10/23/2026 Siv Schwink for Illinois Physics
Burleson’s research focuses on machine-learning methods for particle tracking at CERN’s Large Hadron Collider.
Written by Siv Schwink for Illinois Physics
Burleson’s research focuses on machine-learning methods for particle tracking at CERN’s Large Hadron Collider.
Illinois Physics graduate student Jared Burleson received the 2026 Outstanding Achievement Award of the ATLAS Experiment at CERN during a ceremony Thursday, October 15, at CERN. The 24 award recipients in this year’s cohort share this citation: “For four years of innovation in CPU-, GPU- and FPGA-based tracking, culminating in the December 2025 reports that enabled ATLAS’s Event Filter technology choice.”
The 2026 awards recognize outstanding contributions from December 2024 through December 2025 in detector operation, upgrades, software, computing, combined performance, and outreach.
Burleson works under the supervision of Illinois Physics Professor Mark Neubauer. Since joining Neubauer’s research group in fall 2022, Burleson has focused on developing machine-learning methods for the ATLAS experiment, one of the major particle physics experiments at CERN’s Large Hadron Collider (LHC).
His graduate research focuses on the ATLAS Phase-II Event Filter tracking upgrade, which aims to improve the speed and efficiency of reconstructing particle trajectories from collisions. As the LHC produces increasingly complex collision data, the computational demands of tracking particles through the ATLAS detector continue to grow, creating a need for faster, more efficient algorithms.
Burleson has led ATLAS development efforts applying graph neural networks (GNNs) to particle tracking. These machine-learning models represent detector hits as interconnected nodes and analyze their relationships to identify candidate particle tracks. Unlike conventional neural network architectures that rely on fixed-length inputs, GNNs can accommodate the variable number and spatial arrangement of detector hits, making them well-suited to particle-tracking applications.
GNNs offer opportunities to accelerate tracking on specialized computing hardware, including graphics processing units (GPUs) and field-programmable gate arrays (FPGAs). These technologies can help meet the demanding processing requirements of upgraded ATLAS systems for both online tracking during data collection and offline reconstruction.
As part of the broader ATLAS effort recognized by the award, Burleson has played a leading role in developing graph neural networks for Event Filter tracking. In recognition of his contributions to the upgrade, ATLAS Event Filter tracking coordinators invited him to serve as a co-editor of a report on FPGA-based tracking approaches submitted to the Technology Choice Committee in late 2025. He is also one of three ATLAS paper editors for an upcoming publication documenting the collaboration’s work on graph neural networks for Event Filter tracking.
“I am very proud of our team's ability to tackle the challenges of deploying machine learning algorithms on custom hardware, and I have learned so much about how machine learning is becoming a necessary tool for solving problems within our field,” Burleson said.
Neubauer commented, “Jared is an extremely bright and hard-working student who leads naturally through his work and enthusiasm for particle physics. He thrives in the challenging environment of a large experimental collaboration by proactively seeking out the right people to work with on a given problem, as well as seizing opportunities for mentoring more junior students.”
Beyond his research, Burleson participated in science advocacy trips to Washington, D.C., in 2025 and 2026 to advocate for federal funding for scientific research.
Before joining Illinois, Burleson completed a master’s degree in global affairs through the Schwarzman Scholars program at Tsinghua University in 2022. He earned bachelor’s degrees in physics and mathematics from Southern Methodist University in 2021.
After completing his Ph.D., Burleson hopes to continue working in high-energy particle physics as a postdoctoral researcher at a university or national laboratory. He plans to continue his work with CERN and pursue future collider research, with a focus on the role of machine learning in studying fundamental physics.