Generative models and seq2seq techniques for the flash-simulation of the LHCb experiment

Proceedings of Science. 2025. Vol. 476. P. 1032.

Derkach D., Anderlini L., Capelli S., Corti G., Davis A., Martinelli M.

Simulating detector and reconstruction effects on physics quantities is crucial for data analysis, but it is coming unsustainably costly for the upcoming HEP experiments. The most radical approach to speed-up detector simulation is Flash Simulation, as proposed by the LHCb collaboration in Lamarr, a software package implementing a novel simulation paradigm relying on Deep Generative Models and Seq2seq attention-driven techniques to deliver simulated samples. Thanks to its modular layout, Lamarr provides analysis-level quantities by applying a pipeline of machine learning-based modules that properly transforms the information resulting from physics generators. Good agreement is observed by comparing key reconstructed quantities obtained with Lamarr against those from the existing detailed Geant4-based simulation. Lamarr has been designated with dual capabilities: it can function as a stand-alone simulation framework, while also being seamlessly integrated into the LHCb simulation software.

Keywords: машинное обучение, computer simulation, симуляция, machine learning, particle physics, generative modeling, физика частиц, генеративные модели