DINOv2
product on 1 show · 1 statements across 1 episodes · said 7 times in 1 episodes since 2024
Mentions by year, every show
tap a year for its mentions
Latent Space 7
2024 7 mentions in 1 episode
every mention on every show, scene by scene, with the transcript →
1 statements about DINOv2, every show
Robicheaux: Adding DINOv2 features degrades multimodal language modeling performance
“As you increase the number of Dynav two features, your model does worse and worse and worse on the actual language modeling task, and that's because Dynav two features were trained completely from a self-supervised manner and completely in image space. It know…”