EuCAIFCon 2026

Session

🔀 Explainability & Theory

24 Aug 2026, 16:00

1.404

Conveners

🔀 Explainability & Theory

• Gert Aarts (Universitaet Bielefeld)

🔀 Explainability & Theory

• Michael Krämer (RWTH Aachen University)

🔀 Explainability & Theory

• Christoph Weniger (GRAPPA, University of Amsterdam)

17. The Latent Information Geometry of Jet Classification

Rebecca Maria Kuntz (Zentrum für Astronomie der Universität Heidelberg, Astronomisches Rechen-Institut)

24/08/2026, 16:00

Explainability & Theory

Latent representations are an important theme in modern machine learning. Networks trained with a notion of locality encode task-specific similarity as closeness in the latent space. We analyze this latent information for a variational autoencoder with a classifier head using tools from differential geometry, specifically information geometry. Here, we explore the learned latent space using...

85. From Information Geometry to Jet Substructure: A Triality of Cumulant Tensors, Energy Correlators, and Hypergraphs

Aritra Bal (Karlsruhe Institute of Technology (KIT))

24/08/2026, 16:10

Explainability & Theory

Pairwise Fisher graphs capture local covariance information, but they cannot distinguish an irreducible multi-observable radiation pattern from a collection of ordinary pairwise correlations. We show that the higher Fisher tensors supply this missing structure. In a finite basis of binned EECs, ECFs, or EFPs, and in the natural exponential-family coordinates generated by that basis, the...

36. Generative Criticality in Large Language Model Temperature Scaling

Xingyu Guo (South China Normal Univeristy)

24/08/2026, 16:20

Explainability & Theory

We propose a statistical-field framework for text generated by large language models (LLMs), treating token embeddings as continuous spin variables on a one-dimensional chain. Defining a susceptibility from the connected two-point correlator and an order parameter from the ensemble-averaged embedding field, we vary the softmax temperature $T$ and observe a sharp susceptibility peak near a...

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

Yong Sheng Koay (Uppsala University)

24/08/2026, 16:30

Explainability & Theory

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...

62. StableWein: A Computational Tool for Bounded-From-Below Constraints in the Z2 x Z2-Symmetric Three-Higgs-Doublet Model

Darius Jurčiukonis (Vilnius University (LT))

24/08/2026, 16:50

Explainability & Theory

We consider a three-Higgs-doublet extension of the electroweak Standard Model invariant under a $Z_2 \times Z_2$ symmetry. Since necessary and sufficient bounded-from-below (BFB) conditions are not known for this model, we propose an approach based on increasingly stringent necessary conditions. This procedure is implemented in the Mathematica package StableWein, which allows the user to...

150. Validation, Calibration, and Explainability of Machine Learning Models - From Particle Physics to Eye-Disease Prognosis

Robert McNulty (University of Liverpool (GB))

24/08/2026, 17:00

Explainability & Theory

With the increasing volume and complexity of data, machine learning (ML) models are becoming indispensable tools for identifying patterns within structured datasets. However, as these models grow in complexity, it becomes challenging to determine whether they are truly learning meaningful relationships or capturing unintended artifacts. This lack of interpretability leads to mistrust,...

26. Explainable Fuzzy-AI Reasoning for Skin Radiation Risk Classification in Medical Physics Applications

Seyedeh Fatemeh Mirekhtiary (Near East University)

24/08/2026, 17:10

Explainability & Theory

Artificial intelligence methods are increasingly used in physics to support classification, prediction, uncertainty handling, and interpretable decision-making. In medical physics, radiation risk assessment often depends on multiple interacting parameters, including absorbed dose, exposure duration, source activity, irradiated skin area, radiation energy, source-to-skin distance, shielding...

29. Gravitational Duals from Equations of State: Large Hierarchies and False Vacua

Pau Solé Vilaró (ICC - Universitat de Barcelona)

26/08/2026, 16:00

Explainability & Theory

We investigate the reconstruction of holographic duals for strongly coupled quantum field theories in regimes characterized by large hierarchies and the presence of false vacua. Within the gauge/gravity duality, these features translate into non-trivial thermodynamic behaviour and exotic renormalization group flows, including skipping flows between non-adjacent fixed points. Building on...

105. Physics-informed Renormalisation Group Flows

Friederike Ihssen (ITP Heidelberg)

26/08/2026, 16:10

Explainability & Theory

The renormalisation group considers general coarse-graining transformations in lattice systems and more broadly speaking field theories or data spaces and is based on an analytically known optimal transport equation.
This framework has a natural correspondence with modern generative architectures in terms of pooling and convolutions, but differs in terms of the non-linearity with corresponds...

42. Community Detection on Complex Networks through Transformer-based Message Passing and Denoising Diffusion

Edoardo Murano (Sapienza Università di Roma and INFN)

26/08/2026, 16:20

Explainability & Theory

Partitioning a graph into communities is an NP-hard optimization problem with a natural statistical-physics formulation: the optimal partition is the ground state of an antiferromagnetic Potts model, with modularity playing the role of negative energy. Clustering on graph-structured data is a recurring task in fundamental physics, where detector and event data are naturally represented as...

176. A graph-bandwidth law for context windows in autoregressive samplers

Tae-Geun Kim (Fudan U. / RIKEN)

26/08/2026, 16:30

Explainability & Theory

An autoregressive neural sampler writes a lattice configuration site by site, each site conditioned on the sites already written, and it returns independent samples with an exact likelihood. Each conditional sees only a context window of fixed reach, and nothing in the architecture says how far that reach has to extend.

