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:20260728T173900
DTEND;TZID=America/Los_Angeles:20260728T174000
UID:dac_DAC 2026_sess306_LBR052@linklings.com
SUMMARY:Late Breaking Results: Recoverability-guided Layer-wise N:M Sparsi
 ty under Latency Constraints
DESCRIPTION:Liu Yiming (University of Science and Technology of China), We
 nqi Lou (USTC), Ke Zhiwei (University of Science&Technology of China), Fen
 grui Zuo and Chao Wang (University of Science and Technology of China), an
 d Xuehai Zhou (USTC)\n\nLayer-wise N:M sparsity balances accuracy and hard
 ware acceleration for Vision Transformers (ViTs), yet identifying effectiv
 e configurations is costly due to fine-tuning overhead and latency-induced
  fragmentation. We present HaLSpar, a hardware-aware framework that couple
 s a recoverability-driven zero-shot proxy (RCG) with a latency-constrained
  search strategy. By estimating recovery potential without repeated fine-t
 uning, HaLSpar directly optimizes sparsity configurations. On ImageNet-1K 
 with multiple ViT and Swin models, it achieves up to 270x faster search wh
 ile delivering 1.5x–2.5x speedups with minimal accuracy degradation.\n\nTr
 ack: Student\n\n
END:VEVENT
END:VCALENDAR