Princeton & UPenn's Recurrent Looped Transformer Carries State Across Tokens
TheTuringPost · x · 2026-10-17
Turing Post highlights a new architecture from Princeton and UPenn: the Recurrent Looped Transformer (RLT), which lets a Transformer carry forward a running hidden state, updating it after each token.
The key idea: longer sequences create a longer chain of computation without requiring more layers per token — a fixed-depth network can trade sequence length for more effective inference compute.
Turing Post is an AI newsletter for engineers and researchers, claiming 100,000+ readers from top AI labs, VC funds and universities.
More from Research
- Terry Tao's Four Types of Mathematization: Heavy AI Use Needs Strong Human Understanding — ravithejads · 2026-10-17
- Princeton's LabOS, Featured in Nature: An AI Co-Scientist for Hypothesis and Experiment Design — MengdiWang10 · 2026-10-17
- 'Tip-of-the-tongue' queries: a blind spot for modern agentic retrieval — bclavie · 2026-10-17
- Tip-of-the-tongue queries emerge as a key test of agentic retrieval systems — ctjlewis · 2026-10-17
- micro1 launches LegalReasonBench to test models on attorney-authored legal matters — douwekiela · 2026-10-17
- LEASH: weak-to-strong escalation matches Claude Opus 5 at 19.2% lower cost on OSWorld — xwang_lk · 2026-10-17