aiqbench analysis
This research applies a GPT-style autoregressive transformer to accelerate detector simulations for the CLAS12 experiment, achieving inference rates over 700 events per second on a single GPU. By treating calorimeter hits as token sequences similar to language models, this approach offers a high-fidelity alternative to traditional Monte-Carlo methods that are nearing computational limits. The work highlights how deep generative AI is becoming essential for enabling the massive data throughput required by next-generation particle physics experiments.
GPT-Based Fast Simulation of CLAS12 Detector Hits via Conditional Autoregressive Generation
arXiv:2606.16035v1 Announce Type: cross Abstract: 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.
Abstract: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.
Instrumentation and Detectors (physics.ins-det); Machine Learning (cs.LG); High Energy Physics - Experiment (hep-ex); Nuclear Experiment (nucl-ex); Data Analysis, Statistics and Probability (physics.data-an)
arXiv:2606.16035 [physics.ins-det]
(or arXiv:2606.16035v1 [physics.ins-det] for this version)
https://doi.org/10.48550/arXiv.2606.16035 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 204 words
Related coverage
Scaling Collider Event Generation with Residual-Quantized Tokens
arXiv · Oct 2, 2026
NVIDIA GTC Taipei at COMPUTEX: Live Updates on What’s Next in AI
NVIDIA · May 21, 2026
Developing Healthcare Robotics with GPU-Native Medical Physics Simulation
NVIDIA · Jul 28, 2026
Humanity’s Last Invention — Richard Socher of Recursive
Latent Space · Sep 14, 2026