-
Rishab Kumar Jha18/08/2026, 13:35
Project Description: Built a proof-of-concept for centralized observability and distributed tracing across multiple Kubernetes clusters. Unified metrics, logs, and traces into a single Grafana dashboard where you can pick any cluster and service and correlate all three, including jumping from a latency spike straight to the exact trace. Designed a scalable parent/child OpenTelemetry...
Go to contribution page -
David Benko18/08/2026, 13:42
Project Description: Evaluate and benchmark Oracle SQLcl Model Contect Protocol (MCP) server performance and accuracy using open agentic models. Document installation and use of Oracle SQLcl MCP server for popular developer tools (e.g. VSCode). Implement automatically applied DB resource limits for database sessions identified as running an AI/MCP based client.
Supervisor: Andrzej...
Go to contribution page -
Jordie Biemold18/08/2026, 13:49
Project Description: The Hadoop infrastructure at CERN consists of many services (like HDFS, YARN, Spark, ZooKeeper) that all collect logging data in their own files. These services are used to store large amounts of data (from experiments and other sources) and process it efficiently. Before, the logs were located on each server individually, this made looking for (the source of) errors...
Go to contribution page -
Kilian Mahler18/08/2026, 13:56
Project Description:
The goal of this project is to evaluate and implement monitoring and alerting for Oracle databases using CERN’s centralized monitoring infrastructure, MONIT, together with the Oracle Database Metrics Exporter.Supervisor: Abel Cabezas Alonso, Miroslav Potocky
Go to contribution page -
Yucheng Zhang18/08/2026, 14:03
Project Description:
Go to contribution page
This project investigates whether PEPPER can safely use reduced floating-point precision to accelerate parton-level event generation on modern CPUs and GPUs. By comparing FP32 and FP64 calculations with CADNA, it identifies where rounding errors affect matrix elements and event weights, supporting the development of a reliable mixed-precision approach for HL-LHC... -
Aditya Tandon18/08/2026, 14:10
Project Description: The main aim of this project was to identify suitable platforms for doing Tensor Network simulations of entangled quantum systems and to leverage massively parallel GPUs to speed them up.
For this purpose, benchmarking against existing thesis codes and libraries must be performed before testing the simulations on research systems.Supervisor: Dr...
Go to contribution page -
Ayaan Aziz Dewani18/08/2026, 14:17
Project Description:
Go to contribution page
Modern high-energy physics experiments such as CMS increasingly rely on heterogeneous computing architectures combining CPUs, GPUs, and high-performance storage systems. While GPU acceleration has significantly improved compute throughput, I/O and data movement between storage, host memory, and device memory remain a critical bottleneck. GPUDirect Storage (GDS) is a... -
Ayoub Agouzoul18/08/2026, 14:24
-
Abbas Naim18/08/2026, 14:31
-
Emilly Rodrigues (CERN)18/08/2026, 14:38
Project Description:
Go to contribution page
The project studies a compact machine-learning model for reconstructing jets directly from six-layer ATLAS calorimeter images. The target environment is the FPGA-based Global Event Processor of the Phase-II Global Trigger, where the reconstruction must preserve the physically relevant jet information while using a small model. The work therefore evaluates... -
Karla Lucic (CERN)18/08/2026, 14:45
Project Description: An attention-based graph neural network that filters muon-segment pairs before track seeding in the ATLAS Phase-II reconstruction, validated end to end in ATHENA.
Supervisor: Davide Di Croce, Johannes Junggeburth
Go to contribution page -
Maksymilian Artur Moskwytyn (CERN)18/08/2026, 15:14
Project Description: This project develops a reproducible, hardware-aware MLOps pipeline for optimizing neural-network models for LHC hardware triggers. It combines automated architecture and quantization search, experiment tracking, physics-level validation, and FPGA deployment, with a reusable workflow demonstrated on an MHA-based minimum-bias anomaly-detection use...
