Yann LeCun and colleagues have developed the V-JEPA (Video Joint Embedding Predictive Architecture) with a second version coming soon that achieves the most promising results of any model so far for learning physical world models.

factualpending

Speaker

Unknown Speaker (video narrator/analyst)

Evidence Quote

“this is where Yanakan talks about his famous VJ architecture... they're actually coming out with version two... this one is probably having the most promising results out of any model so far”

Source

Metas AI Boss Says He DONE With LLMS...— TheAIGRID
Created: 8/11/2026, 5:05:19 AM

Your notes

Loading notes...