Application of a Mixture of Experts-based Foundation Model to the GlueX DIRC Detector

2026/04/17 by Cristiano Fanelli, James Giroux, Cole Granger +1 · 1 voice
Computer Science · Physics and Astronomy · #Benchmark (surveying) #Cherenkov radiation #Detector #Kinematics #Noise (video) #Particle Detector Development and Performance #Particle physics theoretical and experimental studies #Radiation Detection and Scintillator Technologies #Robustness (evolution) #cs.LG #hep-ex #nucl-ex #physics.data-an #physics.ins-det

paper · pdf · doi:10.48550/arxiv.2604.24775

openalex publication_date 2026/04/17 · arxiv published 2026/04/17 · arxiv updated 2026/04/17 · openalex created_date 2026/04/30 · openalex updated_date 2026/07/28

Abstract

We present a Mixture-of-Experts-based foundation model applied to the GlueX DIRC detector at Jefferson Lab, demonstrating its utility as a unified framework for fast simulation, particle identification, and hit-level noise filtering of Cherenkov photons. By leveraging a single shared transformer backbone across all tasks, the approach eliminates the fragmentation of task-specific pipelines while maintaining competitive-and in several cases superior-performance relative to established methods. The model operates directly on low-level detector inputs, performing hit-by-hit autoregressive generation over split spatial and temporal vocabularies with continuous kinematic conditioning, and supports class-conditional generation of pions and kaons through its Mixture-of-Experts architecture. We benchmark against the standard geometrical reconstruction and prior deep learning methods across the full kinematic phase space of the GlueX DIRC, demonstrating that the foundation model framework transfers effectively to this detector without architectural modification. This work positions the foundation model as a practical and scalable alternative to the suite of task-specific models currently proposed for GlueX DIRC analysis.

Citations

• Towards Foundation Models for Experimental Readout Systems Combining Discrete and Continuous Data
• Generative Models for Fast Simulation of Cherenkov Detectors at the Electron-Ion Collider
• HEP-JEPA: A foundation model for collider physics using joint embedding predictive architecture
• OmniJet-α_C: Learning point cloud calorimeter simulations using generative transformers
• Bumblebee: Foundation Model for Particle Physics Discovery
• Deep(er) Reconstruction of Imaging Cherenkov Detectors with Swin Transformers and Normalizing Flow Models
• Finetuning Foundation Models for Joint Analysis Optimization
• Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models
• On Layer Normalization in the Transformer Architecture
• Scaling Laws for Neural Language Models
• Normalizing Flows for Probabilistic Modeling and Inference
• Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
• Gaussian Error Linear Units (GELUs)
• The GlueX DIRC Project
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

Discussions

• Cristiano Fanelli, James Giroux, Cole Granger, Justin Stevens: Application of a Mixture of Experts-based Foundation Model to the GlueX DIRC Detector https://arxiv.org/abs/2604.24775 https://arxiv.org/ [bsky, 0 points, 0 comments]

Related

• Towards Foundation Models for Experimental Readout Systems Combining Discrete and Continuous Data
• Generative Models for Fast Simulation of Cherenkov Detectors at the Electron-Ion Collider
• Installation and Commissioning of the GlueX DIRC
• Deep(er) Reconstruction of Imaging Cherenkov Detectors with Swin Transformers and Normalizing Flow Models
• Particle identification in the GlueX detector with machine learning