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

TL;DR

This paper introduces a Mixture-of-Experts foundation model for the GlueX DIRC detector that unifies multiple tasks like simulation and particle ID, outperforming traditional methods.

Contribution

It presents a single shared transformer-based model that handles various detector analysis tasks without task-specific pipelines, demonstrating superior performance.

Findings

Model achieves competitive or superior results compared to traditional methods.

Framework transfers effectively across the full kinematic phase space.

Supports class-conditional generation of pions and kaons.

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.