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:
DTSTART;TZID=America/Los_Angeles:20260728T175700
DTEND;TZID=America/Los_Angeles:20260728T175800
UID:dac_DAC 2026_sess317_RESEARCH1440@linklings.com
SUMMARY:TACo: Training-Free, Hardware-Aware ViT Architecture Search with a
  Hypervolume-Based Unified Zero-Cost Score
DESCRIPTION:Eunji Kwon (Kookmin University)\n\nWe propose TACo, a training
 -free, hardware-aware architecture search framework for Vision Transformer
 s (ViTs), powered by a Hypervolume-based Unified Zero-Cost Score (HV-score
 ) that integrates four accuracy- and hardware-related dimensions: a newly 
 proposed zero-cost accuracy score (ZAS), latency, energy, and activation m
 emory. TACo rapidly estimates the potential of candidate ViTs without trai
 ning: ZAS captures layer-wise gradient stability, weight–gradient coupling
 , and gradient-modulated activation stability, while the HV-score guides m
 ulti-objective selection using Pareto and hypervolume principles. Experime
 nts on CIFAR-10 and ImageNet-1K show that TACo reduces search time from GP
 U-days to GPU-hours while identifying a well-balanced ViT architecture in 
 terms of accuracy and computational cost.\n\nTrack: EDA7-II. Physical Desi
 gn and Verification, Design\n\nSession Chairs: Christian Pilato (Politecni
 co di Milano); Mohsen Imani (University of California, Irvine); Flavio Pon
 zina (San Diego State University); Amin Farshidi (Cadence Design Systems, 
 Inc.); Yonggan Fu (Georgia Institute of Technology, NVIDIA); Dimitrios Tsa
 ras (Huawei, Hong Kong University of Science and Technology (HKUST)); Anh 
 Nguyen (Fujitsu Limited); Ruiyang Qin (Villanova University); Jiliang Zhan
 g (Hunan University); Meng Li (Peking University); and Rassul Bairamkulov 
 (Advanced Micro Devices (AMD))\n\n
END:VEVENT
END:VCALENDAR