BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//OneJoy//events//EN
BEGIN:VEVENT
UID:onejoy-event-39366@onejoy
DTSTAMP:20261006T154255Z
DTSTART:20260918T190000Z
DTEND:20260918T210000Z
SUMMARY:World Models with V-JEPA 2: prediction in representation space
LOCATION:
DESCRIPTION:Welcome to AI Build & Learn\, a weekly AI engineering stream where we pick a new topic and learn by building together.\n\n​This event is about world models with V-JEPA 2\, Meta's self-supervised video model that learns by predicting in representation space instead of generating pixels. We'll load the model\, hide parts of a video clip\, watch it predict the missing pieces as embeddings rather than images\, and measure how good those predictions actually are.\n\n​V-JEPA 2 is trained on internet-scale vide\nhttps://onejoy.io/event/39366
URL:https://onejoy.io/event/39366
END:VEVENT
END:VCALENDAR