BEGIN:VCALENDAR
VERSION:2.0
PRODID:Baylor CMS Calendar /PHP/
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:US_Central
BEGIN:STANDARD
DTSTART:20001029T020000
RRULE:FREQ=YEARLY;WKST=MO;INTERVAL=1;BYMONTH=11;BYDAY=1SU
TZNAME:Standard Time
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20010401T020000
RRULE:FREQ=YEARLY;WKST=MO;INTERVAL=1;BYMONTH=3;BYDAY=2SU
TZNAME:Daylight Saving Time
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:Baylor_CMS_Event-4451
DTSTAMP:20260623T210549Z
SUMMARY:Guest Lecture: "Large Language Models, Model Collapse, and the Conservation of Information" with George Montañez, Ph.D.
DESCRIPTION:Location: Cashion 311"Large Language Models, Model Collapse, and the Conservation of Information".Abstract: Do Large Language Models (LLMs) think and reason? Are they perpetual information machines, producing endless coherent and correct text from finite training data? We explore how LLMs work and whether they produce rational thought and endless information. We show how theoretical considerations and experimental results from philosophy, statistics, information theory, and machine learning argue against the thesis that LLMs are rational, information-generating entities.\n\nVIEW EVENT ONLINE:\n
LOCATION:
DTSTART;TZID=US_Central:20251114T121500
DTEND;TZID=US_Central:20251114T131500
END:VEVENT
END:VCALENDAR