BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20241027T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20240331T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RDATE:20250330T020000
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.28596.field_data.0@www.u-gov-ricerca.uniroma1.it
DTSTAMP:20260404T180809Z
CREATED:20241004T074259Z
DESCRIPTION:AbstractRetrieval Augmented Generation (RAG) is a technique we 
 proposed in 2020 that allows generative AI models to access external infor
 mation\, enhancing their responses to prompts. Since then\, the popularity
  of this approach has skyrocketed\, becoming the de facto standard for han
 dling knowledge-intensive tasks in both academia and industry. In this tal
 k\, I will describe various applications of RAG\, including improving Wiki
 pedia verifiability and providing a glimpse into the work we’re doing at S
 amaya AI. I will then discuss some limitations of this architecture\, such
  as the “lost in the middle” effect\, and conclude by outlining future res
 earch directions that I find most exciting.Fabio Petroni's BiographyFabio 
 Petroni is the Co-Founder and CTO of Samaya AI\, specializing in the inter
 section of AI and knowledge. He holds a Ph.D. in Engineering of Computer S
 cience from Sapienza University and has extensive research experience at i
 ndustrial labs\, including the FAIR team at Meta AI and the R&D department
  at Thomson Reuters. Fabio is renowned for his research on knowledge-inten
 sive NLP\, highlighted by awards such as first place in the NeurIPS Effici
 ent Open-Domain Question Answering competition in 2020 and the Google Best
  Paper Award at AKBC 2020. He has authored multiple high-impact publicatio
 ns\, including “Language Models as Knowledge Bases?” and the original RAG 
 paper.Zoom link to attend remotelyhttps://uniroma1.zoom.us/j/83261382718
DTSTART;TZID=Europe/Paris:20241022T150000
DTEND;TZID=Europe/Paris:20241022T150000
LAST-MODIFIED:20241004T080349Z
LOCATION:Aula Magna DIAG
SUMMARY:Retrieval Augmented Generation (RAG): Applications\, Limitations\, 
 and Future Directions - Fabio Petroni
URL;TYPE=URI:http://www.u-gov-ricerca.uniroma1.it/node/28596
END:VEVENT
END:VCALENDAR