Ankit Sharma

DINO V3 - Self-supervised learning for vision at unprecedented scale

by
A state-of-the-art computer vision model trained with self-supervised learning (SSL) that produces powerful, high-resolution image features.

Add a comment

Replies

Best
Jeremy Yan

Ngl, your AI research (V-JEPA, Llama models) has been way more impressive than most people realize. Are these breakthroughs actually making it into consumer products?