Research

Papers

• E. Moreno et al., COLLIDE-2V - 750 Million Dual-View LHC Event Dataset for Low-Latency ML

  Proceedings of 28th Conference on Computing in High Energy and Nuclear Physics (CHEP 2026), Bangkok, Thailand (2026).

• T. Ourida at al., Real-Time Uncertainty Quantification for Jet Tagging Models on the Level-1 Trigger
• T. Ourida at al., Attention-Driven Context Enrichment for Stabilized Real-Time Jet Tagging

  Proceedings of 28th Conference on Computing in High Energy and Nuclear Physics (CHEP 2026), Bangkok, Thailand (2026).

• J. Gonski et al., Machine Learning on Heterogeneous, Edge, and Quantum Hardware for Particle Physics (ML-HEQUPP)

  White paper from Machine Learning for the Front End (ML4FE) Workshop (2025), submitted to PRX Intelligence.

• J.F. Schulte et al., hls4ml: A Flexible, Open-Source Platform for Deep Learning Acceleration on Reconfigurable Hardware, accepted by ACM Transactions on Reconfigurable Technology and Systems.

• Summers et al., Roadmap on fast machine learning for science, Mach. Learn.: Sci. Technol. 7 (2026) 021501.
• M.Barbone et al., Application of computational modelling to particle physics, Comput. Phys. Commun. Vol. 37 (2025), Iss. 5 : pp. 1358–1382.
• Z. Zheng et al., JetFormer: A Scalable and Efficient Transformer for Jet Tagging from Offline Analysis to FPGA Triggers
• L. Laatu et al., Sub-microsecond Transformers for Jet Tagging on FPGAs Machine Learning and the Physical Sciences Workshop, NeurIPS (2025).
• Z.Que et al., JEDI-linear: Fast and Efficient Graph Neural Networks for Jet Tagging on FPGAs.2025 International Conference on Field Programmable Technology (ICFPT), Shanghai, China

• P. Odagiu et al., Sets are All You Need: Ultrafast Jet Classification on FPGAs for HL-LHC, Machine Learning: Science and Technology (2024)
• C. Brown et al., Quantum Pathways for Charged Track Finding in High-Energy Collisions, Front. Artif. Intell. 7:1339785 (2024)
• M. Mieskolainen, HyperTrack: neural combinatorics for high energy physics, EPJ Web of Conferences 295, 09021 (2024)
• M. Barbone et al., Fast, high-quality pseudo random number generators for heterogeneous computing, EPJ Web of Conferences 295, 11010 (2024)
• M. Barbone et al., Embedded Continual Learning for HEP, EPJ Web of Conferences 295, 09014 (2024)
• C. Brown et al., The Deployment of Realtime ML in Changing Environments, EPJ Web of Conferences 295, 09037 (2024)
• M. Barbone et al., Acceleration of a Deep Neural Network for the Compact Muon Solenoid, EPJ Web of Conferences 295, 09002 (2024)
• F. Wojcicki et al., Accelerating Transformer Neural Networks on FPGAs for High Energy Physics Experiments, 2022 International Conference on Field-Programmable Technology (ICFPT).
• M. Barbone et al., GPU acceleration of Monte Carlo simulations: particle physics methods applied to medicine, ACAT 2022 Conference Proceedings.
• L. Borgna et al., Accelerating the DBSCAN clustering algorithm for low-latency primary vertex reconstruction, ACAT 2022 Conference Proceedings.
• Z. Que et al., LL-GNN: Low Latency Graph Neural Networks on FPGAs for Particle Detectors, ACM Trans. Embed. Comput. Syst. Vol. 23 Article 17 (2024)
• Z. Que et al., Optimizing Graph Neural Networks for Jet Tagging in Particle Physics on FPGAs, 32nd International Conference on Field-Programmable Logic and Applications (2022)
• L. Våge, Accelerated graph building for particle tracking graph neural nets, CTD 2022 Conference Proceedings.
• C. Brown et al., Track Finding and Neural Network-Based Primary Vertex Reconstruction with FPGAs for the Upgrade of the CMS Level-1 Trigger System, CTD 2022 Conference Proceedings.
• C. Brown et al., Neural Network-Based Primary Vertex Reconstruction with FPGAs for the Upgrade of the CMS Level-1 Trigger System, J. Phys.: Conf. Ser. 2438 012106 (2023)
• M. Barbone et al., Demonstration of FPGA Acceleration of Monte Carlo Simulation,J. Phys.: Conf. Ser. 2438 012023 (2023)

Talks & posters

• E. Moreno, COLLIDE-2V - 750 Million Dual-View LHC Event Dataset for Low-Latency ML, CHEP 2026
• T. Ourida Real-Time Uncertainty Quantification for Jet Tagging Models on the Level-1 Trigger, CHEP 2026
• T. Ourida Attention-Driven Context Enrichment for Stabilized Real-Time Jet Tagging, CHEP 2026
• L. Laatu, Sub-microsecond Transformers for Jet Tagging on FPGAs, NeurIPS (2025).
• Z. Que, JEDI-linear: Fast and Efficient Graph Neural Networks for Jet Tagging on FPGAs, ICFPT 2025
• L. Laatu, Low-latency Jet Tagging for HL-LHC Using Transformer Architectures, FastML 2025
• C. Sun, Low-Latency Resource-Efficient GNNs for Jet Tagging on FPGAs, FastML 2025
• L. Laatu, Evolution of the oneAPI backend for hls4ml, FastML 2025

