Massimiliano Viola
@massiviola01
ML @BedrockRobotics | Ex Stanford, ETH Zurich | Computer Vision • 3D • Generative Models |
Views and geese are my own ⬆️
245 Following 1.2K Followers
Self-supervised learning is the engine behind modern computer vision.
In practice, this used to translate to "let's wait around for the next DINO".
But not anymore: now it's LeJEPA's turn, and you can finally pretrain SSL models on your own data.
Here's an overview ⬇️ 1/n
Show more
JEPA is one of the hottest buzzwords in machine learning right now.
Are you still unsure what that means for video models?
Then I've got you covered!😌
In this week's post, we examine the shift in video self-supervised learning from pixel-space to latent-space modeling.
Show more
