arXiv subjects

Huilin Qu

Publications and source records attributed to Huilin Qu.

At least 19 recordsLinked to original sources

arXiv2026

Virtues and Vices of Equivariant Transformers

We study for the first time the benefit of Lorentz-equivariant transformers for large-size jet tagging and flavor tagging. To control their computing demands, we optimize all implementations for inference cost metrics. In our scaling studies, we find that Lorentz-equivariant networks outperform standard transformers, provided geometric features are relevant. This holds true in an idealized world as well as for limited resources. The conditional gain from Lorentz equivariance provides interesting input to the development of foundation models for LHC data.

hep-ph↗

arXiv2026

CaloTrilogy: Toward a Breakthrough in One-Step, End-to-End, Physics-Guided Shower Generation for Modern Calorimeters

High-precision calorimeter simulation at current and future colliders imposes rapidly growing computational demands, motivating the development of machine-learning surrogates for traditional Monte Carlo tools such as Geant4. Flow matching and diffusion-based generative models have become leading approaches for high-dimensional fast simulation because of their sample quality, but typically require ${\cal O}(100)$ function evaluations at inference and often rely on auxiliary networks to constrain global observables, compromising streamlined end-to-end generation. We introduce a unified framework that improves the balance between speed, shower quality, and physics fidelity. The method combines: (i) an average velocity field integrator that enables sampling in one or a few evaluations; (ii) a learned generative prior in shower space, constructed from data rather than random noise; and (iii) physics-guided loss terms that impose inductive biases on key observables during training. These elements are training time regularizers, preserving end-to-end inference with no additional cost. With only one or a few evaluation steps, the model achieves shower quality competitive with state-of-the-art flow and diffusion approaches, tested on several public high granularity calorimeter datasets. The results demonstrate inter-layer shower structure consistent with the underlying physics, providing a strong candidate for future fast simulation workflows.

hep-ex↗

arXiv2026

Learning from all particles in high-energy collisions

Particle colliders stand as an irreplaceable pillar of inquiry for exploring the fundamental building blocks of matter and forces of the Universe, yet fully decoding complex collision event information remains a significant challenge. Recent advances in artificial intelligence (AI) have revolutionized complex data analysis across scientific disciplines, inspiring novel strategies to extract the rich information embedded in collider events. Here we introduce two complementary concepts -- the holistic approach and Advanced Color Singlet Identification -- to enhance signal-background separation, which is a critical prerequisite for precise physics measurements. By leveraging all reconstructed particles and inferring their parentage via deep learning, these methods improve the precision of key Higgs physics benchmark measurements by up to sixfold and enable realistic prospects for observing rare Higgs decays previously deemed inaccessible. Our results demonstrate how integrating particle-level information with modern AI technologies can substantially boost the discovery potential of high-energy colliders, paving a new path to unravel the fundamental physical laws underlying particle physics experiments.

hep-ex↗

arXiv2025

CaloChallenge 2022: A Community Challenge for Fast Calorimeter Simulation

We present the results of the "Fast Calorimeter Simulation Challenge 2022" - the CaloChallenge. We study state-of-the-art generative models on four calorimeter shower datasets of increasing dimensionality, ranging from a few hundred voxels to a few tens of thousand voxels. The 31 individual submissions span a wide range of current popular generative architectures, including Variational AutoEncoders (VAEs), Generative Adversarial Networks (GANs), Normalizing Flows, Diffusion models, and models based on Conditional Flow Matching. We compare all submissions in terms of quality of generated calorimeter showers, as well as shower generation time and model size. To assess the quality we use a broad range of different metrics including differences in 1-dimensional histograms of observables, KPD/FPD scores, AUCs of binary classifiers, and the log-posterior of a multiclass classifier. The results of the CaloChallenge provide the most complete and comprehensive survey of cutting-edge approaches to calorimeter fast simulation to date. In addition, our work provides a uniquely detailed perspective on the important problem of how to evaluate generative models. As such, the results presented here should be applicable for other domains that use generative AI and require fast and faithful generation of samples in a large phase space.

physics.ins-det↗

arXiv2025

Lorentz-Equivariance without Limitations

Lorentz Local Canonicalization (LLoCa) ensures exact Lorentz-equivariance for arbitrary neural networks with minimal computational overhead. For the LHC, it equivariantly predicts local reference frames for each particle and propagates any-order tensorial information between them. We apply it to graph networks and transformers. We showcase its cutting-edge performance on amplitude regression, end-to-end event generation, and jet tagging. For jet tagging, we introduce a large top tagging dataset to benchmark LLoCa versions of a range of established benchmark architectures and highlight the importance of symmetry breaking.

