hadronic showers. With the aim of lowering CPU usage in Run 3 of the LHC, the collaboration introduced AtlFast3, a fast simulation tool that combines classical histogram-based parameterisations with calorimeter models built on GANs. Once Run 3 was underway, a new effort was launched...
Go to contribution page -
Thorsten Buss (RWTH Aachen)24/08/2026, 16:10Simulations & Generative Models
To reduce the high computational demand of detector simulations in high-energy physics, various generative surrogate models have been proposed. Classically, one generative model per incident particle type is trained, requiring separate trainings and model weights. This results in increased training and human effort, as well as a larger memory footprint during inference, since multiple sets of...
Go to contribution page -
Lorenzo Valente (University of Hamburg)24/08/2026, 16:20Simulations & Generative Models
Deep generative surrogates can cut the computing cost of detailed Geant4 calorimeter simulation, but they remain tied to the detector they were trained on: each new geometry typically demands a large in-domain dataset. We present two studies that reduce this dependence for point cloud generative models.
In the first, a CaloClouds-based diffusion model pre-trained on ILD photon showers...
Go to contribution page -
Henry Day-Hall (DESY)24/08/2026, 16:30Simulations & Generative Models
Physics employs careful factorising of effects to make powerful general predictions. In a Mixture of Experts network, well chosen factorisation of knowledge can improve both memory footprint and generalisation.
This work explores the relative merits of Expert networks, in comparison to equivalent generalist models. In the setting of fast generative calorimeter simulation, both architectures...
Go to contribution page -
Dmitrii Kobylianskii (Weizmann Institute of Science)24/08/2026, 16:50Simulations & Generative Models
Detector simulation and event reconstruction constitute the primary computational bottleneck in modern particle physics. To bypass these CPU-intensive processing chains, we present Parnassus (Particle-flow Neural Assisted Simulations), a state-of-the-art generative AI framework for end-to-end fast simulation. Utilizing conditional flow matching, Parnassus maps truth-level stable particles...
Go to contribution page -
Oliver Schumann (LMU Munich)24/08/2026, 17:00Simulations & Generative Models
By striving for ever-higher luminosities, the Belle II detector is set to observe rare decay signals. However, these high luminosities correspond to an increased demand for MC-simulated events. Therefore, an efficient algorithm to produce and process simulated events in large quantities is vital for the successful interpretation of Belle II’s data. While generating events in the MC simulation...
Go to contribution page -
Luigi Favaro (UCLouvain - CP3)24/08/2026, 17:10Simulations & Generative Models
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...
Go to contribution page -
Gert Aarts (Universitaet Bielefeld)25/08/2026, 11:00Simulations & Generative Models
Diffusion models are a widely used method in generative AI to produce images and videos. I will discuss the application to lattice field theory and the connection with methods known from theoretical physics, such as stochastic quantisation. Applications to non-abelian gauge theories using gauge-equivariant convolutional neural networks are presented.
Go to contribution page -
Bao-Dong Sun (Ruhr-Universität Bochum)25/08/2026, 11:10Simulations & Generative Models
We apply score-based diffusion models to two-dimensional SU(2) lattice pure gauge theory with the Wilson action, extending recent work on U(1) gauge theories. The SU(2) manifold structure is handled through a quaternion parameterization. The model is trained on 10,000 configurations generated via Hybrid Monte Carlo at a fixed coupling $\beta_0= 2.0$ on an $8\times 8$ lattice, augmented to...
Go to contribution page -
Andreas Ipp (TU Wien)25/08/2026, 11:20Simulations & Generative Models
Numerical simulations of quantum field theories are indispensable for precision studies of the Standard Model, yet extracting continuum physics from discretized spacetime remains challenging due to lattice artifacts. Renormalization-group improved fixed-point (FP) actions provide an elegant solution by suppressing these artifacts, but their complexity has long prevented their practical use....
Go to contribution page -
Prof. Kai Zhou (CUHK-Shenzhen)25/08/2026, 11:30Simulations & Generative Models
Generative AI is rapidly becoming more than a tool for producing realistic images: in physics, it can be understood as a learnable machinery for transporting, sampling, and interrogating high-dimensional probability measures. In this talk I will discuss how this viewpoint opens new routes for exploring QCD matter under extreme conditions, where both first-principles theory and event-by-event...
Go to contribution page -
Timur Sypchenko (IPPP)25/08/2026, 11:50Simulations & Generative Models
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...
Go to contribution page -
Iuliia Panteleeva25/08/2026, 12:00Simulations & Generative Models
Extracting hadronic form factors from sparse and noisy lattice QCD data typically relies on parametric ansätze, introducing model-dependence. We present a generative framework based on denoising diffusion models for parameterisation-independent reconstruction of these quantities. The generative prior is built from a large ensemble of synthetic curves drawn from distinct functional classes...
Go to contribution page -
Jan Pawlowski (Heidelberg university)25/08/2026, 12:10Simulations & Generative Models
The physics-informed renormalisation group describes general reparametrisation of given data distributions. It provides an analytic flow in terms of the distribution itself and the differential reparametrisation, the physics-informed kernel. From the perspective of quantum field theory, this flow can be understood as a general non-linear coarse graining procedure. From the perspective of...
