Looped transformers trend traced back to Almeida & Pineda's 1987 recurrent network work
PlisSergey · x · 2026-10-07
With "looped transformers" flooding feeds lately, Sergey Plis points back to a 2016 paper as where he first saw looping in neural networks — old ideas coming back around.
Responding, CSProfKGD notes the 2016 work had even older precedents: Almeida and, independently, Pineda obtained significant results for looping neural networks around 1987 — and that's not even the oldest. The idea of trading depth for recurrence has a decades-long history.
Related event: Looped Transformer Trend Traced Back to Older Papers(3 posts)→
More from Research
- COLM'26: MathDuels self-play benchmark co-evolves difficulty across 19 frontier models — AI4Code · 2026-10-08
- Apple's Stepped MoE: one model scales 1-4B parameters, beating dense counterparts — apple · 2026-10-08
- Apple-style compression: LSP learns which subspaces to drop, cutting LLM weights 70% — Massimo Bini · 2026-10-08
- Cisco ships VLoc Bench: 500 real vulnerabilities to test if AI agents can find buggy code — aminkarbasi · 2026-10-08
- ByteDance Seed Paper Explains Phase Blind Spots in KV Compression Behind DeepSeek's Erratic Long- Context Performance — teortaxesTex · 2026-10-08
- VeriSoftBench: repo-scale Lean 4 verification benchmark, best LLM scores just 41% — xiye_nlp · 2026-10-08