Set the reach one unit short of what the target needs and the interior...

84. QUIVER: QUantum-Informed Views for Enhanced Representations in Large Machine Learning Models

Aritra Bal (Karlsruhe Institute of Technology (KIT))

26/08/2026, 16:50

Explainability & Theory

Large machine learning models benefit substantially from multimodal inputs that provide a complementary view of the same example. We introduce <span style="font-variant: small-caps;">Quiver</span> (QUantum-Informed Views for Enhanced Representations), a paradigm that enriches classical data-driven features...

39. ARQuAdia-Net: Learning Quantum Annealing Dynamics for 3-SAT

Lorenzo Colantonio (Sapienza Università di Roma and INFN)

26/08/2026, 17:00

Explainability & Theory

In recent years, approaches inspired by fundamental physics have played an important role in the development of modern machine learning algorithms, from energy based models to diffusion processes. Motivated by this perspective, we propose a hybrid quantum-classical learning framework inspired by adiabatic quantum dynamics and quantum annealing for solving constraint satisfaction problems.In...

79. tn4ml: Tensor Network Training and Customization for Machine Learning

Ema Puljak (CERN)

26/08/2026, 17:10

Explainability & Theory

Tensor Networks have emerged as a prominent alternative to neural networks for addressing machine learning challenges in foundational sciences, offering a bridge between quantum information techniques and classical learning algorithms. This transfer of methods from quantum information to machine learning has the potential to enhance model interpretability and efficiency, paving the way for...

127. Geometry of hidden feature spaces in Quantum Neural Networks

Vishal Ngairangbam (Karlsruhe Institute of Technology)

26/08/2026, 17:20

Explainability & Theory

Classical neural networks have rich feature learning capabilities where each functional composition has the ability to transform the hidden representations into non-isometric geometries. In quantum neural networks, however, depth or state reachability alone does not guarantee this feature-learning capability. We study this question in the pure-state setting by viewing encoded data as embedded...

31. Discovering Euler-Lagrange equations from trajectory data

Luca Wolf

27/08/2026, 14:00

Explainability & Theory

Neural ODEs enable the automatic discovery of a system's ordinary differential equations (ODEs) using only trajectory measurements. We combine this powerful and widely used machine learning method with the principle of stationary action from theoretical physics to learn only ODEs that are admissible as fundamental physical laws. To this end, we develop Helmholtz metrics, a machine learning...

181. Learning Relativistic Geodesics and Chaotic Dynamics via Stabilized Lagrangian Neural Networks

Abdullah Umut Hamzaogullari (Bogazici University)

27/08/2026, 14:10

Explainability & Theory

Lagrangian Neural Networks (LNNs) can learn arbitrary Lagrangians from trajectory data, but their unusual optimization objective leads to significant training instabilities that limit their application to complex systems. We propose several improvements that address these fundamental challenges, namely, a Hessian regularization scheme that penalizes unphysical signatures in the Lagrangian’s...

182. Recovering Irreducible Three-Body Interactions with Lagrangian Neural Networks

Sena Kalabalik

27/08/2026, 14:20

Explainability & Theory

Lagrangian Neural Networks (LNNs) learn mechanical systems directly from trajectory data by parameterizing a scalar Lagrangian and deriving the dynamics through the Euler-Lagrange equations, so that the learned model is strongly biased toward motion that respects the variational structure of mechanics. The interactions studied in this way have so far been pairwise-additive, leaving open...

179. Solving Schwarzschild Geodesic Motion with Lagrangian Neural Networks

Mr Sukru Caglar (Bogazici University)

27/08/2026, 14:30

Explainability & Theory

Lagrangian Neural Networks (LNNs) learn dynamics from trajectory data by parameterizing a scalar Lagrangian and deriving accelerations through the Euler–Lagrange equation, providing a variational inductive bias that improves physical consistency over purely data-driven models. LNNs have recently been extended to general relativistic settings, leaving Schwarzschild geodesics as an open...

180. Lagrangian Neural Networks with Simultaneously Learned Constraints

Abdullah Umut Hamzaogullari (Bogazici University)

27/08/2026, 14:50

Explainability & Theory

Lagrangian Neural Networks (LNNs) learn dynamical laws from trajectory data by representing a system’s Lagrangian with a neural network. In their standard formulation, however, LNNs are typically applied using carefully chosen generalized coordinates, such as angular coordinates for a pendulum, which already encode the system’s constraints and true degrees of freedom. Existing approaches...

16. Black Hole Spectroscopy via Physics-Informed Neural Networks: The Case of Massive Scalar Fields in Schwarzschild Spacetime

Prof. M. B. Cruz (State University of Paraiba)

27/08/2026, 15:00

Explainability & Theory

The detection of gravitational waves has turned the study of quasinormal modes (QNMs) into a fundamental tool for testing General Relativity. However, traditional numerical methods often face stability challenges when dealing with massive fields or high-order overtones. In this work, we present a robust computational framework based on Physics-Informed Neural Networks (PINNs) to solve the...

155. Neural Boltzmann Equations

Jonas Spinner (Durham University)

27/08/2026, 15:10

Explainability & Theory

The dynamics of particles in the early universe are described by Boltzmann equations, which involve high-dimensional phase space integrals. Classical approaches use quadrature integration and evolve the system on a fixed momentum grid, which scales poorly to high-dimensional integrals and parameter scans, severely limiting the complexity of processes that can be studied. We introduce Neural...