• C. Brown, The Deployment of Realtime ML in Changing Environments CHEP 2023.
• M. Barbone, Fast, high-quality pseudo random number generators for heterogeneous computing CHEP 2023.
• M. Barbone, Embedded Continual Learning for HEP CHEP 2023.
• M. Barbone, Acceleration of a CMS DNN based Algorithm CHEP 2023.
• M. Mieskolainen, HyperTrack: neural combinatorics for high energy physics CHEP 2023.
• F. Wojcicki et al., Accelerating Transformer Neural Networks on FPGAs for High Energy Physics Experiments, FPT 2022.
• M. Barbone et al., GPU acceleration of Monte Carlo simulations: particle physics methods applied to medicine, ACAT 2022.
• L. Borgna et al., Accelerating the DBSCAN clustering algorithm for low-latency primary vertex reconstruction, ACAT 2022.
• C. Brown, Development of a DNN for Vertexing and Track to vertex association in the GTT, ML@L1 Trigger Workshop at the LPC, 2022.
• C. Brown et al., End-to-End Vertex Finding for the CMS Level-1 Trigger, Fast Machine Learning for Science Workshop 2022.
• Z. Que et al., Accelerating JEDI-net for jet tagging on FPGAs, Fast Machine Learning for Science Workshop 2022.
• B. Radburn-Smith et al., Deployment of ML in changing environments, Fast Machine Learning for Science Workshop 2022.
• Z. Que et al., Optimizing Graph Neural Networks for Jet Tagging in Particle Physics on FPGAs, Monthly Fast ML meeting.
• Z. Que et al., Optimizing Graph Neural Networks for Jet Tagging in Particle Physics on FPGAs, FPL 2022.
• L. Våge et al., Accelerated graph building for particle tracking graph neural nets, Connecting The Dots 2022.
• C. Brown et al., Track Finding and Neural Network-Based Primary Vertex Reconstruction with FPGAs for the Upgrade of the CMS Level-1 Trigger System, Connecting The Dots 2022.
• T. Ourida et al., FPGA acceleration of the CMS DNN based LLP Jet Algorithm for the LHC High-Luminosity upgrade, 5th Inter-experiment Machine Learning Workshop, CERN, 2022.
• A. Rose, Centre for High-Throughput Digital Electronics and Embedded Machine Learning, Towards the future of AI, Imperial College London, 2022.
• L. Borgna, Fast Primary Vertex and Track Reconstruction Methods, SwiftHEP Workshop 2022.
• M. Barbone et al., Simulations: A case study, SwiftHep/ExcaliburHep Workshop, 2021.
• L. Våge et al., Accelerating particle tracking for the HL-LHC, SwiftHep/ExcaliburHep Workshop 2021.
• M. Barbone et al., Demonstration of FPGA Acceleration of Monte Carlo Simulation, ACAT 2021.
• C. Brown et al., Neural network based primary vertex reconstruction with FPGAs for the upgrade of the CMS level-1 trigger system, ACAT 2021.
• M. Barbone, Demonstration of FPGA Acceleration of Monte Carlo Simulation, Geant4 simulation collaboration bi-weekly meeting, 2022.
• M. Barbone, FPGA Acceleration of Monte Carlo Simulation, HEP Software Foundation Detector Simulation Working Group, 2021.
• Que et al., JEDI-linear: Fast and Efficient Graph Neural Networks for Jet Tagging on FPGAs.
• 2025 International Conference on Field Programmable Technology (ICFPT), Shanghai, China

Code repositories

• Github Repository for Centre for Embedded Machine-learning and High-throughput Digital Electronics at Imperial College
• GNN-JEDInet-FPGA repository for HLS-based template for the GNN-based JEDI-net
• Repository for Multiple Scattering Monte Carlo code

Seminars & lectures

• Z. Que, Accelerating graph neural network for jet tagging using FPGAs, Compute Accelerator Forum, CERN.
• M. Barbone, Introduction to FPGA acceleration, CERN OpenLab Lecture Programme.
• A. Rose, Trigger and DAQ, UK Advanced Instrumentation Training 2022.
• M. Barbone, Introduction to FPGA acceleration, Compute Accelerator Forum, CERN.
• M. Barbone, Practical HPC, Flatiron Institute, New York.

Masters projects

• L. Rozanov, Fast Machine Learning for the CMS Level-1 Trigger, MSc thesis (Supervisor A. Tapper)
• S. Baccas, Accelerated Bayesian Cluster Analysis for Super Resolved Microscopy, (supervisors: A. Rose, P. French).
• Heterogeneous Hardware Solutions of neutrino algorithms (supervisors: E. Atkin, I. Xiotidis)
  • Track reconstruction of neutrino interactions within a High-Pressure Gas Argon TPC detector
  • Vertex finding in neutrino interactions in a High-Pressure Gas Argon TPC environment with CNNs
• Optimisation of spline evaluation for neutrino oscillation analysis with Intel OneAPI (supervisors: E. Atkin, I. Xiotidis)
• Tracking with Quantum Computers in High Energy Physics (supervisors: C. Brown, I. Xiotidis)
• Quantum Machine Learning for High Energy Physics (supervisor: B. Maier)
• Using Differentiable Programming for Experiment Optimization (supervisor: B. Maier)
• Machine learning-based Event Reconstruction for Future Highly Granular Detectors at the Large Hadron Collider (supervisors: R. Bainbridge, B. Maier)
• Computing students at undergraduate and MSc level through the Custom Computing Research Group (supervisor: W Luk)