hep-ph↗

arXiv2025

LDMX -- The Light Dark Matter eXperiment

The Light Dark Matter eXperiment (LDMX) is an electron fixed-target experiment optimized to search for sub-GeV dark matter production through the missing momentum signature. LDMX is designed to operate in End Station A at SLAC, using an 8 GeV electron beam accelerated alongside the LCLS-II drive beam. The design of the apparatus is strongly motivated by the performance requirements of a high-rate missing momentum search and leverages detector technologies and designs from other experiments along with existing facilities at SLAC. LDMX will improve on previous results by up to three orders of magnitude, enabling broad sensitivity to dark sector scenarios including the dark matter interaction strengths motivated by freeze-out of MeV-GeV mass dark matter to the observed relic abundance. With hermetic forward coverage, LDMX also has sensitivity to visible signatures of dark sectors and provides a unique probe of electron-nuclear interactions important to interpreting data from accelerator-based neutrino experiments. This report encompasses the technical design of the LDMX Detector, its simulated performance, and the physics capabilities of the experiment.

hep-ex↗

arXiv2025

A Lorentz-Equivariant Transformer for All of the LHC

We show that the Lorentz-Equivariant Geometric Algebra Transformer (L-GATr) yields state-of-the-art performance for a wide range of machine learning tasks at the Large Hadron Collider. L-GATr represents data in a geometric algebra over space-time and is equivariant under Lorentz transformations. The underlying architecture is a versatile and scalable transformer, which is able to break symmetries if needed. We demonstrate the power of L-GATr for amplitude regression and jet classification, and then benchmark it as the first Lorentz-equivariant generative network. For all three LHC tasks, we find significant improvements over previous architectures.

hep-ph↗

arXiv2025

One-to-one correspondence reconstruction at the electron-positron Higgs factory

We propose one-to-one correspondence reconstruction for electron-positron Higgs factories. For each visible particle, one-to-one correspondence aims to associate relevant detector hits with only one reconstructed particle and accurately identify its species. To achieve this goal, we develop a novel detector concept featuring 5-dimensional calorimetry that provides spatial, energy, and time measurements for each hit, and a reconstruction framework that combines state-of-the-art particle flow and artificial intelligence algorithms. In the benchmark process of Higgs to di-jets, over 90% of visible energy can be successfully mapped into well-reconstructed particles that not only maintain a one-to-one correspondence relationship but also associate with the correct combination of cluster and track, improving the invariant mass resolution of hadronically decayed Higgs bosons by 25%. Performing simultaneous identification on these well-reconstructed particles, we observe efficiencies of 97% to nearly 100% for charged particles ($e^{\pm}$, $μ^{\pm}$, $π^{\pm}$, $K^{\pm}$, $p/\bar{p}$) and photons ($γ$), and 75% to 80% for neutral hadrons ($K_L^0$, $n$, $\bar{n}$). For physics measurements of Higgs to invisible and exotic decays, golden channels to probe new physics, one-to-one correspondence could enhance discovery power by 10% to up to a factor of two. This study demonstrates the necessity and feasibility of one-to-one correspondence reconstruction at electron-positron Higgs factories.

hep-ex↗

arXiv2025

Choose Your Diffusion: Efficient and flexible ways to accelerate the diffusion model in fast high energy physics simulation

The diffusion model has demonstrated promising results in image generation, recently becoming mainstream and representing a notable advancement for many generative modeling tasks. Prior applications of the diffusion model for both fast event and detector simulation in high energy physics have shown exceptional performance, providing a viable solution to generate sufficient statistics within a constrained computational budget in preparation for the High Luminosity LHC. However, many of these applications suffer from slow generation with large sampling steps and face challenges in finding the optimal balance between sample quality and speed. The study focuses on the latest benchmark developments in efficient ODE/SDE-based samplers, schedulers, and fast convergence training techniques. We test on the public CaloChallenge and JetNet datasets with the designs implemented on the existing architecture, the performance of the generated classes surpass previous models, achieving significant speedup via various evaluation metrics.

