StockDuty ← Dashboard Oct 08, 2026 02:30 AM ET
SignalTech/AI

A Princeton team says its Recurrent Looped Transformer grows the compute path with sequence length at a fixed per-token cost, attacking the fixed-depth limit that gates long-context work. Trained on 4

A Princeton team says its Recurrent Looped Transformer grows the compute path with sequence length at a fixed per-token cost, attacking the fixed-depth limit that gates long-context work. Trained on 4

What happened: Researchers introduced the Recurrent Looped Transformer (RLT), which splits its layers between a parallel causal encoder and a recurrent decoder that merges encoder output with the previous token's final decoder state. Key numbers: Six algorithmic tasks, five splits of eight layers, three seeds. Why it matters: The results indicate that feedback and per-token recurrence drive the gains, and that chunking trades permutation tracking accuracy for parallelism.
Researchers introduced the Recurrent Looped Transformer (RLT), which splits its layers between a parallel causal encoder and a recurrent decoder that merges encoder output with the previous token's final decoder state.
The results indicate that feedback and per-token recurrence drive the gains, and that chunking trades permutation tracking accuracy for parallelism.
Sources