reViT-B/16

Search everything

Mentions · 7d0
Mentions · 30d2
All mentions2
First seenOct 7, 2026
Last mentioned17d ago

Timeline

2 articles · newest first

One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts

A recurrent vision Transformer matches full-depth accuracy with one block and about 70% fewer parameters.

arXiv cs.AI / cs.LG / cs.CLOct 8, 17:58 UTC · 17d agoAI research1 · 1 read

One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts

A recurrent vision Transformer matches full-depth encoder accuracy with about 70% fewer stored parameters.

Hugging Face daily papersOct 7, 20:00 UTC · 18d agoAI research1 · 1 read

Appears with

DINOv2ai model · 2
DeiT IIIai model · 2

Entities are extracted by the model from each article. First seen Oct 7, 2026, last mentioned 17d ago. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.