BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260202T201248Z
LOCATION:Second Floor Atrium
DTSTART;TZID=America/Chicago:20251120T080000
DTEND;TZID=America/Chicago:20251120T170000
UID:submissions.supercomputing.org_SC25_sess533_post233@linklings.com
SUMMARY:PhySiViT: A Physics Simulation Vision Transformer
DESCRIPTION:Jessica Ezemba (Carnegie Mellon University), James Afful (Iowa
  State University), and Mei-Yu Wang (Pittsburgh Supercomputing Center)\n\n
 Modern scientific computing generates massive simulation data across physi
 cs domains, yet researchers lack general-purpose tools for efficient analy
 sis. While vision transformers like CLIP and DINO have revolutionized natu
 ral image analysis, no equivalent exists for physics simulation data. This
  project trains a custom vision transformer on “the Well” dataset, a 15 TB
  collection of diverse physics simulations. Using only 7 million images (c
 ompared to >100 million for CLIP/DINOv2), we trained our physics foundatio
 n model in 22 hours on a single Cerebras CS-3 server. Despite reduced trai
 ning scale, our model demonstrates competitive classification performance 
 while exceeding at physics-specific tasks: temporal forecasting (𝑅2 = 0.33
  vs. DINOv2’s 0.23) and physics clustering (silhouette score = 0.232 vs. D
 INOv2’s 0.195). This work demonstrates that efficient, domain-focused foun
 dation models can achieve better performance in specialized scientific dom
 ains.\n\nTag: Research & ACM SRC Posters\n\nRegistration Category: Technic
 al Program Reg Pass\n\nSession Chairs: Kento Sato (RIKEN Center for Comput
 ational Science (R-CCS)); Chris Schlipalius (Pawsey Supercomputing Researc
 h Centre; Commonwealth Scientific and Industrial Research Organisation (CS
 IRO), Australia); and Anja Gerbes (Georg-August-Universität Göttingen)\n\n
END:VEVENT
END:VCALENDAR