DINOv2: State-of-the-art computer vision models with self-supervised learning (dinov2.metademolab.com) | HN Screenshots

YHacker Newsscreenshots

Screenshot of dinov2.metademolab.com: DINOv2: State-of-the-art computer vision models with self-supervised learning

First screen, captured 3 years ago.

Looks similar

Screenshot of molmo.allenai.org: Molmo: a family of open multimodal AI models

Molmo: a family of open multimodal AI models (molmo.allenai.org)

16 points by jasondavies 2 years ago | 3 comments

Screenshot of frankzliu.com: Vision Transformers Are Overrated

Vision Transformers Are Overrated (frankzliu.com)

62 points by fzliu 2 years ago | 16 comments

Screenshot of rwkv.com: RWKV Language Model

RWKV Language Model (rwkv.com)

147 points by simonpure 1 year ago | 47 comments

Screenshot of arxiv.org: Vision Transformers Need Registers

Vision Transformers Need Registers (arxiv.org)

74 points by felineflock 1 year ago | 9 comments

Screenshot of magvit.cs.cmu.edu: Magvit: Masked Generative Video Transformer

Magvit: Masked Generative Video Transformer (magvit.cs.cmu.edu)

108 points by mfiguiere 3 years ago | 6 comments

Screenshot of arxiv.org: Do transformers need three projections? Systematic study of QKV variants

Do transformers need three projections? Systematic study of QKV variants (arxiv.org)

202 points by Anon84 4 months ago | 39 comments