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:20260730T152637Z
LOCATION:
DTSTART;TZID=America/Los_Angeles:20260728T124500
DTEND;TZID=America/Los_Angeles:20260728T124600
UID:dac_DAC 2026_sess315_RESEARCH2914@linklings.com
SUMMARY:LUNA: LUT-Based Neural Architecture for Fast and Low-Cost Qubit Re
 adout
DESCRIPTION:Muhammad Ali Farooq (Arizona State University), Giuseppe Di Gu
 glielmo (Fermi National Accelerator Laboratory), Abhi Rajagopala (Universi
 ty of Arkansas), Nhan Tran (Fermi National Accelerator Laboratory), and Vi
 dya A. Chhabria and Aman Arora (Arizona State University)\n\nQubit readout
  is a critical operation in quantum computing systems, which maps the anal
 og response of qubits into discrete classical states. Deep neural networks
  (DNNs) have recently emerged as a promising solution to improve readout a
 ccuracy . Prior hardware implementations of DNN-based readout are resource
 -intensive and suffer from high inference latency, limiting their practica
 l use in low-latency decoding and quantum error correction (QEC) loops.\nT
 his paper proposes LUNA, a fast and efficient superconducting qubit readou
 t accelerator that combines low-cost integrator-based preprocessing with L
 ook-Up Table (LUT) based neural networks for classification. The architect
 ure uses simple integrators for dimensionality reduction with minimal hard
 ware overhead, and employs LogicNets (DNNs synthesized into LUT logic) to 
 drastically reduce resource usage while enabling ultra-low-latency inferen
 ce. We integrate this with a differential evolution based exploration and 
 optimization framework to identify high-quality design points. Our results
  show up to a 10.95× reduction in area and 30% lower latency with little t
 o no loss in fidelity compared to the state-of-the-art. LUNA enables scala
 ble, low-footprint, and high-speed qubit readout, supporting the developme
 nt of larger and more reliable quantum computing systems.\n\nTopics: Quant
 um\n\nTrack: DES6. Quantum Computing, Systems\n\nSession Chairs: Hokeun Ki
 m (Arizona State University); BaekGyu Kim (Daegu Gyeongbuk Institute of Sc
 ience and Technology); Xiang Chen (Peking University); Sangyeob Kim (Yonse
 i University); Robert M. Radway (University of Pennsylvania); Prashanth Mo
 han (University of Pittsburgh); Xiaoxuan Yang (University of Virginia, Sta
 nford University); Ramtin Zand (University of South Carolina); Hadi Kamali
  (University of Central Florida); Jiafeng Xie (Villanova University); Prab
 uddha Chakraborty (University of Maine); Junichiro Kadomoto (University of
  Tokyo); and Yosuke Ueno (RIKEN)\n\n
END:VEVENT
END:VCALENDAR