Go to contribution page -
Manfred Przemyslaw Gawlas (CERN)18/08/2026, 15:21
Project Description:
Go to contribution page
Muon reconstruction is a central component of the ATLAS physics program and a key contributor to the overall computational cost of event reconstruction. The muon spectrometer provides precision tracking in the outermost region of the detector, and muon segment fitting is a core step in the outside-in reconstruction chain. Our group has implemented a highly optimized... -
Sergio Estrada Paredes (CERN)18/08/2026, 15:28
Project Description:
Go to contribution page
This project focuses on optimising the ATLAS HL-LHC trigger menu for Higgs-pair production, targeting the HH -> bbτ(had)τ(lep) final state. The goal is to maximise the signal efficiency while maintaining the background rate within the available trigger budget. To achieve this, the muon and electron channels are optimised separately across the trigger chain. At... -
Shahd Abuhassan18/08/2026, 15:35
Project Description: Hls4ml is an open-source toolkit that converts trained machine-learning models into FPGA firmware using high-level synthesis, enabling ultra-low-latency inference for real-time applications such as LHC trigger systems. PandA/Bambu is an advanced open-source HLS framework that compiles C/C++ into optimized hardware designs and offers a rich set of optimization passes...
Go to contribution page -
Shaun Christopher Lee18/08/2026, 15:42
Project Description:
Machine learning models are widely used at CERN for a variety of tasks, including data analysis, pattern recognition, and anomaly detection. These models are often highly sophisticated in order to handle the complexity of the data they process. In addition, when deployed in real-time systems such as trigger pipelines, they must deliver extremely fast inference...
Go to contribution page -
Stylianos Kostakis (Aristotle University of Thessaloniki (GR))18/08/2026, 15:49
Project Description:
Go to contribution page
Machine learning is rapidly replacing heuristic-based algorithms across many domains, and ATLAS plans to make extensive use of ML in both its hardware and software triggers during the HL-LHC era. While mature optimization platforms exist for deploying ML in software, very few MLOps pipelines targeting custom FPGA-based electronics have been tested at scale. Within... -
Maximilian Spannring18/08/2026, 15:56
Project Description:
Go to contribution page
Accurate physics reconstruction of collision events at the LHC relies on precise knowledge of detector conditions at the moment an event is acquired. As these conditions fluctuate during data-taking, calibrations must be derived to account for them. Within the Next Generation Triggers (NGT) project, a novel approach is being tested to derive calibrations for online... -
Weronika Karolina Sobien18/08/2026, 16:03
Project Description:
The CMS experiment relies on rapid event reconstruction at the High-Level Trigger to select interesting proton–proton collisions in real time. For the upcoming Run 4, the Next Generation Trigger (NGT) scouting stream aims to record events at exceptionally high rates by utilizing dedicated fast reconstruction algorithms and reduced data formats. This presentation...
Go to contribution page -
Hannah Grace Havel18/08/2026, 16:10
Project Description:
With the start of the High Luminosity LHC era, or “phase-2,” the upgraded machine will provide unprecedented volumes of data at extreme energies and intensities. Extracting meaningful physics requires advanced data-analysis techniques and algorithms.Within the CMS experiment, we are developing an innovative online trigger system to handle the enormous data rates...
Go to contribution page -
Estefania Moreno Leon18/08/2026, 16:17
Project Description:
Go to contribution page
The objective is to use Machine Learning to derive optimal representations of LHC collision events that naturally cluster Standard Model processes while maximizing sensitivity to anomalous signatures beyond the Standard Model (BSM). The project will focus on applying state-of-the-art representation learning methods, including unsupervised (Autoencoder) and... -
12. Bi-Directional Isaac Sim and MuJoCo Bridge for 3D Digital Twin Powered LHC Robotic InterventionsOgulcan Gurelli (OpenLab)18/08/2026, 16:24
This project builds a live, bi-directional bridge between two robotics simulators, MuJoCo and NVIDIA Isaac Sim, to support robotic maintenance interventions inside a 3D digital twin of the LHC. MuJoCo acts as the single source of truth for physics, while Isaac Sim mirrors the simulation in real time, rendering it photorealistically inside CERN's actual accelerator geometry; control commands...
Go to contribution page -
Jeremi Machniewski18/08/2026, 16:31
-
18/08/2026, 17:00
Choose timezone
Your profile timezone: