← Back to KHAO

Tech ·

Recurrent Looped Transformer

2 min read

Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.

◌ Single Source

Prompt and response share one state transition. Encoder memory is prefix-restricted; decoder attention respects its local window. Neither decoder state component resets at the serving boundary.

Known tokens can be encoded in a causal batch.

Key facts

Summary

Recurrent Looped Transformer (RLT) combines a causal encoder with a recurrent decoder that carries its final hidden state and layerwise sliding-window attention (SWA) cache across every prompt and response token. The design brings together latent reasoning with unbounded temporal depth, model–hardware co-design, and model–RL algorithm co-design. Infinite depth refers to an extensible temporal path, not infinite work within a token. Rebuild the full history under current parameters, including prompt states and decoder SWA KV. Here \(M_{\le t}\) is global encoder memory, \(s_t\) is the recurrent output, and \(C_t^D\) contains layerwise decoder KV.

Read full article at yifanzhang-pro.github.io →