Learning Standard Model structure from LHC data with Riemannian flow matching

• URL: http://arxiv.org/abs/2607.16144v1
• Date: Fri, 17 Jul 2026 17:23:22 GMT
• Title: Learning Standard Model structure from LHC data with Riemannian flow matching
• Abstract summary: We show that a single transformer-based generative model can capture Standard Model structure spanning five decades of invariant mass.<n>The model is trained on $sim 109$ real $pp$ collision events from the ATLAS Open Data 13TeV release.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work we demonstrate that a single transformer-based generative model can capture Standard Model structure spanning five decades of invariant mass, from the sub-GeV regime to the TeV continuum, a range that no single Monte Carlo sample covers. To achieve this we design \textsc{ShellFlow}, a Riemannian conditional flow matching model that, given the recorded event composition, generates each particle on its on-shell manifold. Its only physics priors are the on-shell condition and the invariant-mass formula. The model is trained on $\sim 10^{9}$ real $pp$ collision events from the ATLAS Open Data 13~TeV release and told nothing else. From a single training run, the model learns to reproduce all of the following: intra-particle kinematics, the dilepton resonances ($J/ψ$, $Υ$, $Z$) at their PDG positions, the leptonic Weinberg angle, the $W$ and top-quark masses, and inter-particle correlations that enter no training objective. A substantial fraction of the Standard Model is thus learnable directly from recorded collision data.

Related papers

• Non-Markovian Poissonian Spontaneous Collapse Models [0.0]
  Spontaneous collapse models provide a possible solution to the measurement problem by modifying standard quantum dynamics.<n>We investigate a non-Markovian version of the Poissonian Spontaneous Localization (PSL) model.<n>We show how $_t$ can be made equal to that obtained by non-Markovian CSL models.
  arXiv  Detail & Related papers  (2026-07-09T21:28:38Z)
• Embedded Random Matrix Ensembles to Statistical Shell Model: Operation of $q$-normal forms [0.0]
  Embedded random matrix ensembles operating in nuclear shell model spaces form the basis for statistical shell model.<n>In practice, partitioning via spherical configurations ($tildem$) and angular momentum $J$ are essential.<n>Also described is the role of the $q$ parameter in generating statistical properties of general quantum many-particle systems.
  arXiv  Detail & Related papers  (2026-06-28T05:25:29Z)
• Inverting the Bellman Equation: From $Q$-Values to World Models [57.827849584133425]
  We prove that value-based agents trained on a sufficiently rich set of reward functions implicitly encode a unique and accurate world model.<n>We find that policies trained exclusively on a ttReacher agent's implicit world model are quasi-optimal on out-of-distribution, velocity-based goals despite position-only training.
  arXiv  Detail & Related papers  (2026-06-19T07:26:14Z)
• Cross-Domain Transfer with Particle Physics Foundation Models: From Jets to Neutrino Interactions [0.4062071796326536]
  Future AI-based studies in particle physics will likely start from a foundation model to accelerate training and enhance sensitivity.<n>We investigate whether the OmniLearned foundation model pre-trained on diverse high-$Q2$ simulated and real collisions can be effectively transferred to a few-GeV fixed-target neutrino experiment.
  arXiv  Detail & Related papers  (2026-04-14T06:53:22Z)
• Multi-Subspace Multi-Modal Modeling for Diffusion Models: Estimation, Convergence and Mixture of Experts [15.571607959541913]
  We propose the mixture subspace of low-rank mixture of Gaussian (MoLR-MoG) modeling, which models the target data as a union of $K$ linear subspaces.<n>With this modeling, the corresponding score function naturally has a mixture of expert (MoE) structure, captures the multi-modal information, and contains nonlinear property.<n>We show that MoE-latent MoG NN achieves a comparable performance with MoE-latent Unet with $10 times$ parameters.
  arXiv  Detail & Related papers  (2026-01-04T10:45:06Z)
• Delta-learned force fields for nonbonded interactions: Addressing the strength mismatch between covalent-nonbonded interaction for global models [0.0]
  We introduce textit$Delta$-sGDML, a scale-aware formulation that decouples intra- and intermolecular physics by training fragment-specific models and composing them at inference.<n>We show that textit$Delta$-sGDML delivers consistent gains over a single global model, with fragment-resolved force-error reductions up to textbf75%, without loss of energy accuracy.
  arXiv  Detail & Related papers  (2025-11-01T06:15:05Z)
• SE(3)-Stochastic Flow Matching for Protein Backbone Generation [54.951832422425454]
  We introduce FoldFlow, a series of novel generative models of increasing modeling power based on the flow-matching paradigm over $3mathrmD$ rigid motions. Our family of FoldFlowgenerative models offers several advantages over previous approaches to the generative modeling of proteins.
  arXiv  Detail & Related papers  (2023-10-03T19:24:24Z)
• Tangent Model Composition for Ensembling and Continual Fine-tuning [69.92177580782929]
  Tangent Model Composition (TMC) is a method to combine component models independently fine-tuned around a pre-trained point. TMC improves accuracy by 4.2% compared to ensembling non-linearly fine-tuned models.
  arXiv  Detail & Related papers  (2023-07-16T17:45:33Z)
• Neural Inference of Gaussian Processes for Time Series Data of Quasars [72.79083473275742]
  We introduce a new model that enables it to describe quasar spectra completely. We also introduce a new method of inference of Gaussian process parameters, which we call $textitNeural Inference$. The combination of both the CDRW model and Neural Inference significantly outperforms the baseline DRW and MLE.
  arXiv  Detail & Related papers  (2022-11-17T13:01:26Z)
• Neural Implicit Manifold Learning for Topology-Aware Density Estimation [15.878635603835063]
  Current generative models learn $mathcalM$ by mapping an $m$-dimensional latent variable through a neural network. We show that our model can learn manifold-supported distributions with complex topologies more accurately than pushforward models.
  arXiv  Detail & Related papers  (2022-06-22T18:00:00Z)
• Exploring Sparse Expert Models and Beyond [51.90860155810848]
  Mixture-of-Experts (MoE) models can achieve promising results with outrageous large amount of parameters but constant computation cost. We propose a simple method called expert prototyping that splits experts into different prototypes and applies $k$ top-$1$ routing. This strategy improves the model quality but maintains constant computational costs, and our further exploration on extremely large-scale models reflects that it is more effective in training larger models.
  arXiv  Detail & Related papers  (2021-05-31T16:12:44Z)
• Generative Temporal Difference Learning for Infinite-Horizon Prediction [101.59882753763888]
  We introduce the $gamma$-model, a predictive model of environment dynamics with an infinite probabilistic horizon. We discuss how its training reflects an inescapable tradeoff between training-time and testing-time compounding errors.
  arXiv  Detail & Related papers  (2020-10-27T17:54:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.