# GPT-Based Fast Simulation of CLAS12 Detector Hits via Conditional Autoregressive Generation

arXiv: https://arxiv.org/abs/2606.16035 · HTML: https://mlsanity.com/paper/2606.16035/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 50 references that are in the map.
- First posted on arXiv 14 Jun 2026.

## Builds on (most cited first, 22 of 22)

- [A Living Review of Machine Learning for Particle Physics](https://mlsanity.com/paper/2102.02770/) (2021)
- [Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multi-Layer Calorimeters](https://mlsanity.com/paper/1705.02355/) (2017)
- [Score-based Generative Models for Calorimeter Shower Simulation](https://mlsanity.com/paper/2206.11898/) (2022)
- [Calorimetry with Deep Learning: Particle Simulation and Reconstruction for Collider Physics](https://mlsanity.com/paper/1912.06794/) (2019)
- [CaloFlow II: Even Faster and Still Accurate Generation of Calorimeter Showers with Normalizing Flows](https://mlsanity.com/paper/2110.11377/) (2021)
- [CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulation](https://mlsanity.com/paper/2305.04847/) (2023)
- [CaloMan: Fast generation of calorimeter showers with density estimation on learned manifolds](https://mlsanity.com/paper/2211.15380/) (2022)
- [Generative Models for Fast Calorimeter Simulation.LHCb case](https://mlsanity.com/paper/1812.01319/) (2018)
- [Inductive Simulation of Calorimeter Showers with Normalizing Flows](https://mlsanity.com/paper/2305.11934/) (2023)
- [Deep Generative Models for Detector Signature Simulation: A Taxonomic Review](https://mlsanity.com/paper/2312.09597/) (2023)
- [New directions for surrogate models and differentiable programming for High Energy Physics detector simulation](https://mlsanity.com/paper/2203.08806/) (2022)
- [Calo-VQ: Vector-Quantized Two-Stage Generative Model in Calorimeter Simulation](https://mlsanity.com/paper/2405.06605/) (2024)
- [OmniJet-αC: Learning point cloud calorimeter simulations using generative transformers](https://mlsanity.com/paper/2501.05534/) (2025)
- [CaloQVAE : Simulating high-energy particle-calorimeter interactions using hybrid quantum-classical generative models](https://mlsanity.com/paper/2312.03179/) (2023)
- [CaloHadronic: a diffusion model for the generation of hadronic showers](https://mlsanity.com/paper/2506.21720/) (2025)
- [CaloDVAE : Discrete Variational Autoencoders for Fast Calorimeter Shower Simulation](https://mlsanity.com/paper/2210.07430/) (2022)
- [Towards Foundation Models for Experimental Readout Systems Combining Discrete and Continuous Data](https://mlsanity.com/paper/2505.08736/) (2025)
- [AllShowers: One model for all calorimeter showers](https://mlsanity.com/paper/2601.11716/) (2026)
- [Generalizable Foundation Models for Calorimetry via Mixtures-of-Experts and Parameter Efficient Fine Tuning](https://mlsanity.com/paper/2603.28804/) (2026)
- [Calorimeter Shower Superresolution with Conditional Normalizing Flows: Implementation and Statistical Evaluation](https://mlsanity.com/paper/2603.26813/) (2026)
- [Application of a Mixture of Experts-based Foundation Model to the GlueX DIRC Detector](https://mlsanity.com/paper/2604.24775/) (2026)
- [SPADE: Split-and-Delay Embeddings for Autoregressive High-Granularity Calorimeter Simulation](https://mlsanity.com/paper/2606.11304/) (2026)

## Abstract (arXiv)

Modern particles physics experiments have demonstrated an increasing need for fast, high-fidelity detector simulation as detector components have improved and subsequent computational requirements approach the limits of available resources. Recently, deep generative models have emerged as a promising alternative to traditional Monte-Carlo methods, with recent works drawing inspiration from large language models (LLMs) and self-supervised next-token prediction methods. In this work, we present an application of a GPT-style autoregressive transformer as a fast surrogate model for the calorimeter inside the CLAS12 experiment at the Thomas Jefferson National Accelerator Facility. The model is conditioned on incident momentum and generates realistic detector hits autoregressively across all nine calorimeter layers as sequences of strip, ADC, and TDC tokens. We demonstrate that the model faithfully reproduces hit multiplicity, spatial distributions, energy deposits, and the energy-momentum response of the electromagnetic calorimeter. The generator achieves inference rates exceeding 700 events per second on a single GPU, providing a substantial speedup over traditional Geant4-based simulations while maintaining physics fidelity essential for high-luminosity experimental programs.