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:20260202T201257Z
LOCATION:Second Floor Atrium
DTSTART;TZID=America/Chicago:20251121T080000
DTEND;TZID=America/Chicago:20251121T120000
UID:submissions.supercomputing.org_SC25_sess620_post198@linklings.com
SUMMARY:DiffPro: Joint Timestep and Layer-Wise Precision Optimization for 
 Efficient Diffusion Inference
DESCRIPTION:Farhana Amin (Virginia Tech), Kanchon Gharami (Embry-Riddle Ae
 ronautical University), and Dimitrios S. Nikolopoulos (Virginia Tech)\n\nD
 iffPro is a simple framework to speed up and shrink diffusion models while
  preserving image quality. It combines layer-wise quantization, guided by 
 a manifold-based sensitivity check with adaptive timestep selection. Compa
 red with quantization-only or sampling-only baselines, this joint strategy
  yields better FID–memory trade-offs. We evaluate on MNIST, CIFAR-10, and 
 CelebA using both PTQ and QAT, showing meaningful size reductions (e.g., ~
 34 MB on a CIFAR-10 setup) with competitive FID. Current limits include oc
 casional mis-ranking of a few blocks at high noise and a focus on uncondit
 ioned models. Next, we will extend DiffPro to text/class-conditioned diffu
 sion, replace hand-tuned thresholds with a budgeted optimizer that co-sele
 cts per-layer bit-widths and timesteps using per-timestep sensitivity, and
  incorporate hardware-aware costs.\n\nTag: Research & ACM SRC Posters\n\nR
 egistration Category: Technical Program Reg Pass\n\nSession Chairs: Kento 
 Sato (RIKEN Center for Computational Science (R-CCS)); Anja Gerbes (Georg-
 August-Universität Göttingen); and Chris Schlipalius (Pawsey Supercomputin
 g Research Centre; Commonwealth Scientific and Industrial Research Organis
 ation (CSIRO), Australia)\n\n
END:VEVENT
END:VCALENDAR
