DINO V3, released August 2025, achieved 88.4% ImageNet accuracy using joint embedding architecture, marking the first time self-supervised vision models matched state-of-the-art weakly-supervised and supervised models on image classification.

factualpending

Speaker

Unidentified Speaker — Yann LeCun's $1B Bet Against LLMs [Part 1] [kYkIdXwW2AE]

Evidence Quote

“DINO V3... achieving a very near state-of-the-art image net accuracy of 88.4% using a joint embedding architecture”

Source

Yann LeCun's $1B Bet Against LLMs [Part 1]— Welch Labs
Created: 8/12/2026, 6:35:53 PM

Your notes

Loading notes...