BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
DTSTART:20260308T030000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:PDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251102T010000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:PST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260122T190638Z
UID:C0B05D61-FABD-4C9F-A998-FDDC71411F75
DTSTART;TZID=America/Los_Angeles:20260119T140000
DTEND;TZID=America/Los_Angeles:20260119T150000
DESCRIPTION:Technical Seminar by Professor Amin Arbabian from Stanford Univ
 ersity with the following abstract:\n\nAI-driven machine perception is tra
 nsforming domains such as robotics\, healthcare\, consumer electronics\, a
 nd the IoE. As neural networks scale and edge sensors generate ever-larger
  data volumes\, inference tasks are becoming increasingly resource-intensi
 ve\, pushing up against computational limits. This talk explores two key a
 spects of this trend. First\, we introduce a new 3D sensing paradigm that 
 exemplifies the dramatic increase in data rates for next-generation physic
 al AI systems. Second\, we present a neuroscience-inspired adaptive infere
 nce framework that addresses processing bottlenecks in edge-based AI. We d
 erive theoretical bounds and provide empirical results showing 10–100× 
 efficiency gains in vision and language tasks. We further highlight how op
 timal design of adaptive inference state spaces can unlock even greater co
 mputational savings.\n\nSpeaker(s): Amin Arbabian\, \n\nRoom: 3038\, Bldg:
  Macleod Building\, 2356 Main Mall\, Vancouver\, British Columbia\, Canada
 \, V6T 1Z4
LOCATION:Room: 3038\, Bldg: Macleod Building\, 2356 Main Mall\, Vancouver\,
  British Columbia\, Canada\, V6T 1Z4
ORGANIZER:shahriar@ece.ubc.ca
SEQUENCE:23
SUMMARY:New Paradigms in Edge Sensing & Perception Systems 
URL;VALUE=URI:https://events.vtools.ieee.org/m/532917
X-ALT-DESC:Description: <br /><p>Technical Seminar by Professor Amin Arbabi
 an from Stanford University with the following abstract:</p>\n<p>AI-driven
  machine perception is transforming domains such as robotics\, healthcare\
 , consumer electronics\, and the IoE. As neural networks scale and edge se
 nsors generate ever-larger data volumes\, inference tasks are becoming inc
 reasingly resource-intensive\, pushing up against computational limits. Th
 is talk explores two key aspects of this trend. First\, we introduce a new
  3D sensing paradigm that exemplifies the dramatic increase in data rates 
 for next-generation physical AI systems. Second\, we present a neuroscienc
 e-inspired adaptive inference framework that addresses processing bottlene
 cks in edge-based AI. We derive theoretical bounds and provide empirical r
 esults showing 10&ndash\;100&times\; efficiency gains in vision and langua
 ge tasks. We further highlight how optimal design of adaptive inference st
 ate spaces can unlock even greater computational savings.</p>
END:VEVENT
END:VCALENDAR