Yifan Zhang

Stories

Princeton researcher proposes Recurrent Looped Transformer for deeper AI reasoning

As of September 2026: Paper published September 2026; no implementation released

Yifan Zhang, a Princeton researcher, posted a technical report September 12 describing the Recurrent Looped Transformer (RLT). It pairs a causal encoder with a recurrent decoder that carries its hidden state and sliding-window attention cache across every token.

Updated Sep 13