DINOv3-L

Search everything

Mentions · 7d0
Mentions · 30d1
All mentions2
First seenSep 24, 2026
Last mentioned23d ago

Timeline

2 articles · newest first

Super-Resolution in The Right Latent Space: A Frozen Vision-Foundation Substrate

RAESR restores images in a frozen DINOv3-L latent space, leading reported super-resolution quality and speed.

Hugging Face daily papersOct 7, 20:00 UTC · 23d agoAI research2

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

FuseReg trains decoders on random encoder-layer subsets, narrowing the reconstruction-generation gap in RAEs.

Hugging Face daily papersSep 24, 20:00 UTC · Sep 24, 2026AI research3 · 2 reads

Appears with

RAESRai model · 1

Entities are extracted by the model from each article. First seen Sep 24, 2026, last mentioned 23d ago. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.