002919577 001__ 2919577
002919577 003__ SzGeCERN
002919577 005__ 20241212232708.0
002919577 0247_ $$2DOI$$9EDP Sciences$$a10.1051/epjconf/202429509039
002919577 0248_ $$aoai:cds.cern.ch:2919577$$pcerncds:FULLTEXT$$pcerncds:CERN:FULLTEXT$$pcerncds:CERN
002919577 035__ $$9https://inspirehep.net/api/oai2d$$aoai:inspirehep.net:2785621$$d2024-12-11T08:01:30Z$$h2024-12-12T05:08:44Z$$mmarcxml
002919577 035__ $$9Inspire$$a2785621
002919577 041__ $$aeng
002919577 100__ $$aRaikwar, Piyush$$uCERN
002919577 245__ $$9EDP Sciences$$aTransformers for Generalized Fast Shower Simulation
002919577 260__ $$c2024
002919577 300__ $$a8 p
002919577 520__ $$9EDP Sciences$$aRecently, transformer-based foundation models have proven to be a generalized architecture applicable to various data modalities, ranging from text to audio and even a combination of multiple modalities. Transformers by design should accurately model the non-trivial structure of particle showers thanks to the absence of strong inductive bias, better modeling of long-range dependencies, and interpolation and extrapolation capabilities. In this paper, we explore a transformer-based generative model for detector-agnostic fast shower simulation, where the goal is to generate synthetic particle showers, i.e., the energy depositions in the calorimeter. When trained with an adequate amount and variety of showers, these models should learn better representations compared to other deep learning models, and hence should quickly adapt to new detectors. In this work, we will show the prototype of a transformer-based generative model for fast shower simulation, as well as explore certain aspects of transformer architecture such as input data representation, sequence formation, and the learning mechanism for our unconventional shower data.
002919577 540__ $$aCC-BY-4.0$$bEDP Sciences$$uhttps://creativecommons.org/licenses/by/4.0/
002919577 65017 $$2SzGeCERN$$aComputing and Computers
002919577 690C_ $$aARTICLE
002919577 690C_ $$aCERN
002919577 700__ $$aCardoso, Renato$$uCERN
002919577 700__ $$aChernyavskaya, Nadezda$$uCERN
002919577 700__ $$aJaruskova, Kristina$$uCERN
002919577 700__ $$aPokorski, Witold$$uCERN
002919577 700__ $$aSalamani, Dalila$$uCERN
002919577 700__ $$aSrivatsa, Mudhakar$$uIBM Watson Res. Ctr.
002919577 700__ $$aTsolaki, Kalliopi$$uCERN
002919577 700__ $$aVallecorsa, Sofia$$uCERN
002919577 700__ $$aZaborowska, Anna$$uCERN
002919577 773__ $$c09039$$pEPJ Web Conf.$$v295$$wC23-05-08$$y2024
002919577 8564_ $$82695895$$s1955506$$uhttp://cds.cern.ch/record/2919577/files/document.pdf$$yFulltext
002919577 960__ $$a13
002919577 962__ $$b2853081$$k09039$$nnorfolk20230508
002919577 980__ $$aARTICLE
002919577 980__ $$aConferencePaper