observation · 7 Mar 2024 · 37:28

Yann LeCun observes that the techniques developed at FAIR, DINO and I-JEPA, work well for learning representations from images.

The two techniques we've developed at FAIR, DINO and I-JEPA work really well for that.

Watch at 37:28

Named things

DINO · paper · mentions
I-JEPA · paper · mentions