Go to contribution page -
Renzo Kapust (University of Heidelberg)25/08/2026, 12:20Simulations & Generative Models
Computing observables with respect to highly oscillatory or complex-valued distributions is an important task in physics, in particular in quantum field theory. For complex distributions, however, traditional sampling algorithms either lose their straightforward applicability or are rendered inefficient by the oscillations, which cause a signal-to-noise problem that scales exponentially with...
Go to contribution page -
Victoria Isensee (TU Darmstadt / GSI)26/08/2026, 14:00Simulations & Generative Models
Inferring physical parameters — such as magnetic field and alignment errors -- from sparse, noisy sensor data is essential for maintaining designed performance in machines like the GSI heavy-ion synchrotron SIS18 and the FAIR fragment separator SFRS. Rather than fitting a surrogate to simulation output, we construct a Gaussian Process kernel from an ensemble of forward simulations of the...
Go to contribution page -
Zewei Xiong (GSI, Darmstadt)26/08/2026, 14:10Simulations & Generative Models
Neutron-rich outflows in neutron-star mergers (NSMs) or other explosive events can be subject to substantial heating through the release of rest-mass energy in the course of the rapid neutron-capture (r-) process. This r-process heating can potentially have a significant impact on the dynamics determining the velocity distribution of the ejecta, but due to the complexity of detailed nuclear...
Go to contribution page -
Ariadna Uxue Palomino Ylla (Nagoya University)26/08/2026, 14:20Simulations & Generative Models
We investigate whether matter-induced deviations from a vacuum black hole spacetime can be constrained through redshift observations of orbiting stars. Building on our previous study of redshift signatures in fluid-perturbed black hole backgrounds, we consider the problem of efficiently connecting model parameters to observable redshift curves in a setting relevant for data analysis. Since...
Go to contribution page -
Divesh Jain (Heidelberg University)26/08/2026, 14:30Simulations & Generative Models
The Epoch of Reionization marks the period when the first galaxies ionized the neutral hydrogen in the intergalactic medium. Upcoming 21 cm experiment such as SKA, together with line-intensity mapping and galaxy surveys, will observe overlapping cosmic volumes. Much of their constraining power will come from cross-correlating different tracers, since each observable is affected by different...
Go to contribution page -
Thomas Blankenburg26/08/2026, 14:50Simulations & Generative Models
Observations of the large-scale structure, such as intensity maps of the 21cm line of neutral hydrogen, raise the question whether a precise, robust, and efficient mapping can be established from these observables to the underlying dark matter density field. We present a direct diffusion framework based on Conditional Flow Matching that enables accurate reconstruction of dark matter density...
Go to contribution page -
Haris Kapetanovic26/08/2026, 15:00Simulations & Generative Models
Fourier Neural Operators (FNOs) and related architectures have emerged as promising surrogates for physical systems, with notable success in fluid dynamics, where they achieve high accuracy at a small fraction of the cost of conventional solvers. Reionization cosmology is a demanding test of that promise: the neutral fraction field in 21cm simulations is near-binary, dominated by sharp...
Go to contribution page -
Waleed Esmail26/08/2026, 15:10Simulations & Generative Models
Fast waveform surrogates are essential for gravitational-wave inference, but neural surrogates typically lack uncertainty estimates and offer little guidance on how accuracy scales with training resources. We present an autoregressive flow-matching surrogate for binary-black-hole waveforms that operates on amplitude-phase representations and samples each successive segment with a conditional...
Go to contribution page -
Xisco Jimenez Forteza (Universitat de les Illes Balears)26/08/2026, 15:20Explainability & Theory
Machine learning techniques are increasingly being explored as complementary tools for solving complex problems in gravitational physics. In this talk, I will present recent work on the application of neural-network-based methods to black hole dynamics across different regimes. On the one hand, perturbative models provide an ideal framework for investigating the spectral properties of black...
Go to contribution page -
Giovanni De Crescenzo27/08/2026, 11:00Simulations & Generative Models
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...
Go to contribution page -
Sophia Vent (Heidelberg University)27/08/2026, 11:10Simulations & Generative Models
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...
Go to contribution page -
Daohan Wang (Marietta Blau Institute for Particle Physics, Austrian Academy of Sciences)27/08/2026, 11:20Simulations & Generative Models
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 controlled from Python that integrates normalizing-flow proposals with the parton-level event generator \Pepper. Helicity-conditioned coupling flows are trained...
Go to contribution page -
Rebecca Revelli (Heidelberg University)27/08/2026, 11:40Simulations & Generative Models
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...
Go to contribution page -
Javier Mariño Villadamigo (University of Heidelberg)27/08/2026, 11:50Simulations & Generative Models
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 rep-
Go to contribution page
resentative QCD processes, we achieve speed-up of... -
Gergely Gábor Barnaföldi (HUN-REN Wigner RCP)27/08/2026, 12:00Simulations & Generative Models
Hadronization is a non-perturbative process, which theoretical description can not be deduced from first principles. Modeling hadron formation requires several assumptions and various phenomenological approaches. Utilizing state-of-the-art Deep Learning algorithms, it is eventually possible to train neural networks to learn non-linear and non-perturbative features of the physical processes. In...
Go to contribution page