BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T000713Z
LOCATION:501-502
DTSTART;TZID=America/Denver:20231113T115000
DTEND;TZID=America/Denver:20231113T121000
UID:submissions.supercomputing.org_SC23_sess440_ws_ai4s107@linklings.com
SUMMARY:Toward Foundation Models for Materials Science:  The Open MatSci M
 L Toolkit
DESCRIPTION:Kin Long Kelvin Lee (Intel Corporation), Carmelo Gonzales (Int
 el Labs), Matthew Spellings (Vector Institute), Mikhail Galkin and Santiag
 o Miret (Intel Labs), and Nalini Kumar (Intel Corporation)\n\nArtificial i
 ntelligence and machine learning have shown great promise in their ability
  to accelerate novel materials discovery. As researchers and domain scient
 ists seek to unify and consolidate chemical knowledge, the case for models
  with potential to generalize across different tasks within materials scie
 nce – so-called "foundation models" –  grows with ambitions. This manuscri
 pt reviews our recent progress with development of Open MatSci ML Toolkit,
  and details experiments that lay the groundwork for foundation model rese
 arch and development with our framework. Our key results show that for sim
 ple applications, pre-training appears to provide worse modeling performan
 ce than training models from random initialization. However, for more comp
 lex instances, such as when a model is required to learn across multiple d
 atasets and types of targets simultaneously, the inductive bias from pre-t
 raining provides significantly better performance. This insight will hopef
 ully inform subsequent efforts into creating foundation models for materia
 ls science applications.\n\nTag: Artificial Intelligence/Machine Learning\
 n\nRegistration Category: Workshop Reg Pass\n\nSession Chairs: Murali Eman
 i (Argonne National Laboratory (ANL)); Gokcen Kestor (Barcelona Supercompu
 ting Center (BSC); University of California, Merced); and Dong Li (Univers
 ity of California, Merced)\n\n
END:VEVENT
END:VCALENDAR