Application of a Mixture of Experts-based Foundation Model to the GlueX DIRC Detector
For the GlueX DIRC detector community, this work offers a scalable alternative to fragmented task-specific pipelines, though the application is domain-specific and incremental in nature.
The paper presents a Mixture-of-Experts-based foundation model for the GlueX DIRC detector that unifies fast simulation, particle identification, and noise filtering, achieving competitive or superior performance compared to task-specific methods across the full kinematic phase space.
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.