US LUA annual meeting

Session

Lightning Round Talks

Dec 17, 2024, 2:00 PM

51/1-102 - Kavli Auditorium (SLAC)

34. A foundational model for particle physics discovery

AJ Wildridge (Purdue University)

12/17/24, 2:00 PM

35. Anomaly Detection and Stability Measurements with the CMS Pixel Luminosity Telescope

Katie Ream (University of Michigan)

12/17/24, 2:10 PM

Lighting talks

36. Automating ATLAS control room anomaly detection with deep learning

Avery Hanna (Tufts University)

12/17/24, 2:20 PM

Lighting talks

37. eFPGA-based ML Implementation on Future Collider Detector Readout

Kenny Jia (SLAC)

12/17/24, 2:30 PM

Lighting talks

38. Search for millicharged particles with the MilliQan experiment using Run 3 data

Sai Neha Santpur (University of California, Santa Barbara)

12/17/24, 2:40 PM

Lighting talks

39. Search for production at CMS Run 2 with each Higgs boson decaying to a b-quark pair

Wei Wei (University of California, Davis)

12/17/24, 2:50 PM

Lighting talks

40. A journey through module quality control of the ATLAS Inner Tracker pixel upgrade

Emily Thompson (Lawrence Berkeley National Lab)

12/17/24, 3:00 PM

Lighting talks

41. Real-time analysis in HLT1 at LHCb in Run 3

Kate Richardson (Massachusetts Institute of Technology)

12/17/24, 3:10 PM

Lighting talks

43. The BEST Searches for Vector-Like Quarks at CMS

Samantha Abbott (University of California, Davis)

12/18/24, 11:30 AM

Lighting talks

44. Harnessing Anomaly Detection Tools as Novel Analysis Resources for High Energy Physics

ROCKY GARG (SLAC)

12/18/24, 11:40 AM

Lighting talks

45. Transformer networks for constituent-based b-jet calibration with the ATLAS detector

Brendon Bullard (SLAC)

12/18/24, 11:50 AM

Lighting talks

46. Performance and production of the COLUTA ADC ASIC for the ATLAS HL-LHC Liquid Argon Calorimeter

Lauren Larson (The University of Texas at Austin)

12/18/24, 12:00 PM

Lighting talks

47. GPU-Accelerated Particle Tracking as-a-Service

Miles Cochran-Branson (University of Washington (UW))

12/18/24, 12:10 PM

Lighting talks

48. Glue, Cracking, and Interposers: The ATLAS Inner Tracker Upgrade

Aaron Petersen (Duke University)

12/18/24, 12:20 PM

Lighting talks

52. Standalone Barrel Electron/Photon Reconstruction Performance in the CMS Level-1 Phase-2 Calorimeter Trigger

Ashling Quinn (Princeton University CMS)

12/18/24, 1:40 PM

Lighting talks

53. Integration Testing of the Global Common Modules for the ATLAS Global Trigger

Timothy Mathew (University of Oregon)

12/18/24, 1:50 PM

Lighting talks

54. Using Unsupervised Machine Learning to Rediscover Standard Model Physics at CMS

Elliott Kauffman (Princeton University)

12/18/24, 2:00 PM

Lighting talks

55. Heavy-Flavour Jet Tagging Using Graph Neural Networks at LHCb

Gabriella Pesticci (Kenyon College)

12/18/24, 2:10 PM

Lighting talks

57. Primary Vertex identification using deep learning in the ATLAS Experiment

Qi Bin Lei (Stanford University)

12/18/24, 2:20 PM

Lighting talks

49. Waveform Sampling for Future Detector Timing Layers

Andrew Dowling (Syracuse University)

12/18/24, 2:30 PM

Lighting talks

69. A foundational model for particle physics discovery

AJ Wildridge (Purdue University)

Lighting talks

Bumblebee is a foundation model for particle physics discovery, inspired by BERT. By removing positional encodings and embedding particle 4-vectors, Bumblebee captures both generator- and reconstruction-level information while ensuring sequence-order invariance. Pre-trained on a masked task, it improves dileptonic top quark reconstruction resolution by 10-20% and excels in downstream tasks,...

65. A journey through module quality control of the ATLAS Inner Tracker pixel upgrade

Emily Thompson (Lawrence Berkeley National Lab)

Lighting talks

In the high-luminosity era of the Large Hadron Collider (HL-LHC), the instantaneous luminosity will reach unprecedented levels, with up to 200 proton-proton interactions in a typical bunch crossing. To meet the challenges posed by the HL-LHC environment, the ATLAS Inner Detector will be replaced with an all-silicon system known as the Inner Tracker (ITk). The innermost part of the ITk will...

24. Anomaly Detection and Stability Measurements with the CMS Pixel Luminosity Telescope

Katie Ream (University of Michigan)

Lighting talks

Data from the pixel luminosity telescope (PLT) for CMS needs to be cleaned thoroughly before being submitted for final integrated luminosity calculations for Run 3 data. Cleaning this data by hand is quite labor intensive, however very important to do so. In this talk I will discuss the anomaly detection algorithm I crafted to flag a variety of "anomalies" in the data - data points that need...

23. Automating ATLAS control room anomaly detection with deep learning

Avery Hanna (Tufts University)

Lighting talks

To ensure high-quality data acquisition at ATLAS, the detector status is monitored by a team of shifters in the control room where they watch plots of the incoming data and compare them with the expected standards. We propose the use of an online anomaly detection model to facilitate the detection of issues during data-taking and decrease the workload of the control room staff. Our model is a...

33. eFPGA-based ML Implementation on Future Collider Detector Readout

Haoyi Jia (Stanford University/SLAC National Accelerator Laboratory (US))

Lighting talks

Next generation high energy physics experiments face challenges with high data rates and stringent hardware constraints, driving the need for resources-efficient on-detector readout processing solutions. This work explores the novel application of embedded field programmable gate arrays (eFPGA) technology in detector readout systems. Leveraging eFPGA's unique combination of FPGA's...

31. Glue, Cracking, and Interposers: The ATLAS Inner Tracker Upgrade

Aaron Petersen (Duke University)

Lighting talks

The ATLAS Inner Tracker upgrade (ITk) is a silicon detector that will replace the existing Inner Detector in preparation for the HL-LHC. The subsystem of the ITk that I will be discussing is the ITk strips (more specifically ITk strips barrel) and the difficulties that have appeared in the past year of attempted production, such as module cracking. The ITk strips barrel subsystem is comprised...

68. GPU-Accelerated Particle Tracking as-a-Service

Miles Cochran-Branson (University of Washington (US))

Lighting talks

Particle tracking at Large Hadron Collider (LHC) experiments is a crucial component of particle reconstruction, yet it remains one of the most computationally challenging tasks in this process. As we approach the High-Luminosity LHC era, the complexity of tracking is expected to increase significantly. Leveraging coprocessors such as GPUs presents a promising solution to the rising...

26. Harnessing Anomaly Detection Tools as Novel Analysis Resources for High Energy Physics

ROCKY GARG (SLAC)

Lighting talks

In the realm of High-Energy Physics (HEP), the quest for new physics phenomena demands innovative approaches to data analysis. Anomaly detection (AD) tools, traditionally employed in fields such as cybersecurity and industrial quality control, are emerging as potent resources for uncovering rare and unexpected signals amidst vast datasets generated by particle colliders. By leveraging machine...

22. Heavy-Flavour Jet Tagging Using Graph Neural Networks at LHCb

Gabriella Pesticci (Kenyon College)

Lighting talks

Event reconstruction and particle analyses in high-energy physics (HEP) rely on effective jet-flavour tagging. This presentation introduces a novel b-jet classification method using Graph Neural Networks (GNNs), which are adept at capturing complex relationships in graph-structured data. This is the first application of a GNN b-jet tagger at LHCb, aimed to enhance jet flavour-tagging through...

29. Integration Testing of the Global Common Modules for the ATLAS Global Trigger

Timothy Mathew (University of Oregon)

Lighting talks

ATLAS is expected to receive 10 times the integrated luminosity from the High-Luminosity Large Hadron Collider (HL-LHC) than the previous three LHC runs combined, with approximately 200 interactions per bunch crossing, leading to significant pileup. The ATLAS Trigger and Data Acquisition system is undergoing significant upgrades to manage this pileup increase. As a part of these upgrades, the...

51. Lightning Round Introduction

67. Performance and production of the COLUTA ADC ASCI for the ATLAS HL-LHC Liquid Argon Calorimeter

Lauren Larson (The University of Texas at Austin)

Lighting talks

To handle the intense radiation at the High-Luminosity LHC, the ATLAS Liquid Argon Calorimeter readout electronics are being upgraded. The includes the production of custom ASICs, including the COLUTA chip—an 8-channel, 15-bit, 40 MSPS ADC.
The ADC meets and exceeds the specifications for the analog performance and the HL-LHC radiation tolerance. With 80,000 chips needed, robotic test stands...

62. Primary Vertex identification using deep learning in the ATLAS Experiment

Qi Bin Lei (Stanford University)

Lighting talks

The reconstruction of primary vertices will become significantly more challenging with the High Luminosity Large Hadron Collider (HL-LHC) upgrade, as the number of simultaneous collisions, or pileup, is expected to reach up to $<\mu>=200$. This high pileup places substantial computational demands on conventional combinatorics-based algorithms, resulting in significantly increased latency and...

32. Real-time analysis in HLT1 at LHCb in Run 3

Kate Richardson (Massachusetts Institute of Technology)

Lighting talks

The LHCb upgrade achieved for Run 3 includes a groundbreaking entirely software-based trigger. The removal of the hardware trigger is not only a significant technical advancement, but also enables substantial improvements in physics sensitivity. This presentation focuses on the performance of the first stage of the real-time analysis system (HLT1) running on GPUs. The flexibility provided by...

