BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//euroscipy-2026//talk//Y7YM3G
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-euroscipy-2026-Y7YM3G@pretalx.com
DTSTART;TZID=CET:20260722T160000
DTEND;TZID=CET:20260722T173000
DESCRIPTION:The intuitions you build fine-tuning text models are surprising
 ly bad guides for other modalities. Training configurations that work well
  for language will silently degrade an image model. Dataset sizes that fee
 l tiny for text are more than enough for adapting a visual style. And audi
 o\, despite seeming like its own world\, follows an image pipeline once yo
 u transform sound into spectrograms\, making what counts as a "token" stra
 nger and more interesting than most people expect. The modalities share a 
 vocabulary (fine-tuning\, adapters\, checkpoints) but not a playbook\, and
  the gaps between them are where the most useful lessons live.\n\nThis tal
 k is a practical\, comparative tour of fine-tuning across four modalities:
  text\, images\, audio\, and video. Rather than focusing on one\, we will 
 look at what changes as you move between them\, how you prepare different 
 data\, which training strategies transfer and which don't\, where the gotc
 has hide\, and what model merging can do for you once training is done. Al
 l examples use Python and the HuggingFace ecosystem with publicly availabl
 e models and datasets. Whether you are a practitioner looking to branch ou
 t beyond NLP or someone curious about what multi-modal fine-tuning looks l
 ike in practice\, you will leave with a mental map of the landscape and en
 ough pointers to start exploring on your own.
DTSTAMP:20260603T195654Z
LOCATION:Room 1.19 (Ground Floor\, Shannon)
SUMMARY:Same Recipe\, Different Results: Fine-Tuning Models Across Modaliti
 es - Ramon Perez
URL:https://pretalx.com/euroscipy-2026/talk/Y7YM3G/
END:VEVENT
END:VCALENDAR