physics.ins-det↗

arXiv2024

Jet Tagging with More-Interaction Particle Transformer

In this study, we introduce the More-Interaction Particle Transformer (MIParT), a novel deep learning neural network designed for jet tagging. This framework incorporates our own design, the More-Interaction Attention (MIA) mechanism, which increases the dimensionality of particle interaction embeddings. We tested MIParT using the top tagging and quark-gluon datasets. Our results show that MIParT not only matches the accuracy and AUC of LorentzNet and a series of Lorentz-equivariant methods, but also significantly outperforms the ParT model in background rejection. Specifically, it improves background rejection by approximately 25% at a 30% signal efficiency on the top tagging dataset and by 3% on the quark-gluon dataset. Additionally, MIParT requires only 30% of the parameters and 53% of the computational complexity needed by ParT, proving that high performance can be achieved with reduced model complexity. For very large datasets, we double the dimension of particle embeddings, referring to this variant as MIParT-Large (MIParT-L). We find that MIParT-L can further capitalize on the knowledge from large datasets. From a model pre-trained on the 100M JetClass dataset, the background rejection performance of the fine-tuned MIParT-L improved by 39% on the top tagging dataset and by 6% on the quark-gluon dataset, surpassing that of the fine-tuned ParT. Specifically, the background rejection of fine-tuned MIParT-L improved by an additional 2% compared to the fine-tuned ParT. The results suggest that MIParT has the potential to advance efficiency benchmarks for jet tagging and event identification in particle physics. The code is available at the following GitHub repository: https://github.com/USST-HEP/MIParT

hep-ph↗

arXiv2024

Jet-Origin Identification and Its Application at an Electron-Positron Higgs Factory

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 5 quark species $(b,c,s,u,d)$, 5 anti-quarks $(\bar{b},\bar{c},\bar{s},\bar{u},\bar{d})$, and the gluon. Using state-of-the-art algorithms and simulated $ν\barνH, H\rightarrow jj$ events at 240 GeV center-of-mass energy at the electron-positron Higgs factory, the jet origin identification simultaneously reaches jet flavor tagging efficiencies ranging from 67% to 92% for bottom, charm, and strange quarks, and jet charge flip rates of 7% to 24% for all quark species. We apply the jet origin identification to Higgs rare and exotic decay measurements at the nominal luminosity of the Circular Electron Positron Collider (CEPC), and conclude that the upper limits on the branching ratios of $H\rightarrow s \bar{s}, u\bar{u}, d\bar{d}$, and $H\rightarrow sb, db, uc, ds$ can be determined to $2\!\!\times\!\!10^{-4}$ to $1\!\!\times\!\!10^{-3}$ at 95% confidence level. The derived upper limit for $H\rightarrow s \bar{s}$ decay is approximately three times the prediction of the Standard Model.

hep-ex↗

arXiv2024

Accelerating Resonance Searches via Signature-Oriented Pre-training

The search for heavy resonances beyond the Standard Model (BSM) is a key objective at the LHC. While the recent use of advanced deep neural networks for boosted-jet tagging significantly enhances the sensitivity of dedicated searches, it is limited to specific final states, leaving vast potential BSM phase space underexplored. We introduce a novel experimental method, Signature-Oriented Pre-training for Heavy-resonance ObservatioN (Sophon), which leverages deep learning to cover an extensive number of boosted final states. Pre-trained on the comprehensive JetClass-II dataset, the Sophon model learns intricate jet signatures, ensuring the optimal constructions of various jet tagging discriminates and enabling high-performance transfer learning capabilities. We show that the method can not only push widespread model-specific searches to their sensitivity frontier, but also greatly improve model-agnostic approaches, accelerating LHC resonance searches in a broad sense.

hep-ph↗

arXiv2024

BUFF: Boosted Decision Tree based Ultra-Fast Flow matching

Tabular data stands out as one of the most frequently encountered types in high energy physics. Unlike commonly homogeneous data such as pixelated images, simulating high-dimensional tabular data and accurately capturing their correlations are often quite challenging, even with the most advanced architectures. Based on the findings that tree-based models surpass the performance of deep learning models for tasks specific to tabular data, we adopt the very recent generative modeling class named conditional flow matching and employ different techniques to integrate the usage of Gradient Boosted Trees. The performances are evaluated for various tasks on different analysis level with several public datasets. We demonstrate the training and inference time of most high-level simulation tasks can achieve speedup by orders of magnitude. The application can be extended to low-level feature simulation and conditioned generations with competitive performance.

physics.ins-det↗

arXiv2024

Does Lorentz-symmetric design boost network performance in jet physics?

