BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Large Language Models: What Works (Really Well) and What’s Next
DTSTART:20260603T140000Z
DTEND:20260603T153000Z
DTSTAMP:20260615T042900Z
UID:indico-event-52563@agenda.infn.it
DESCRIPTION:Speakers: Roberto Navigli\n\nLarge Language Models (LLMs) have
  rapidly evolved from research prototypes into widely deployed systems tha
 t are transforming how we search\, write\, code\, learn\, and interact wit
 h knowledge. In this talk I will introduce the key factors behind the succ
 ess behind LLMs and offer a pragmatic perspective on what these models act
 ually do well today\, highlighting the capabilities that have proven genui
 nely robust across applications\, from reasoning over text and multilingua
 l understanding to knowledge access and human-AI interaction. I will then 
 examine the key limitations that remain unresolved\, including factuality\
 , reasoning reliability\, efficiency\, and grounding in real-world knowled
 ge. Finally\, I will discuss a few research directions that may shape the 
 future of AI\, including neuro-symbolic approaches\, continual learning\, 
 multimodal intelligence\, and more trustworthy and interpretable systems.\
 n\nhttps://agenda.infn.it/event/52563/
LOCATION:Aula Conversi (Dip. di Fisica - Edificio G. Marconi)
URL:https://agenda.infn.it/event/52563/
END:VEVENT
END:VCALENDAR