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:20260402T024534Z
LOCATION:Level 3 Lobby
DTSTART;TZID=America/Los_Angeles:20250622T180000
DTEND;TZID=America/Los_Angeles:20250622T190000
UID:dac_DAC 2025_sess261_RESEARCH2159@linklings.com
SUMMARY:A Retina-Inspired Pathway to Real-Time Motion Prediction inside Im
 age Sensors for Extreme-Edge Intelligence
DESCRIPTION:Subhradip Chakraborty (University of Wisconsin, Madison); Shay
  Snyder (George Mason University); Md Kaiser (University of Wisconsin, Mad
 ison); Maryam Parsa (George Mason University); Gregory Schwartz (Northwest
 ern University); and Akhilesh Jaiswal (University of Wisconsin, Madison)\n
 \nEnergy-efficient, real-time motion prediction (MP) enables autonomous ag
 ents to swiftly track objects and adapt to unexpected trajectory changes, 
 essential for tasks like escape, attack, and tracking. We present a retina
 -inspired neuromorphic framework capable of real-time, energy-efficient MP
  within image sensor pixels. Our hardware-algorithm co-design utilizes a b
 iphasic filter, spike adder, non-linear circuit, and a 2D array for multi-
 directional MP, implemented on GlobalFoundries 22nm FDSOI technology. A 3D
  Cu-Cu hybrid bonding approach enables design compactness, reducing area a
 nd routing complexity. Validated on Berkeley DeepDrive dataset, the model 
 provides efficient, low-latency MP for decision-making scenarios that depe
 nd on predictive visual computation.\n\nTracks: DES5: Emerging Device and 
 Interconnect Technologies\n\n
END:VEVENT
END:VCALENDAR