Conveners
Jet Physics
- Philip Coleman Harris (Massachusetts Inst. of Technology (US))
Jet Physics
- Raghav Kansal (Caltech / Fermilab)
Jet Physics
- Daniel Whiteson (University of California Irvine (US))
Jet Physics
- Raghav Kansal (Caltech / Fermilab)
-
Leonardo Lima Da Silva (Universidade de Sao Paulo (USP) (BR)), Marcelo Gameiro Munhoz (Universidade de Sao Paulo (USP) (BR))8/18/25, 2:00 PM
This project investigates jet quenching phenomena observed in relativistic heavy-ion collisions by applying machine learning techniques to modifications in jet substructures resulting from interactions between jets and the quark-gluon plasma (QGP). A robust dataset is generated using the Jet Evolution With Energy Loss (JEWEL) framework, and the findings are compared with results obtained from...
Go to contribution page -
Dr Ahmed Hammad (KEK, Japan)8/18/25, 2:20 PM
I will introduce IAFormer, a novel Transformer-based architecture that efficiently integrates pairwise particle interactions through a dynamic
Go to contribution page
sparse attention mechanism. By leveraging sparsity, IAFormer dynamically prioritizes relevant particle tokens while reducing computational overhead associated with less informative ones. This approach significantly lowers the model complexity without... -
Zichun Hao (California Institute of Technology)8/18/25, 2:40 PM
In high-energy physics (HEP) experiments, jets are key concepts in physics analysis. While supervised learning approaches have demonstrated success in tasks such as jet classification and mass regression, they often require large amounts of labeled data and rely on the accuracy of computationally expensive simulations. Self-supervised learning (SSL) has shown promising results for developing...
Go to contribution page -
Raghav Kansal (Caltech / Fermilab)8/18/25, 3:00 PM
We present a novel deep neural network classifier, the ``particle transformer'', ParT, for identifying highly Lorentz-boosted, multi-pronged jets for measurements and searches with the CMS detector at the LHC. Based on a self-attention architecture, ParT is trained on a wide variety of topologies, notably demonstrating strong performance for the first time on boosted Higgs boson decays to...
Go to contribution page -
Ian Pang8/19/25, 2:00 PM
In recent years, foundation models for jet physics, often based on transformer architectures, have been increasingly applied to tasks such as jet classification, jet generation, and anomaly detection. Conditioning on high-level jet features (HLFs) is crucial for many of these tasks. However, pretraining on all possible HLFs is impractical due to their vast variety. To address this, we propose...
Go to contribution page -
Joschka Birk (Hamburg University (DE))8/19/25, 2:20 PM
Over the last few years, different pre-training strategies for foundation models in HEP have been proposed. Some of them, like generative pre-training (used in OmniJet-$\alpha$) and Masked Particle Modeling (MPM), rely on self-supervised pre-training, allowing models to be pre-trained on unlabelled data collected by experiments.
Go to contribution page
We present studies that compare those two self-supervised... -
Diptaparna Biswas (Universitaet Siegen (DE))8/19/25, 2:40 PM
Accurate identification of jets that originate from heavy-flavour hadrons is pivotal for many ATLAS analyses, from Higgs-boson and top-quark measurements to searches for new physics. We present GN3, the newest heavy-flavour tagger, which introduces a full-transformer architecture tailored to the environment of Run 2 and Run 3.
GN3 processes low-level track, vertex, neutral particle, and...
Go to contribution page -
Congqiao Li (Peking University (CN)), Dawei Fu (Peking University (CN))8/19/25, 3:00 PM
I will present recent advances in the development of inclusive, large-scale pretrained models for Lorentz-boosted jets at the LHC's general-purpose experiments. These models significantly enhance the LHC physics program by (1) extending the sensitivity reach of model-specific analyses, and (2) substantially improving model-agnostic strategies, thereby unlocking previously unreached physics...
Go to contribution page -
Edoardo Critelli (UCL (GB))8/20/25, 2:00 PM
Flavour tagging, the identification of jets originating from b- and c-quarks, is a critical component of the physics programme of the ATLAS experiment at the Large Hadron Collider. In recent years, ATLAS introduced new machine learning algorithms based on the transformer architecture, which use information from charged particle tracks within a jet to predict the jet flavour without the need...
Go to contribution page -
Yevgeny Kats (Ben-Gurion University)8/20/25, 2:20 PM
Many ML tools tackle the problem of jet tagging (or flavor tagging), namely determining what particle type gave rise to the jet. We point out that another task to which ML tools can be applied is "fragmentation tagging", which is a question about the hadronization process that occurred in a given jet. For example, one may ask whether a given b-jet contained a b-meson or a b-baryon. This can in...
Go to contribution page -
Rikab Gambhir (MIT)8/20/25, 2:40 PM
Jet tagging using information extracted from the kinematics of particles inside jets is a common task in high-energy collider physics. Often, event classifiers are designed by targeting the best performance in terms of accuracy, AUC, or similar metrics, and many classifiers have been developed that score high on these metrics by training on simulations such as PYTHIA. However, optimizing these...
Go to contribution page -
Chang Sun (California Institute of Technology (US))8/20/25, 3:00 PM
We explore the innovative use of MLP-Mixer models for real-time jet tagging and establish their feasibility on resource-constrained hardware like FPGAs. MLP-Mixers excel in processing sequences of jet constituents, achieving state-of-the-art performance on datasets mimicking Large Hadron Collider conditions. By using advanced optimization techniques such as High-Granularity Quantization and...
Go to contribution page -
Mr Jhoao Gabriel Martins Campos Almeida Arneiro (Universidade de Sao Paulo (USP) (BR))8/21/25, 11:20 AM
The use of neural networks in high-energy physics has rapidly expanded, particularly in jet tagging applications. This study explores a convolutional neural network (CNN) based approach to classify jets produced in high-energy collisions by differentiating between heavy quark (charm, bottom), light quark (up, down, strange), and gluon jets. The method constructs image-like representations...
Go to contribution page -
Jai Bardhan8/21/25, 11:40 AM
We present HEP-JEPA, a transformer architecture-based foundation model for tasks at high-energy particle colliders such as the Large Hadron Collider. We pre-train the model on particle jets using a self-supervised strategy inspired by the Joint Embedding Predictive Architecture on the large-scale JetClass dataset containing 100M jets. We evaluate and compare HEP-JEPA to other foundation models...
Go to contribution page -
Ethan Lewis Simpson (The University of Manchester (GB))8/21/25, 12:00 PM
The Lund jet plane is a representation of the emissions within a jet, where each point corresponds to an emission. Hard and soft emissions, as well as colinear and wide-angle emissions, correspond to different regions of the Lund plane and are populated differently by jets with different origins. This means the Lund plane can be used for jet tagging.
Go to contribution page
We present previous studies done in ATLAS... -
João A. Gonçalves (LIP - IST)8/21/25, 12:20 PM
The phenomena of Jet Quenching, a key signature of the Quark-Gluon Plasma (QGP) formed in Heavy-Ion (HI) collisions, provides a window of insight into the properties of the primordial liquid. In this study, we evaluate the discriminating power of Energy Flow Networks (EFNs), enhanced with substructure observables, in distinguishing between jets stemming from proton-proton (pp) and jets...
Go to contribution page -
Ian Pang8/21/25, 12:40 PM
In this work, we explore two distinct jet generation approaches—continuous flow matching models and tokenized autoregressive models—to assess their effectiveness in precision generative modeling of jets. We examine the strengths and limitations of each approach, providing insights into how they inform the theoretical limits of jet tagging and the trade-offs between continuous and tokenized...
Go to contribution page