BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250626T234540Z
LOCATION:B206
DTSTART;TZID=America/New_York:20241122T112400
DTEND;TZID=America/New_York:20241122T113600
UID:submissions.supercomputing.org_SC24_sess769_ws_adugai132@linklings.com
SUMMARY:G-LED: Generative AI for Learning the Effective Dynamics of High-d
 imensional, Complex Systems
DESCRIPTION:Han Gao, Sebastian Kaltenbach, and Petros Koumoutsakos (Harvar
 d University)\n\nWe present novel generative models for accelerating simul
 ations of high-dimensional systems through learning and evolving their eff
 ective dynamics. In our Generative Learning of Effective Dynamics (G-LED) 
 framework, instances of high dimensional data are down sampled to a lower 
 dimensional manifold that is evolved through an auto-regressive attention 
 mechanism. Subsequently Bayesian diffusion models are employed, that map t
 his low-dimensional manifold onto its corresponding  high-dimensional spac
 e. These diffusion models operate simultaneously on batches of data and ca
 n incorporate physical constraints using the concept of virtual observable
 s and gradient guidance. We demonstrate unprecedented capabilities in capt
 uring the evolution of benchmark models such as Kuramoto-Sivashinsky as we
 ll as simulations of 3D turbulent channel flows.\n\nTag: Artificial Intell
 igence/Machine Learning\n\nRegistration Category: Workshop Reg Pass\n\nSes
 sion Chairs: Charlie Catlett (Argonne National Laboratory (ANL), Universit
 y of Chicago); Fabrizio Gagliardi (Barcelona Supercomputing Center (BSC), 
 Association for Computing Machinery (ACM)); Neeraj Kumar (Pacific Northwes
 t National Laboratory (PNNL)); Satoshi Matsuoka (RIKEN, Tokyo Institute of
  Technology); Irina Rish (University of Montreal, Canada; Mila – Quebec AI
  Institute); Rick Stevens (Argonne National Laboratory (ANL), University o
 f Chicago); and Valerie Taylor (Argonne National Laboratory (ANL), Univers
 ity of Chicago)\n\n
END:VEVENT
END:VCALENDAR