BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260624T171341Z
LOCATION:Bldg. 8 - B 102
DTSTART;TZID=Europe/Stockholm:20260629T150000
DTEND;TZID=Europe/Stockholm:20260629T153000
UID:submissions.pasc-conference.org_PASC26_sess111_msa223@linklings.com
SUMMARY:Open Discussion: Trustworthy Machine Learning Potentials - Challen
 ges and Perspectives
DESCRIPTION:Michał Sanocki (Technical University of Munich)\n\nThis sessio
 n will be an open discussion following the presentations in the minisympos
 ium. The goal is to create space for speakers and participants to exchange
  perspectives on common challenges in developing and applying machine lear
 ning interatomic potentials. Topics raised by the talks include dataset qu
 ality and coverage, biases in training data, transferability of foundation
  models, and the role of uncertainty in improving model reliability.\nRath
 er than formal presentations, this session will encourage interactive disc
 ussion with the audience. We aim to compare different approaches presented
  in the minisymposium, identify shared challenges, and discuss practical e
 xperiences in building and deploying machine learning potentials. Particul
 ar emphasis will be placed on lessons learned, limitations of current meth
 ods, and promising directions for future research. The discussion will als
 o provide an opportunity to gather feedback from researchers working on co
 mplementary approaches. The overall objective is to encourage open exchang
 e and highlight key challenges and opportunities for developing more relia
 ble and transferable machine learning potentials.\n\nDomain: Chemistry and
  Materials, Physics, Computational Methods and Applied Mathematics\n\nSess
 ion Chairs: Michał Sanocki (Technical University of Munich); Ian Störmer (
 Technical University of Munich); and Philip Loche (Technical University of
  Munich, EPFL)\n\n
END:VEVENT
END:VCALENDAR