Princeton and Penn Propose Recurrent Looped Transformer for Length Extrapolation

Princeton and UPenn researchers propose the Recurrent Looped Transformer (RLT), which adds recurrent computation depth for state-tracking tasks, achieving 100% accuracy on parity extrapolation to 256 bits.

2026-10-17 ~ 2026-10-17 · 2 related posts

• Princeton & UPenn propose Recurrent Looped Transformer: 100% parity at 256 bits after training on 40 — TheTuringPost · 2026-10-17
• Princeton/Penn's Recurrent Looped Transformer hits 100% on 256-bit parity extrapolation — TheTuringPost · 2026-10-17