BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260730T152640Z
LOCATION:Exhibit Hall
DTSTART;TZID=America/Los_Angeles:20260728T171400
DTEND;TZID=America/Los_Angeles:20260728T171400
UID:dac_DAC 2026_sess306_WIP3216@linklings.com
SUMMARY:Late Breaking Results: Quantum-Aware Model Compression Techniques 
 for Scalable Quantum Machine Learning
DESCRIPTION:Nouhaila Innan (New York University Abu Dhabi) and Muhammad Sh
 afique (New York University Abu Dhabi (NYUAD))\n\nVariational quantum circ
 uits (VQCs) are promising yet costly to deploy because redundant parameter
 s and deep entangling layers amplify noise and runtime. We present Q-Compr
 ession, a post-training pipeline that masks small-magnitude angles, snaps 
 low-sensitivity parameters to a low-bit grid using a curvature proxy, and 
 freezes noise-dominated updates via gradient-variance tracking. Across MNI
 ST, FashionMNIST, and KMNIST (binary 0-vs-rest), Q-Compression preserves a
 ccuracy and often slightly improves it while reducing circuit operations a
 nd depth. Best settings (e.g., keep ratio 0.75, 16 levels) maintain $>0.99
 7$ accuracy with substantial complexity savings. These reductions yield sh
 allower, uniform circuits that are better suited to NISQ execution and tun
 ing.\n\nTrack: Student\n\n
END:VEVENT
END:VCALENDAR