Ouro-2.6B-Thinking

Search everything

Mentions · 7d0
Mentions · 30d2
All mentions2
First seenSep 30, 2026
Last mentioned24d ago

Timeline

2 articles · newest first

Decoding Looped Transformers Better for (Almost) Free

Training-free LoopCD improves looped Transformer decoding and can cut recurrent compute by up to 48%.

arXiv cs.AI / cs.LG / cs.CLOct 1, 17:58 UTC · 24d agoAI research3 · 1 read

Decoding Looped Transformers Better for (Almost) Free

LoopCD uses earlier recurrent states for contrastive decoding, boosting looped Transformers while cutting inference FLOPs.

Hugging Face daily papersSep 30, 20:00 UTC · 25d agoAI research2 · 1 read

Appears with

Huginnai model · 2

Entities are extracted by the model from each article. First seen Sep 30, 2026, last mentioned 24d ago. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.