BEGIN:VCALENDAR
VERSION:2.0
PRODID:www.dresden-science-calendar.de
METHOD:PUBLISH
CALSCALE:GREGORIAN
X-MICROSOFT-CALSCALE:GREGORIAN
X-WR-TIMEZONE:Europe/Berlin
BEGIN:VTIMEZONE
TZID:Europe/Berlin
X-LIC-LOCATION:Europe/Berlin
BEGIN:DAYLIGHT
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
DTSTART:19810329T030000
RRULE:FREQ=YEARLY;INTERVAL=1;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
DTSTART:19961027T030000
RRULE:FREQ=YEARLY;INTERVAL=1;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:DSC-23050
DTSTART;TZID=Europe/Berlin:20260806T164000
SEQUENCE:1784735670
TRANSP:OPAQUE
DTEND;TZID=Europe/Berlin:20260806T181000
URL:https://dresden-science-calendar.org/calendar/de/detail/23050
LOCATION:TUD Andreas-Pfitzmann-Bau\, Nöthnitzer Straße 4601069 Dresden
SUMMARY:Litvak: From Understanding Language to Assisting Humans: Context-Aw
 are AI for Communication and Softwar
CLASS:PUBLIC
DESCRIPTION:Speaker: Dr. Marina Litvak \nInstitute of Speaker: ScaDS.AI Dre
 sden/Leipzig\nTopics:\n\n Location:\n  Name: TUD Andreas-Pfitzmann-Bau (Ro
 om 1004)\n  Street: Nöthnitzer Straße 46\n  City: 01069 Dresden\n  Phone
 : \n  Fax: \nDescription: Artificial intelligence has evolved from systems
  that process isolated information into increasingly capable assistants fo
 r complex human tasks. However\, many limitations of modern AI systems can
  be traced to an insufficient understanding of context. Whether interpreti
 ng language\, adapting information to individual users\, or supporting sof
 tware development\, context is essential for producing reliable and useful
  results.    In this lecture\, Dr. Marina Litvak will present research on 
 context-aware AI across three application domains. First\, she will discus
 s multilingual offensive language analysis\, where linguistic and cultural
  context is crucial for distinguishing harmful content from benign languag
 e. Second\, she will present work on document-level text simplification\, 
 showing how retrieval-augmented generation and example-guided prompting ca
 n help large language models produce accessible texts while preserving mea
 ning and coherence. Third\, Dr. Marina Litvak will discuss AI-assisted sof
 tware development\, where knowledge about existing code\, software archite
 cture\, and project requirements enables the reuse and adaptation of softw
 are components beyond conventional code generation. She will conclude with
  future research directions in trustworthy retrieval\, adaptive reasoning\
 , human–AI collaboration\, and intelligent software engineering.
DTSTAMP:20260730T084612Z
CREATED:20260722T155430Z
LAST-MODIFIED:20260722T155430Z
END:VEVENT
END:VCALENDAR