BEGIN:VCALENDAR
PRODID:-//AddEvent Inc//AddEvent.com v1.7//EN
VERSION:2.0
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:STANDARD
DTSTART:20261101T010000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260308T030000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
DESCRIPTION:Learning from unlabeled video has emerged as a powerful paradigm for training world models without action supervision. However\, existing approaches often rely on monolithic inverse and forward dynamics models\, which struggle to scale in settings where different entities act simultaneously. In this work\, we propose a factored dynamics framework FLAM that decomposes the latent state into in- dependent factors\, each with its own inverse and forward model. \n\n------\n\nCreate your own Add to Calendar links with addevent.com/r/a \n
X-ALT-DESC;FMTTYPE=text/html:Learning from unlabeled video has emerged as a powerful paradigm for training world models without action supervision. However, existing approaches often rely on monolithic inverse and forward dynamics models, which struggle to scale in settings where different entities act simultaneously. In this work, we propose a factored dynamics framework FLAM that decomposes the latent state into in- dependent factors, each with its own inverse and forward model.
------
Create your own Add to Calendar links with addevent.com/r/a
UID:8ea0462042a84e5c816e4df7c8604709addeventcom
SUMMARY:Chang Shi - FLAM: Scaling Latent Action World Models with Factorization (Embodied AI)
DTSTART;TZID=America/Los_Angeles:20251121T110000
DTEND;TZID=America/Los_Angeles:20251121T120000
DTSTAMP:20260910T172327Z
TRANSP:OPAQUE
STATUS:CONFIRMED
SEQUENCE:0
LOCATION:https://meet.google.com/aha-ijie-gzu?hs=122&authuser=0
X-MICROSOFT-CDO-BUSYSTATUS:BUSY
BEGIN:VALARM
TRIGGER:-PT30M
ACTION:DISPLAY
DESCRIPTION:Reminder
END:VALARM
END:VEVENT
END:VCALENDAR