The particle-flow (PF) algorithm aims to provide a global event description for each collision in terms of the comprehensive list of final-state particles. It is of central importance to event reconstruction in the CMS experiment at the CERN LHC, and has been a focus of developments in light of planned high-luminosity running conditions with increased pileup and detector granularity. Existing...
The HL-LHC upgrade of the ATLAS inner detector (ITk) brings an unprecedented challenge, both in terms of the large number of silicon hit cluster readouts and the throughput required for budget-constrained track reconstruction. Applying Graph Neural Networks (GNNs) has been shown to be a promising solution to this problem with competitive physics performance at sub-second inference time. In...
The T2K experiment has recently started a dedicated AI/ML working group for its Near Detector (ND280) to coordinate and support machine learning applications across its physics program. This talk presents an overview of the current efforts and developments within the collaboration, highlighting how state-of-the-art machine learning techniques are being employed to improve event reconstruction,...
To enhance the scientific discovery power of high-energy collider experiments, we propose and realize the concept of jet-origin identification that categorizes jets into five quark species (u, d, s, c, b), five antiquarks, and the gluon. Using state-of-the-art algorithms and simulated ννH, H → jj events at 240 GeV center-of-mass energy at the electron-positron Higgs factory, the jet-origin...
Deep learning models are defined in terms of a large number of hyperparameters, such as network architectures and optimiser settings. These hyperparameters must be determined separately from the model parameters such as network weights, and are often fixed by ad-hoc methods or by manual inspection of the results. An algorithmic, objective determination of hyperparameters demands the...
Identification of hadronic jets originating from heavy-flavor quarks is essential to several physics analyses in High Energy Physics, such as studies of the properties of the top quark and the Higgs boson and searches for new physics. Recent algorithms used in the CMS experiment are developed using state-of-the-art machine-learning techniques to distinguish jets emerging from the decay of...
Hadronic object reconstruction & classification is one of the most promising settings for cutting-edge machine learning and artificial intelligence algorithms at the LHC. In this contribution, highlights of ML/AI applications by ATLAS to QCD and boosted-object identification, MET reconstruction and other tasks will be presented.
The increasing complexity of modern neural network architectures demands fast and memory-efficient implementations to mitigate computational bottlenecks. In this talk, we present a comprehensive evaluation of the recently proposed BITNET architecture across multiple HEP tasks, including quark-gluon discrimination, SMEFT parameter estimation, and detector simulation. We assess its performance...
Neural networks for LHC physics have to be accurate, reliable, and controlled. Using surrogate loop amplitudes as a use case, we first show how activation functions can be systematically tested with KANs. For reliability and control, we learn uncertainties together with the target amplitude over phase space. Systematic uncertainties can be learned by a heteroscedastic loss, but a comprehensive...
We present an extension of the Particle-flow Neural Assisted Simulations (Parnassus) framework to enable fast simulation and reconstruction of full collider events. Specifically, we employ two generative AI (genAI) approaches—conditional flow matching and diffusion models—to generate reconstructed particle-flow objects conditioned on stable truth-level particles from CMS Open Simulations....
Particle flow reconstruction algorithms lay the foundation for physics analysis at collider experiments. Enhancing these algorithms with deep learning offers a unique opportunity to improve experimental sensitivity at the LHC and future facilities. In this talk, we present HGPflow, a deep learning approach based on hypergraphs that provides a physics-motivated framework for the energy...
Identifying products of ultrarelativistic collisions delivered by the LHC and RHIC colliders is one of the crucial objectives of experiments such as ALICE and STAR, which are specifically designed for this task. They allow for a precise Particle Identification (PID) over a broad momentum range.
Traditionally, PID methods rely on hand-crafted selections, which compare the recorded signal of...
Machine Learning has enabled enormous gains in sensitivity at the LHC and beyond. Much of this progress has relied on excellent simulations of a wide range of processes. However, due to the sophistication of modern machine learning algorithms, discrepancies between simulation and experimental data can significantly limit their effectiveness.
In this work, we present a novel calibration...
With the increasing size of the machine learning (ML) model and vast datasets, the foundation model has transformed how we apply ML to solve real-world problems. Multimodal language models like chatGPT and Llama have expanded their capability to specialized tasks with common pre-train. Similarly, in high-energy physics (HEP), common tasks in the analysis face recurring challenges that demand...
A rising paradigm in AI in recent years is the foundation model, which refers to a model trained on broad data and adaptable to a wide range of downstream tasks. In this work, we present a new approach to learning powerful jet representations directly from unlabelled data. The method employs a Particle Transformer to predict masked particle representations in a latent space, overcoming the...
Advances in Machine Learning, particularly Large Language Models (LLMs), enable more efficient interaction with complex datasets through tokenization and next-token prediction strategies, providing a novel framework for analyzing high-energy physics datasets. This talk presents and compares various approaches to structuring particle physics data as token sequences, allowing LLM-inspired models...
This study presents an analysis of modern open-source large language models (LLMs)—including Llama, Qwen, and Gemma—to evaluate their encoded knowledge of Quantum Chromodynamics (QCD). Through reverse engineering of these models' representations, we uncover the naturally idiosyncratic patterns in how foundational QCD concepts are embedded within their parameter spaces. Our methodology combines...
