BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Parnassus: A GPU-enabled\, Python-based Package for Fast Particle 
 Detector Simulation and Reconstruction
DTSTART:20260930T090000Z
DTEND:20260930T100000Z
DTSTAMP:20261019T185600Z
UID:indico-event-1730127@indico.cern.ch
CONTACT:EP-seminars.colloquia@cern.ch
DESCRIPTION:Speakers: Eilam Gross (Weizmann Institute of Science (IL))\n\n
 Abstract:Generative AI models\, including those behind image-generation to
 ols\, have demonstrated remarkable capabilities for transforming random in
 puts into coherent outputs. Inspired by these advancements\, we've develop
 ed PARNASUS\, a deep-learning model designed for particle physics. Parnass
 us processes point clouds representing particles interacting with a detect
 or and outputs reconstructed particle data.  Parnassus accurately replica
 tes the particle flow algorithm and generalizes well beyond its training s
 et. \nPARNASUS shows that flow-matching AI can deliver full-simulation-qu
 ality detector reconstruction at fast-simulation speeds\, paving the way f
 or the next generation of HEP simulation. Its initial release includes two
  models of the CMS detector: one based on a flow-matching neural network a
 rchitecture and one based on a PyTorch implementation of the Delphes CMS c
 ard (parametric bias and smearing). PyTorch versions of the ATLAS and ALEP
 H Delphes cards are also available. PARNASSUS is a paradise for experiment
 alists as well as phenomenologists who want to test their models in a real
  experimental environment.\nBio: \nProfessor Eilam Gross is an experiment
 al particle physicist at the Weizmann Institute of Science and a long-stan
 ding member of the ATLAS Collaboration. As co-convener of the ATLAS Higgs 
 Physics Group\, he played a leading role in the searches that culminated i
 n the discovery of the Higgs boson in 2012. He also helped establish the s
 tatistical framework now widely used for searches and measurements at the 
 LHC\, notably through seminal work on likelihood-based tests and the look-
 elsewhere effect. Over the past decade\, his research has increasingly foc
 used on deep-learning applications in particle physics\, including particl
 e reconstruction\, anomaly detection\, and generative approaches to detect
 or simulation.\n \nCoffee served at 10h30\n\nhttps://indico.cern.ch/event
 /1730127/\n\nZoom: https://cern.zoom.us/j/98545267593?pwd=akZWdmlyK01zbjFQ
 a0x2c2ZXWW9ydz09
LOCATION:503/1-001 - Council Chamber (CERN)
URL:https://indico.cern.ch/event/1730127/
END:VEVENT
END:VCALENDAR