Related papers: Finetuning Foundation Models for Joint Analysis Op…
Training and Hyperparameter Optimization (HPO) of deep learning-based AI models are often compute resource intensive and calls for the use of large-scale distributed resources as well as scalable and resource efficient hyperparameter search…
At the extreme energies of the Large Hadron Collider, massive particles can be produced at such high velocities that their hadronic decays are collimated and the resulting jets overlap. Deducing whether the substructure of an observed jet…
Domain Incremental Learning is a critical scenario that requires models to continuously adapt to new data domains without retraining. However, domain shifts often cause severe performance degradation. To address this, we propose Hybrid…
In the design phase of an electrical machine, finite element (FE) simulation are commonly used to numerically optimize the performance. The output of the magneto-static FE simulation characterizes the electromagnetic behavior of the…
At the LHC, tagging boosted heavy particle resonances which decay hadronically, such as top quarks and Higgs bosons, can play an essential role in new physics searches. In events with high multiplicity, however, the standard approach to tag…
Adaptive mesh refinement is central to the efficient solution of partial differential equations (PDEs) via the finite element method (FEM). Classical $r$-adaptivity optimizes vertex positions but requires solving expensive auxiliary PDEs…
Foundation models have revolutionized artificial intelligence by providing robust, versatile architectures pre-trained on large-scale datasets. However, adapting these massive models to specific downstream tasks requires fine-tuning, which…
A new approach for efficiently exploring the configuration space and computing the free energy of large atomic and molecular systems is proposed, motivated by an analogy with reinforcement learning. There are two major components in this…
High-fidelity electron microscopy simulations required for quantitative crystal structure refinements face a fundamental challenge: while physical interactions are well-described theoretically, real-world experimental effects are…
Multidimensional efficiency maps are commonly used in high energy physics experiments to mitigate the limitations in the generation of large samples of simulated events. Binned multidimensional efficiency maps are however strongly limited…
Data from high-energy physics experiments are collected with significant financial and human effort and are mostly unique. However, until recently no coherent strategy existed for data preservation and re-use, and many important and complex…
We present a momentum-dependent reweighting strategy to extend current LHC di-Higgs analyses within the $\kappa$-framework and SMEFT into the bosonic sector of the Higgs Effective Field Theory (HEFT). Unlike SMEFT, where symmetry…
This work investigates how the traditional image classification pipelines can be extended into a deep architecture, inspired by recent successes of deep neural networks. We propose a deep boosting framework based on layer-by-layer joint…
The signal for a highly boosted heavy resonance competing against a background of light parton jets at the LHC can be enhanced by analyzing subjets in the "fat" jet that possibly contains the heavy resonance. Three methods for doing this…
Forward and inverse models are used throughout different engineering fields to predict and understand the behaviour of systems and to find parameters from a set of observations. These models use root-finding and minimisation techniques…
High $p_T$ Higgs production at hadron colliders provides a direct probe of the internal structure of the $gg \to H$ loop with the $H \to b\bar{b}$ decay offering the most statistics due to the large branching ratio. Despite the overwhelming…
Foundational Machine Learning Potentials can resolve the accuracy and transferability limitations of classical force fields. They enable microscopic insights into material behavior through Molecular Dynamics simulations, which can crucially…
Parameter-Efficient finetuning (PEFT) enhances model performance on downstream tasks by updating a minimal subset of parameters. Representation finetuning (ReFT) methods further improve efficiency by freezing model weights and optimizing…
As fine-tuning becomes impractical at scale, probing is emerging as the preferred evaluation protocol. However, standard linear probing can understate the capability of models whose pre-training optimizes local representations rather than…
The Higgs boson is thought to provide the interaction that imparts mass to the fundamental fermions, but while measurements at the Large Hadron Collider (LHC) are consistent with this hypothesis, current analysis techniques lack the…