In the deep learning era, improving the neural network performance in jet physics is a rewarding task as it directly contributes to more accurate physics measurements at the LHC. Recent research has proposed various network designs in consideration of the full Lorentz symmetry, but its benefit is still not systematically asserted, given that there remain many successful networks without taking it into account. We conduct a detailed study on the Lorentz-symmetric design. We propose two generalized approaches for modifying a network - these methods are experimented on Particle Flow Network, ParticleNet, and LorentzNet, and exhibit a general performance gain. We also reveal that the notable improvement attributed to the "pairwise mass" feature in the network is due to its introduction of a structure that fully complies with Lorentz symmetry. We confirm that Lorentz-symmetry preservation serves as a strong inductive bias of jet physics, hence calling for attention to such general recipes in future network designs.

hep-ph↗

arXiv2024

Particle Transformer for Jet Tagging

Jet tagging is a critical yet challenging classification task in particle physics. While deep learning has transformed jet tagging and significantly improved performance, the lack of a large-scale public dataset impedes further enhancement. In this work, we present JetClass, a new comprehensive dataset for jet tagging. The JetClass dataset consists of 100 M jets, about two orders of magnitude larger than existing public datasets. A total of 10 types of jets are simulated, including several types unexplored for tagging so far. Based on the large dataset, we propose a new Transformer-based architecture for jet tagging, called Particle Transformer (ParT). By incorporating pairwise particle interactions in the attention mechanism, ParT achieves higher tagging performance than a plain Transformer and surpasses the previous state-of-the-art, ParticleNet, by a large margin. The pre-trained ParT models, once fine-tuned, also substantially enhance the performance on two widely adopted jet tagging benchmarks. The dataset, code and models are publicly available at https://github.com/jet-universe/particle_transformer.

hep-ph↗

arXiv2023

ParticleNet and its application on CEPC Jet Flavor Tagging

Identification of quark flavor is essential for collider experiments in high-energy physics, relying on the flavor tagging algorithm. In this study, using a full simulation of the Circular Electron Positron Collider (CEPC), we investigated the flavor tagging performance of two different algorithms: ParticleNet, originally developed at CMS, and LCFIPlus, the current flavor tagging algorithm employed at CEPC. Compared to LCFIPlus, ParticleNet significantly enhances flavor tagging performance, resulting in a significant improvement in benchmark measurement accuracy, i.e., a 36% improvement for $ν\barνH\to c\bar{c}$ measurement and a 75% improvement for $|V_{cb}|$ measurement via W boson decay when CEPC operates as a Higgs factory at the center-of-mass energy of 240 GeV and integrated luminosity of 5.6 $ab^{-1}$. We compared the performance of ParticleNet and LCFIPlus at different vertex detector configurations, observing that the inner radius is the most sensitive parameter, followed by material budget and spatial resolution.

hep-ex↗

arXiv2023

Optimal transport for a novel event description at hadron colliders

We propose a novel strategy for disentangling proton collisions at hadron colliders such as the LHC that considerably improves over the current state of the art. Employing a metric inspired by optimal transport problems as the cost function of a graph neural network, our algorithm is able to compare two particle collections with different noise levels and learns to flag particles originating from the main interaction amidst products from up to 200 simultaneous pileup collisions. We thereby sidestep the critical task of obtaining a ground truth by labeling particles and avoid arduous human annotation in favor of labels derived in situ through a self-supervised process. We demonstrate how our approach - which, unlike competing algorithms, is trivial to implement - improves the resolution in key objects used in precision measurements and searches alike and present large sensitivity gains in searching for exotic Higgs boson decays at the High-Luminosity LHC.

hep-ph↗

arXiv2022

An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging

Deep learning methods have been increasingly adopted to study jets in particle physics. Since symmetry-preserving behavior has been shown to be an important factor for improving the performance of deep learning in many applications, Lorentz group equivariance - a fundamental spacetime symmetry for elementary particles - has recently been incorporated into a deep learning model for jet tagging. However, the design is computationally costly due to the analytic construction of high-order tensors. In this article, we introduce LorentzNet, a new symmetry-preserving deep learning model for jet tagging. The message passing of LorentzNet relies on an efficient Minkowski dot product attention. Experiments on two representative jet tagging benchmarks show that LorentzNet achieves the best tagging performance and improves significantly over existing state-of-the-art algorithms. The preservation of Lorentz symmetry also greatly improves the efficiency and generalization power of the model, allowing LorentzNet to reach highly competitive performance when trained on only a few thousand jets. Code and models are available at \url{https://github.com/sdogsq/LorentzNet-release}.

hep-ph↗