BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//cfp.pydata.org//london2025//talk//DSAQW9
BEGIN:VTIMEZONE
TZID:GMT
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-london2025-DSAQW9@cfp.pydata.org
DTSTART;TZID=GMT:20250607T134000
DTEND;TZID=GMT:20250607T142500
DESCRIPTION:Large Language Models (LLMs) have grown into prominence as some
  of the most popular technological artifacts of the day. This talk will pr
 ovide a highly accessible and visual overview of LLM concepts relevant to 
 today's data professionals. This includes looking at present-day Transform
 er architectures\, tokenizers\, reward models\, reasoning LLMs\, agentic t
 rajectories\, and the various training stages of a large language model in
 cluding next-word prediction\, instruction-tuning\, preference-tuning\, an
 d reinforcement learning.
DTSTAMP:20260718T235458Z
LOCATION:Grand Hall
SUMMARY:Keynote- From Next Token Prediction to Reasoning and Beyond - Jay A
 lammar
URL:https://cfp.pydata.org/london2025/talk/DSAQW9/
END:VEVENT
END:VCALENDAR