BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Europe/Dublin
BEGIN:DAYLIGHT
DTSTART:20250330T020000
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:IST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251026T010000
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:GMT
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250416T143343Z
UID:701097A4-DF4C-4827-8B47-42D9171282BE
DTSTART;TZID=Europe/Dublin:20250416T130000
DTEND;TZID=Europe/Dublin:20250416T140000
DESCRIPTION:Artificial Intelligence (AI) plays a crucial role in the evolvi
 ng landscape of wireless communications\, addressing challenges that tradi
 tional approaches cannot solve. This talk discusses the evolution of wirel
 ess AI\, emphasizing the transition from isolated\, task-specific models t
 o more generalized and adaptable AI models\, inspired by the recent succes
 s of large language models (LLMs). To overcome the limitations of task-spe
 cific AI strategies in wireless networks\, Wireless Foundation Models are 
 proposed. The concept of Wireless Foundation Models is to create generic m
 odels trained on wireless data (e.g.\, IQ signals\, RSSI\, network KPIs) t
 hat can be applied to a variety of tasks such as interference detection\, 
 activity detection\, power allocation\, channel estimation\, and more.\n\n
 To realize this vision\, several key challenges must be addressed\, such a
 s identifying effective pre-training tasks\, supporting embedded time-seri
 es data\, and enabling human-\n\nunderstandable interaction. Furthermore\,
  it is essential for Wireless Foundation Models to interact with LLMs\, wh
 ich can assist in extracting meta-data (such as classifications\, semantic
  description of the wireless network conditions\, sensing applications\, h
 uman behavior\, etc.) from these models. This integration with LLMs can le
 ad to continuous optimization of wireless networks.\n\nSpeaker(s): Adnan\n
 \nVirtual: https://events.vtools.ieee.org/m/481093
LOCATION:Virtual: https://events.vtools.ieee.org/m/481093
ORGANIZER:tadhg.creagh.2024@mumail.ie
SEQUENCE:20
SUMMARY:Online Seminar with Prof. Adnan Shahid for Wireless Foundation Mode
 ls
URL;VALUE=URI:https://events.vtools.ieee.org/m/481093
X-ALT-DESC:Description: <br /><p>Artificial Intelligence (AI) plays a cruci
 al role in the evolving landscape of wireless communications\, addressing 
 challenges that traditional approaches cannot solve. This talk discusses t
 he evolution of wireless AI\, emphasizing the transition from isolated\, t
 ask-specific models to more generalized and adaptable AI models\, inspired
  by the recent success of large language models (LLMs). To overcome the li
 mitations of task-specific AI strategies in wireless networks\, Wireless F
 oundation Models are proposed. The concept of Wireless Foundation Models i
 s to create generic models trained on wireless data (e.g.\, IQ signals\, R
 SSI\, network KPIs) that can be applied to a variety of tasks such as inte
 rference detection\, activity detection\, power allocation\, channel estim
 ation\, and more.</p>\n<p>&nbsp\;</p>\n<p>To realize this vision\, several
  key challenges must be addressed\, such as identifying effective pre-trai
 ning tasks\, supporting embedded time-series data\, and enabling human-</p
 >\n<p>understandable interaction. Furthermore\, it is essential for Wirele
 ss Foundation Models to interact with LLMs\, which can assist in extractin
 g meta-data (such as classifications\, semantic description of the wireles
 s network conditions\, sensing applications\, human behavior\, etc.) from 
 these models. This integration with LLMs can lead to continuous optimizati
 on of wireless networks.</p>
END:VEVENT
END:VCALENDAR