64. Search for $t\bar{t}HH$ production at CMS Run 2 with each Higgs boson decaying to a b-quark pair

Wei Wei (University of California, Davis)

Lighting talks

Precision measurements of Higgs boson couplings to Standard Model (SM) particles remain a central focus at the LHC and the upcoming HL-LHC. In particular, the interaction between the Higgs boson and the top quark is particularly compelling due to the large $\sim$ $O$(nb) $t\bar{t}$ cross section and $O(1)$ top-quark Yukawa coupling. The $t\bar{t}HH$ process offers a unique opportunity to probe...

66. Search for millicharged particles with the MilliQan experiment using Run 3 data

Sai Neha Santpur (University of California, Santa Barbara)

The milliQan experiment searches for milli-charged particles, with electric charge O(10$^{-3}$)e or less, produced in pp collisions at the LHC. The milliQan bar detector has collected ~141 fb$^{-1}$ of data during LHC Run 3 and this presentation will focus on the detector performance, study of beam muons to calibrate the detector and the search strategy. The talk will also focus on the newly...

30. Standalone Barrel Electron/Photon Reconstruction Performance in the CMS Level-1 Phase-2 Calorimeter Trigger

Ashling Quinn (Princeton University CMS)

Lighting talks

To mitigate high pileup conditions in the High-Luminosity Large Hadron Collider (HL-LHC), the Phase-2 upgrade to the Compact Muon Solenoid (CMS) detector will make use of tracking and high-granularity calorimeter information for the first time at the Level-1 Trigger. We focus on the barrel region (|η| < 1.5) of the electromagnetic calorimeter (ECAL) where the granularity of the ECAL barrel...

56. Studies into di-Tau mass reconstruction for high mass resonances at the ATLAS experiment

Kyle Granados (CERN)

Lighting talks

61. Studies into di-Tau mass reconstruction for high mass resonances at the ATLAS experiment

Kyle Granados (CERN)

Lighting talks

The invariant mass of particle resonances is a key analysis variable for LHC physics. For analyses with di-tau final states, the direct calculation of the invariant mass is impossible because tau decays always include neutrinos, which escape detection in LHC detectors. The Missing Mass Calculator (MMC) is an algorithm used by the ATLAS Experiment to calculate the invariant mass of resonances...

27. The BEST Searches for Vector Like Quarks at CMS

Samantha Abbott (University of California, Davis)

Lighting talks

The Boosted Event Shape Tagger is a multi-class jet tagger optimized for the diverse final states inherent to all-hadronic decays of Vector-Like Quarks. Its architecture is a simple DNN whose discriminating power benefits from physics-driven observables calculated in the lab frame, but also in a series of Lorentz-boosted frames aiming to provide the network with over/rest/under-boosted frame...

25. Transformer networks for constituent-based b-jet calibration with the ATLAS detector

Brendon Bullard (SLAC)

Lighting talks

The precise measurement of kinematic features of jets is key to the physics program of the LHC. The determination of the energy and mass of jets containing bottom quarks (𝑏-jets) is particularly difficult given their distinct radiation patterns and production of undetectable neutrinos via leptonic heavy flavor decays. This talk will describe a novel calibration technique for the b-jet...

50. Updated measurement prospects for di-Higgs production in the HH→bbγγ channel with the ATLAS experiment at the HL-LHC

Alex Wang (University of California, Santa Cruz)

Lighting talks

70. Updated measurement prospects for di-Higgs production in the HH→bbγγ channel with the ATLAS experiment at the HL-LHC

Alex Wang (University of California Santa Cruz)

Lighting talks

We present an updated prospect study on di-Higgs production in the HH→bbγγ decay channel with the ATLAS experiment at the High Luminosity LHC (HL-LHC). The latest projections are based on extrapolating the recent legacy Run 2 ATLAS search and improve over the previous results shown at Snowmass 2022. We describe in detail the extrapolation process and assumptions, and multiple scenarios for the...

28. Using Unsupervised Machine Learning to Rediscover Standard Model Physics at CMS

Elliott Kauffman (Princeton University)

Lighting talks

Despite extensive search efforts at the LHC, no clear evidence of physics beyond the Standard Model (BSM) has emerged. This raises the possibility that either new physics lies beyond the LHC’s reach or we are not searching in the right places. The CMS Level-1 Trigger (L1T) serves as the first step in selecting events for further analysis. If L1T algorithms fail to select events containing new...

42. Waveform Sampling for Future Detector Timing Layers

Andrew Dowling (Syracuse University)

Lighting talks

60. Waveform Sampling for Future Detector Timing Layers

Andrew Dowling (Syracuse University)

Lighting talks

Detectors in HL-LHC and future colliders such as the FCC will be subjected to large amounts of pileup due to increases in luminosity over LHC run 2. Disentangling pileup is critical for proper event reconstruction, thus the need arises for detectors with fine spatial granularity and picosecond level timing information. Both in-time pileup (multiple MIPs hitting the same cell during the same...