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:20251026T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250330T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.29369.field_data.0@www.u-gov-ricerca.uniroma1.it
DTSTAMP:20260407T214158Z
CREATED:20250603T122046Z
DESCRIPTION:AbstractLarge Language Models (LLMs) such as DeepSeek R-1\, Ope
 nAI o1 and many others have recently demonstrated very robust reasoning ca
 pabilities\, arousing considerable interest in the scientific community. T
 he success of these models usually depends on several factors\, such as in
 ference-time scaling and a fine-tuning phase based on Reinforcement Learni
 ng. In this talk\, we will analyze the main ingredients of reasoning LLMs 
 and we will introduce a new emerging paradigm based on reasoning in a cont
 inuous latent space. Short bioEnver Sangineto is Associate Professor at th
 e University of Modena and Reggio Emilia\, where he teaches Machine Learni
 ng\, Image Processing\, and AI for Automotive. Among his research interest
 s\, he has worked on Tabular Data Generation\, Compositional AI\, Vision-L
 anguage Models\, Diffusion Models\, Transformer Training Regularization an
 d Self-Supervised Learning. He is the author of over 100 publications in i
 nternational journals and conferences and associate editor of Machine Lear
 ning Journal and Machine Vision and Application. In 2014\, he worked at th
 e Center for Research in Computer Vision laboratory at the University of C
 entral Florida (UCF)\, under the supervision of Mubarak Shah\, where he wo
 rked on Object Detection. 
DTSTART;TZID=Europe/Paris:20250606T120000
DTEND;TZID=Europe/Paris:20250606T130000
LAST-MODIFIED:20250603T124241Z
LOCATION:Aula A4 del DIAG
SUMMARY:Talk 'Reasoning with Large Language Models' - Prof. Enver Sangineto
  - Università degli Studi di Modena e Reggio Emilia
URL;TYPE=URI:http://www.u-gov-ricerca.uniroma1.it/node/29369
END:VEVENT
END:VCALENDAR